Agentic AI, shipped with regulator-grade rigor.

Microsoft Power Platform specialist team — 11 specialists (Test Studio + DAX + pac solution check tester, PBIP-git + DAX + ADO power-bi-engineer, canvas/Power Fx, Power Automate + connectors, Dataverse modeling, model-driven apps, pac CLI + ALM, tenant governance/DLP, PCF…

• 11 Agents
• 23 Skills
• 4 Hooks
• 3 Templates

• copilot-studio-engineerUse this agent for Copilot Studio (formerly Power Virtual Agents) bot design and AI Builder integration — topics, generative answers, knowledge sources, prompts in flows, custom and prebuilt AI Builder models, AI Credit budgeting, bot channels (Teams/web/Direct Line).
• dataverse-architectUse this agent for Dataverse data modeling, security model design, plug-ins, and business rules.
• flow-engineerUse this agent for Power Automate work — cloud flows, desktop flows (RPA), and custom connectors.
• model-driven-engineerUse this agent for model-driven app construction — site maps, app modules, forms (main/quick create/quick view), views, dashboards, charts, business process flows, command bar customization, JS web resources, form scripting via Xrm/formContext APIs.
• pcf-developerUse this agent for Power Apps Component Framework (PCF) custom controls — TypeScript, manifest, lifecycle, build, package, register.
• power-bi-engineerUse this agent for Power BI semantic models, DAX authoring/review, reports, dataflows, PBIP project source control, git integration with Azure DevOps / Azure Repos, deployment strategies (Deployment Pipelines vs ADO pipelines), refresh/gateway troubleshooting, and bridging Power BI artifacts with Power Platform solutions/ALM.
• power-fx-engineerUse this agent for canvas Power App work — screen architecture, Power Fx formulas, components and component libraries, delegation, performance, theming, accessibility, Test Studio, Monitor.
• power-pages-engineerUse this agent for Power Pages (formerly Power Apps Portals) — external-facing sites for anonymous or B2C users.
• power-platform-adminUse this agent for tenant-level Power Platform admin work — environment strategy (Default avoidance, Production / Sandbox / Developer / Trial / Teams), managed environments, environment groups, DLP policies at tenant + environment scope, CoE Starter Kit, licensing audits, capacity reporting (Dataverse storage, API entitlements, Power Automate request limits), tenant-level analytics, sharing limits, weekly digest.
• power-platform-testerUse this agent for Power Platform-specific testing — Power Fx unit/integration tests in Test Studio, canvas-app monitor traces, Power Automate flow tests (`Test → Manually`, telemetry-driven assertions), Dataverse data validation, model-driven app form/business-rule testing, DAX measure correctness and performance, Power BI semantic model VertiPaq diagnostics, and `pac solution check`.
• solution-alm-engineerUse this agent for Power Platform Application Lifecycle Management — pac CLI mastery, source control of unpacked solutions, environment variables, connection references, environment strategy at the solution level (dev/test/prod promotion), and ALM pipelines (in-product Power Platform Pipelines, Azure DevOps + Power Platform Build Tools, GitHub Actions for Power Platform).
• alm-pipeline-designDesign end-to-end ALM pipelines for Power Platform solutions — pac CLI primitives, Azure DevOps multi-stage pipelines, source-control unpacked solutions, env-var + connection-reference promotion across DEV → TEST → UAT → PROD, managed-vs-unmanaged discipline.
• canvas-app-performanceDiagnose and fix Power Fx canvas app performance — delegation as a P1 design constraint, lazy-load patterns, Concurrent() vs sequential, ClearCollect vs collection growth, OnStart vs OnVisible, screen-transition cost, control-count budgets per screen, and the connector-call audit via Monitor.
• code-reviewDeep code audit that finds dead wiring, silent failures, unfinished features, placeholder stubs, bloated files, and unnecessary complexity.
• copilot-studio-bot-designDesign Copilot Studio bots — topic vs generative-answers boundaries, knowledge-source hygiene, trigger-phrase design, slot-filling patterns, escalation-to-human criteria, AI Builder vs prompt-flow vs direct Azure OpenAI decisions, and the test-set discipline that catches regressions on every authoring change.
• dataverse-pluginsUse when developing, registering, or deploying Dataverse plugins (C# server-side extensions).
• dataverse-web-apiUse when programmatically creating, modifying, or querying Dataverse schema and metadata via the Web API (OData v4.0).
• dataverse-web-resourcesUse when creating, deploying, or managing Dataverse web resources for model-driven apps.
• dlp-policy-designDesign tenant Data Loss Prevention policies for Power Platform — business / non-business / blocked classification, environment-scoped vs tenant-wide policies, exemption process, common-connector pitfalls (HTTP, SharePoint, Dataverse, custom connectors), and the "every flow gets re-evaluated on policy change" implication.
• grounding-protocolReduce confident-but-incorrect "I can't do that" claims by forcing agents to verify capabilities before refusing scope.
• maintainability-reviewForward-looking maintainability + evolvability review of a Power Platform solution — understandability, modifiability, testability, evolution readiness, ownership.
• managed-solution-importHardened `pac solution import` plus explicit baseline-aware cloud-flow reactivation for SPN-driven CI/CD — preflight, baseline, import, reactivate, verify. Handles the "managed import leaves flows Draft" trap.
• pbir-ref-integrityReport-wide referential-integrity validator for a PBIR Enhanced report's definition/ tree — catches dangling cross-file references before deployment.
• pcf-controlsUse when building, deploying, or using PowerApps Component Framework (PCF) controls.
• plan-with-teamSpawns an Agent Team to collaboratively plan Power Platform / Dataverse applications.
• power-apps-code-appsUse when building, scaffolding, debugging, or deploying Microsoft Power Apps Code Apps using React, Vue, or TypeScript in VS Code.
• power-automateVeteran-level reference for Power Automate work — expressions, error handling + scopes, child flows, solution-aware flows + connection references, Dataverse triggers, throttling, approvals, performance patterns.
• power-biVeteran-level reference for Power BI — PBIP project structure + git, semantic model design, DAX patterns + performance, deployment pipelines, refresh / gateway troubleshooting, integration with Power Platform solutions / ALM.
• power-pages-permissionsDesign table permissions, web roles, and authentication for Power Pages — anonymous vs authenticated patterns, B2C / Entra-External-ID auth, table-permission scoping (global / contact / account / parental / self), record ownership, and the "row I can see in MDA but not in Pages" debugging playbook.
• record-screenRecord a Chrome browser tab to video via CLI.
• report-visualization-designDesign Power BI reports with a checklist-driven method: question-first, 3-30-300 visual hierarchy, question-type visual selection, 8-point grid layout.
• update-model-driven-appUse when programmatically updating an existing model-driven Power Apps app (including custom pages) in a real environment via service principal.
• visual-qaAI-powered visual QA testing that walks through an app in the browser, records every action with annotated captions (what was done, what should happen), captures screenshots/GIFs, and sends the evidence to Gemini for automated review.
• dataverse-payload-preflightValidate a Dataverse create/update payload against live entity metadata in one pass — nonexistent columns, missing required fields, invalid option-set values, malformed lookup binds, and the owner-not-provided SPN-create trap. Collapses the most common Dataverse write failures into a single pre-flight check.
• check-house-opinions.shcheck-house-opinions.sh PostToolUse hook for Edit | Write | MultiEdit on Power Platform source files.
• validate-flow-action-names.shvalidate-flow-action-names.sh PostToolUse hook for Edit | Write | MultiEdit — warns when Power Automate cloud-flow JSON contains auto-generated action names like 'Compose_2'.
• validate-tmdl-measure-metadata.shvalidate-tmdl-measure-metadata.sh PostToolUse hook for Edit | Write | MultiEdit on TMDL files — validates Power BI measures include description, formatString, and displayFolder.
• nudge-dataverse-preflight.shnudge-dataverse-preflight.sh PreToolUse advisory nudge — opt-in, fail-safe; fires when a Bash command looks like a Dataverse create/update and suggests running dataverse-payload-preflight first.
• maintainability-review-template.mdMaintainability Review Template
• power-bi-copilot-ai-instructions.mdPower BI Copilot AI instructions — custom AI instructions for Copilot in Power BI
• power-bi-copilot-readiness-worked-example.mdPower BI Copilot readiness — worked example and readiness checklist

No items match that filter in this plugin.

Corporate finance & FP&A specialist team — FP&A analyst (budgets, forecasts, variance commentary), financial modeler (3-statement, DCF, scenarios), controller (close, JEs, reconciliations), treasury analyst (cash, covenants, FX), valuation analyst… Ships the controller-autopilot: a governed close-to-report cycle (GAAP statements, COA mapping, reconciliation auto-match, review→approve→lock workflow with an append-only audit log, ELT staging, multi-entity consolidation, per-entity dashboard, close schedules) plus a live-integration tier (OAuth GL connectors + drill-through lineage, multi-currency remeasurement, warehouse/RLS multi-tenant dashboard, IdP-backed segregation of duties).

• 7 Agents
• 23 Skills
• 2 Hooks
• 10 Templates

• audit-prep-specialistUse this agent for audit readiness — PBC (provided-by-client) list management, walkthrough documentation, SOC1 / SOC2 control narratives, deficiency remediation, examiner walkthrough rehearsals.
• board-pack-composerUse this agent for board / investor / lender reporting packs — narrative-first composition, section sequencing, KPI selection, executive-summary patterns.
• controllerUse this agent for month-end / quarter-end close work — JE design and review, account reconciliations, accruals, intercompany, close-calendar mechanics, deferred revenue / prepaids / fixed-asset rolls.
• financial-modelerUse this agent for financial-model work — three-statement models, DCF, scenario / sensitivity, model architecture, model documentation.
• fpa-analystUse this agent for FP&A work — budgeting, rolling forecasts, KPI commentary, variance walks, scenario modeling at the P&L level, headcount and opex planning.
• treasury-analystUse this agent for treasury and cash-management work — 13-week direct cash forecasts, working-capital optimization, debt covenant compliance, FX exposure and hedging, banking operations, debt-schedule mechanics.
• valuation-analystUse this agent for valuation work — business valuation (DCF + comparable companies + precedent transactions), 409A valuations, fairness-opinion support, valuation methodology defense, ESOP / RSU strike-price refreshes.
• author-coa-mappingAuthor and validate the per-entity chart-of-accounts → statement-line mapping — the bespoke, judgment-laden asset that makes the close reusable per company. Coverage-checked. Used by controller.
• board-pack-compositionCompose narrative-first board / investor / lender reporting packs — section sequencing, KPI selection, executive-summary patterns.
• close-approval-workflowThe governed review→approve→lock state machine with enforced segregation of duties and an append-only hash-chained audit log — refuses same-actor approval above threshold and illegal transitions. Used by controller + audit-prep-specialist.
• close-schedulesProduce the recurring close supporting schedules — fixed-asset depreciation rollforward, prepaid amortization, deferred-revenue waterfall — each self-checking so beginning + movements == ending to the cent. Used by controller.
• consolidate-entitiesRoll up N entity trial balances into a group consolidation — a balanced intercompany-elimination journal so IC receivable/payable and IC revenue/COGS net to zero, an eliminations + consolidated worksheet. "Eliminate before you consolidate." Used by controller.
• dcf-valuationRun a defensible discounted-cash-flow valuation — explicit projection period, terminal value (Gordon vs exit-multiple), WACC build, sensitivities, scenario weighting, and the cross-check against trading / precedent multiples.
• driver-based-forecastingBuild and refresh a driver-based rolling forecast that survives FP&A review — driver tree from revenue volume × price, opex by category-driver, working-capital roll, capex schedule, scenario layer.
• finance-elt-stagingNormalize a raw accounting-system trial-balance export (QuickBooks Online / NetSuite / Xero / Sage Intacct) into the one canonical staging schema the close autopilot consumes — stamps entity/currency + a close-period watermark, blocks on an unbalanced export. Used by controller.
• idp-segregationIdP-backed segregation of duties for the close — an optionally IdP-verified identity via OIDC claim + signature verification (alg:none / alg-confusion rejected per RFC 8725), SoD keyed on sub@iss + role claims. Used by controller + audit-prep-specialist.
• kpi-definitionDefine KPIs that survive cross-team disagreement — single owner, single formula, single source of truth, decay-tested, documented in a KPI dictionary.
• live-connectorsWire a live GL/accounting-system OAuth2 extractor (QuickBooks Online / NetSuite / Sage Intacct / Xero) that feeds the canonical trial-balance staging seam — atomic rotating refresh, per-entity lock, error-cause routing, plus drill-through GL lineage. Used by controller.
• model-review7-pass review of financial models — assumptions, mechanics, integrity (BS balances, CF reconciles), hardcodes, error-checks, scenarios, documentation.
• month-end-closeRun a clean month-end / quarter-end close — close-calendar mechanics, JE buckets, reconciliation checklist, exception-triage playbook.
• netsuite-closeWire NetSuite as a controller-autopilot source — OAuth2 M2M (cert-signed JWT, no refresh token) or a time-boxed TBA fallback, a SuiteQL BS-cumulative / IS-period trial balance, tie-out, and a changed-after-sign-off drift check. Used by controller.
• multi-currency-translationTranslate/remeasure one entity's functional-currency trial balance into a presentation-currency (USD) TB before consolidation — current-rate or temporal method, blocks on a failed balancing plug or a highly-inflationary + current-rate combo (ASC 830 vs IAS 29). Used by controller.
• per-entity-dashboardRender a close-package into a self-contained, CSP-safe, theme-aware per-entity dashboard — headline KPIs, IS/BS summaries, reconciliation exceptions, top flux, close-state + traceability badges. Used by controller.
• produce-gaap-statementsTurn a reconciled trial balance + a COA mapping into an income statement, balance sheet, and draft cash flow — classification-tested, blocks on unmapped accounts, with an honest traceability badge. Used by controller.
• reconciliation-automatchAuto-match GL journal lines to sub-ledger / bank lines (exact, tolerance, many-to-one grouped) and auto-certify an account only when its unexplained residual is within materiality — else flag for a human. Used by controller.
• reconciliation-summaryBalance-sheet tie-out (book vs sub-ledger, review-by-exception at materiality) plus a materiality-suppressed period-over-period flux table.
• soc-control-walkthroughDocument a SOC 1 / SOC 2 control walkthrough — control description, test of design vs test of operating effectiveness, evidence-of-control patterns, sampling, exception triage, deficiency severity classification (control deficiency / significant deficiency / material weakness).
• thirteen-week-cash-forecastBuild and operate a 13-week direct-method cash forecast — receipts by source, disbursements by category, week-by-week roll, variance-to-prior-forecast cadence, covenant headroom view, and the trigger thresholds for management action.
• variance-commentaryWrite variance commentary that tells a story instead of restating a table — templates for revenue, GM, opex, EBITDA, FCF with named drivers + materiality threshold applied.
• warehouse-dashboardTurn per-entity close packages into a recurring, warehouse-backed, multi-tenant controller dashboard where one controller sees only their portfolio of entities — deny-all-by-default row-level security, reference dbt marts + Postgres FORCE-RLS. Used by controller + board-pack-composer.
• flag-finance-anti-patterns.shflag-finance-anti-patterns.sh PostToolUse hook for Edit | Write | MultiEdit on finance-conventional files.
• scan-finance-secrets.shscan-finance-secrets.sh PostToolUse hook — scans edited finance files for secret/PII shapes (OAuth secrets, API keys, PEM private keys, AWS/Slack tokens, SSN/PAN/IBAN). Advisory by default; run with --ci for a pre-merge gate.
• account-reconciliation.mdAccount reconciliation — [Account name] / [GL #]
• audit-pbc-tracker.mdAudit PBC tracker — [Audit / Period]
• board-pack-outline.mdBoard pack outline — [Entity] [Period]
• cash-flow-forecast.md13-week direct cash forecast — [Entity]
• connector-config.template.jsonPer-entity ELT connector config scaffold — names of environment variables (and a token-store path) that hold credentials at runtime; never the credentials themselves.
• kpi-pack-template.mdKPI pack — [Entity] [Period]
• model-documentation.mdModel documentation — [Model name]
• month-end-close-calendar.mdMonth-end close calendar — [Entity] [Period]
• tax-calendar.mdTax coordination calendar — [Entity] [Year] — a controller coordination tickler, not tax advice.
• variance-commentary.mdVariance commentary — [Entity] [Period]

No items match that filter in this plugin.

Financial-regulatory & compliance specialist team — 12 jurisdiction specialists covering BMA, Bahamas (4 regulators + FIU), Channel Islands (JFSC/GFSC), Cayman (CIMA), UK PRA, and US federal/state regulators, plus AML/KYC analyst, regulatory-reporting analyst, examination-prep specialist, risk-and-controls specialist, policy & procedure writer…

• 12 Agents
• 10 Skills
• 1 Hook
• 11 Templates

• aml-kyc-analystUse this agent for AML / KYC / sanctions / financial-crime work — customer-onboarding KYC, sanctions screening / hit clearing, EDD (enhanced due diligence), SAR / STR narrative drafting, transaction-monitoring rule tuning.
• bahamas-financial-services-specialistUse this agent for The Bahamas financial-services work across its four statutory regulators + FIU — Central Bank of The Bahamas, SCB, Insurance Commission, Gaming Board, and the FIU.
• bermuda-insurance-specialistUse this agent for Bermuda-domiciled insurance work — BMA Insurance Act 1978 + Rules / Codes, captives (Class 1 / 2 / 3 / 3A / 3B), commercial insurers (Class 4 / 3A / IIGB), long-term insurers (Class A-E), reinsurers, ILS / SPI, SAC, BSCR / ECR / MCR, EBS, CISSA, Solvency II equivalence, BMA filings.
• bma-financial-institutions-specialistUse this agent for Bermuda Monetary Authority (BMA) non-insurance financial-institution work — banking & deposit-taking, investment business, digital-asset business, money-service businesses.
• channel-islands-specialistUse this agent for Channel Islands financial-services work — Jersey (JFSC) and Guernsey (GFSC) across banking, funds, trust, insurance, and AML/CFT frameworks.
• cima-cayman-specialistUse this agent for Cayman Islands Monetary Authority (CIMA) work across all sectors — banking, funds, trust companies, insurance, money-service businesses, and virtual-asset providers.
• examination-prep-specialistUse this agent for regulator examination readiness — PBC list management for exam, walkthrough rehearsals, mock examiner interviews, examiner Q&A drafting, MRA / MRIA / management-letter responses, remediation tracking.
• policy-and-procedure-writerUse this agent for compliance manual / policy / procedure authoring — new policy drafting, P&P refreshes, gap analysis against new regulation, regulator-facing documentation, jurisdictional adaptation of an existing policy.
• regulatory-reporting-analystUse this agent for regulatory filings — FATCA, CRS, supervisory returns, Solvency II QRTs, BMA EBS, US RBC, statutory financial statements, supervisory reports, capital adequacy calculations.
• risk-and-controls-specialistUse this agent for enterprise risk management — risk-framework design, three lines of defense, risk-appetite statements, risk registers, KRI design, control self-assessment, ORM / ERM.
• uk-pra-specialistUse this agent for UK prudential-regulation work — the Prudential Regulation Authority (PRA, part of the Bank of England) rules for banks, building societies, insurers (Solvency UK), and internationally-active firms.
• us-financial-regulation-specialistUse this agent for United States financial-regulatory work across the fragmented federal + state alphabet soup — Federal Reserve, OCC, FDIC, CFPB, SEC, CFTC, FinCEN, and state banking/insurance regulators.
• aml-program-reviewStructured review of an AML program against FATF / FFIEC expectations — the 5 pillars, common findings, regulatory citations with primary sources.
• bma-licensing-classificationClassify a Bermuda (non-insurance) entity into its BMA sector + licence class and resolve its AML/ATF position before an application or regulatory change.
• control-testingCompliance / second-line control testing rubric — design adequacy + operating effectiveness for compliance controls (KYC quality, monitoring rule tuning, training coverage, regulatory-mapping freshness).
• examination-readinessPre-exam playbook for regulator examinations — PBC tracker, walkthrough rehearsal, mock interviews, exam-week posture, MRA / MRIA / management-letter response patterns.
• kyc-edd-reviewKYC file + EDD review playbook — risk-rating logic, BOI / UBO verification, source-of-wealth vs source-of-funds, EDD trigger conditions, file completeness checklist, sign-off chain.
• regulatory-mappingMap internal controls / policies / procedures to specific regulatory citations (regulator + section + paragraph).
• risk-register-buildBuild / refresh an enterprise risk register that survives audit committee scrutiny — three lines of defense assignment, inherent + residual rating math, KRI design, risk-appetite mapping, control coverage, and the half-yearly refresh cadence.
• sanctions-hit-dispositionDisposition framework for sanctions screening alerts — true-match vs false-positive triage, secondary-match evidence chain, escalation criteria, documented-rationale template, list-version capture, and the audit-trail requirements that survive examiner review.
• sar-narrative-draftingDraft SAR / STR narratives that survive regulator review — typology + the W's + what to omit + reviewer sign-off chain.
• supervisory-return-prepPeriod-end supervisory / regulatory return preparation playbook — data lineage, maker-checker, materiality / threshold definitions, common return families (FATCA, CRS, BMA EBS, Solvency II, supervisory returns, capital adequacy / RBC), late-filing protocols.
• scrub-confidential-pre-write.shscrub-confidential-pre-write.sh PreToolUse hook for Write | Edit | MultiEdit.
• aml-program-outline.mdAML program outline — [Entity]
• bma-aml-risk-assessment.mdBMA AML/ATF risk assessment — [Entity]
• bma-change-of-control-notification.mdBMA change-of-control notification template
• bma-licensing-classification-workpaper.mdBMA licensing classification workpaper — [Entity]
• control-narrative.mdControl narrative — [Control ID] [Control name]
• examination-response-tracker.mdExamination response tracker — [Regulator] [Exam type] [Period]
• kyc-edd-workpaper.mdKYC / EDD workpaper — [Customer ID]
• policy-template.md[Policy Name]
• risk-register.mdRisk register — [Entity / Domain]
• sar-narrative-template.mdSAR / STR narrative — [Case ID]
• supervisory-return-checklist.mdPre-submission checklist — [Return name] [Period]

No items match that filter in this plugin.

Web design & build specialist team — web architect (IA, stack, hosting), UX designer (wireframes, flows, conversion), visual designer (brand, typography, tokens), frontend implementer (HTML/CSS/JS, React, Astro, Next), content strategist (copy, microcopy, SEO content)… Now ships the gold-standard-website-pipeline: a nine-gate build checklist (discovery → IA → tokens → content → build → a11y → perf → SEO/AEO → pre-launch) ending in one Go / Conditional / No-go call, plus a non-React static-site build path.

• 7 Agents
• 13 Skills
• 1 Hook
• 8 Templates

• accessibility-auditorUse this agent for accessibility work — WCAG 2.2 AA / AAA audits, ARIA review, keyboard-navigation review, screen-reader testing, color-contrast checks, focus management, reduced-motion / reduced-data accommodation.
• content-strategistUse this agent for content / copy work — site copy, content hierarchy, microcopy, SEO content, content style guide, content audit, content modeling for headless CMS.
• frontend-implementerUse this agent for web frontend implementation — HTML, CSS, vanilla JS, React, Astro, Next, component-library work, responsive patterns, design-token wiring, build integration.
• performance-engineerUse this agent for web performance work — Core Web Vitals (LCP / CLS / INP) diagnosis and tuning, image / font / JS optimization, CDN strategy, caching, third-party hygiene, performance budgets.
• ux-designerUse this agent for UX work — wireframes, user flows, screen-level layouts, conversion design, interaction design, usability heuristics.
• visual-designerUse this agent for visual / brand work — brand systems, typography, color, layout grids, design tokens, component visual style, theming, dark-mode, motion design.
• web-architectUse this agent for web architecture decisions — site architecture, information architecture, tech-stack selection, hosting / CDN, build pipeline, repo structure, content modeling for headless CMS, technical SEO foundations.
• accessibility-reviewWCAG 2.2-aligned accessibility audit — semantics, ARIA, keyboard navigation, color contrast, focus management, motion preferences.
• gold-standard-website-pipelineThe gated pipeline the web-design Team Lead runs on a new marketing site or storefront — nine fail-closed gates (discovery → IA → tokens → content → build → a11y → perf → SEO/AEO → pre-launch), each against numeric WCAG 2.2 / CWV / SEO bars, ending in one Go / Conditional / No-go.
• static-site-implementationBuild a non-React static site: semantic HTML, token-driven CSS, and an SSG-first Astro/11ty/Hugo or plain HTML+CSS build with islands only where earned. Covers reflow to 320px, in-markup performance, and accessible markup. Dispatched by gold-standard-website-pipeline for non-React static stacks.
• content-auditAudit existing site content — full inventory (URL × type × intent × last-updated × owner), scoring against business / user-need / SEO criteria, remediation queue (keep / consolidate / rewrite / retire), and the migration plan when re-platforming.
• conversion-designDesign and audit conversion-focused screens — funnel definition, friction-vs-trust balance, form field selection (every field is a cost), one CTA per screen discipline, social-proof placement, microcopy patterns, and the conversion-rate measurement plan.
• core-web-vitals-tuningDiagnose and improve Core Web Vitals (LCP / CLS / INP).
• design-system-auditAudit an existing brand / design system for consistency, completeness, token coverage, dark-mode readiness.
• design-tokens-scaffoldingScaffold a token system from brand spec to token JSON to CSS variables to framework theme (Tailwind / Shadcn / CSS-in-JS / Theme UI).
• information-architectureDesign site information architecture — sitemap, URL taxonomy, navigation patterns (primary / utility / footer / contextual), card-sort discipline, content model that the IA implies, and the URL-to-template mapping.
• card-tile-uiDesign and implement an Intercom-style card / tile UI — discrete soft-shadowed rounded surfaces on a neutral base with dual-accent theming.
• fluent-react-implementationImplement a Fluent UI v9 + React website end-to-end — set up FluentProvider, turn a brand color into a Fluent palette, scaffold pages with FluentProvider theme tokens.
• seo-technical-auditTechnical SEO sweep — crawlability, indexability, schema markup, sitemaps, OG / Twitter Card metadata, hreflang, structured data.
• third-party-script-hygieneCatalogue and hygiene-audit third-party scripts on a marketing site — performance budget by category (analytics / chat / A/B / fonts / video / social), async-defer patterns, consent-gating (GDPR / CCPA / consent-mode v2), CSP implications, and the periodic re-audit cadence.
• check-web-anti-patterns.shcheck-web-anti-patterns.sh PostToolUse hook for Edit | Write | MultiEdit on web-conventional files.
• accessibility-audit-report.mdAccessibility audit report — [Site / scope]
• content-style-guide.mdContent style guide — [Brand / site]
• design-brief.mdDesign brief — [Project name]
• design-system-spec.mdDesign system spec — [System name] [Version]
• launch-checklist.mdLaunch checklist — [Site / project] [Launch date]
• performance-budget.mdPerformance budget — [Site / page-type]
• seo-audit-report.mdSEO audit report — [Site]
• site-architecture.mdSite architecture — [Site name]

No items match that filter in this plugin.

EdTech-flavored Partner Success Manager team — 6 specialist agents anchored on the PSM lane, plus a centralized CS dashboard integration layer (Planhat/Gainsight/Totango connectors, Power BI / HTML portfolio reports, dbt models).

• 6 Agents
• 16 Skills
• 1 Hook
• 38 Templates

• ferpa-comms-translatorUse this agent for FERPA-aware (and segment-equivalent data-privacy) multilingual, multi-audience partner & end-user communication.
• learning-analytics-analystUse this agent for partner-engagement signal design, health-score architecture, dashboard specs, and metric interpretation.
• partner-profile-curatorUse this agent to maintain the durable partner record — the context that outlives any one PSM seat.
• partner-success-managerUse this agent for EdTech-specialized PSM work — onboarding, adoption, ongoing pulse, day-to-day partner-facing work.
• qbr-composerUse this agent for Quarterly Business Review materials end-to-end — data pull plan → narrative → deck → talk track → followup tracker.
• success-playbook-designerUse this agent to design or refresh PSM plays — renewal plays, expansion plays, recovery (red-flag intervention) plays, advocacy plays.
• adoption-sequencing-k12Sequence K-12 partner adoption activities by stage (newly-implemented / first-year-sustaining / multi-year-mature / pre-renewal) with school-year-phase overlay.
• advocacy-program-designDesign a structured EdTech advocacy program with 5-tier ladder (logo → quote → case study → speaker → peer call).
• cs-platform-integrationBack-end integration contract for a centralized EdTech customer success dashboard sitting on top of Planhat, Gainsight, or Totango connectors.
• daily-action-queueCompute "today's top N accounts" for a K-12 EdTech PSM as a ranked list with next-best-action + confidence + rationale.
• executive-sponsor-mappingMap the partner's buying committee — economic buyer, champion, technical buyer / IT, user-champion, blocker, executive sponsor — across segments (K-12 / higher-ed / corp L&D).
• expansion-play-designDesign expansion motions that fire only when the partner has earned value — 3-gate eligibility (top-quartile health + demonstrable adoption + organizational readiness), value-trigger taxonomy, seat / module / department land-and-expand patterns, internal-champion-armament, ROI-storytelling format, and the "don't sell to bottom-quartile" discipline.
• implementation-90-day-arcRun the 90-day technical-onboarding arc for a newly-contracted EdTech partner — discovery (weeks 1-2) → integration setup (3-4) → train-the-trainer (5-6) → go-live + Day-30 measurement (7-8) → stabilization + PSM handoff (9-12).
• health-report-dashboardBuild a self-contained, Power-BI/Tableau-style HTML portfolio report from partner-health data — KPI cards, sparklines, heatmaps, and a per-partner drill view.
• partner-health-scoringDesign and maintain a partner health score that actually predicts renewal / churn for EdTech partners.
• partner-training-program-designDesign partner-facing training programs for EdTech — train-the-trainer is the only model that scales in K-12.
• psm-dashboard-buildCodex's master roadmap for executing the Partner Success Command Center build — data model, API layer, UI tiers, acceptance tests.
• qbr-compositionCompose a Quarterly Business Review end-to-end — data pull plan, narrative arc, deck outline, talk track, post-QBR commitment tracker.
• recovery-play-designDesign red-flag intervention sequences — root-cause diagnostic before remedy (4 parallel hypotheses), time-bound recovery plan with measurable 30/60/90-day signal targets, escalation criteria (PSM → success leadership → exec sponsor → counsel → churn-prep), the "is this recoverable?" rule, churn-prep workflow when not, and the post-recovery learning capture.
• renewal-play-designDesign renewal motions that earn the renewal instead of negotiating it — T-180/T-120/T-90/T-60/T-30/T-0 sequence, sponsor-confirmation arc, value-evidence pack, multi-thread the buying committee, decision-memo support, expand/maintain/contract decision rule, and segment-specific overlays (K-12 budget cycle, higher-ed academic calendar, corp L&D fiscal year).
• rostering-data-qualityDiagnose rostering / SIS / LMS data-sync issues in EdTech contexts — K-12 (Clever, ClassLink, OneRoster), higher-ed (SIS/LMS), corporate L&D (HRIS/LMS).
• success-plan-authoringAuthor a 30/60/90 day or quarterly success plan for an EdTech partner that has measurable success criteria, named owners, and a defensible cadence.
• flag-psm-anti-patterns.shflag-psm-anti-patterns.sh PostToolUse hook for Edit | Write | MultiEdit on EdTech-PSM artifact files.
• adoption-diagnostic-worksheet.mdAdoption diagnostic worksheet — `<partner_name>`
• annual-partner-review.mdAnnual Partner Review — `<Partner Name>` — `<Year>`
• case-study-draft.mdCase study draft — `<partner_name | "Anonymized Partner">`
• cross-functional-partnership-map.mdCross-functional partnership map — `<partner_name | vendor_name>`
• dashboard-evidence-reference/(template folder — Evidence.dev partner health dashboard reference implementation)
• dashboard-streamlit-reference/(template folder — Streamlit partner health dashboard reference implementation)
• dashboard-tier-0.5-reference/(template folder — Snowflake + dbt + dynamic-tables partner success pipeline reference)
• escalation-memo.mdEscalation Memo — `<Partner Name>` — `<short risk description>`
• health-score-dashboard.mdHealth-Score Dashboard — Spec
• implementation-90-day-plan.mdImplementation 90-day plan — `<partner_name>`
• onboarding-checklist.mdOnboarding Checklist — First 90 Days — `<Partner Name>`
• partner-pickup-brief.mdPartner pickup brief — `<partner_name>`
• partner-profile.mdPartner Profile — `<Partner Name>`
• qbr-deck-outline.mdQBR Deck Outline — `<Partner Name>` — `<Quarter>`
• reference-pipeline-tracker.mdReference customer pipeline tracker
• renewal-decision-memo.mdRenewal decision memo — `<partner_name>`
• success-plan.mdSuccess Plan — `<Partner Name>`
• touchpoint-log.mdTouchpoint Log — `<Partner Name>`
• train-the-trainer-curriculum.mdTrain-the-trainer curriculum — `<partner_name>`

No items match that filter in this plugin.

Data-platform team — 4 specialist agents (database-setup-guide, etl-pipeline-engineer, dashboard-builder, connector-developer) that guide cloud-database setup, ELT pipelines, embedded dashboards, multi-tenant RLS, and identity resolution…

• 4 Agents
• 13 Skills
• 1 Hook
• 18 Templates

• connector-developerUse this agent for custom Airbyte connector authoring when an ELT vendor doesn't ship a connector for the source the engagement needs.
• dashboard-builderUse this agent for interactive dashboard front-end generation — Evidence.dev (marketing-site portfolio), Apache Superset / Metabase OSS (client deliverable), Cube + Next.js + Tremor + Recharts + shadcn/ui (productized SaaS), Power BI Embedded F-SKU (Microsoft-stack engagements).
• database-setup-guideUse this agent for cloud-database setup guidance — Supabase, Neon, RDS, Azure SQL, Fabric, DuckDB, MotherDuck, Snowflake, Databricks, Turso.
• etl-pipeline-engineerUse this agent for ELT pipeline design and configuration — Airbyte, Fivetran, n8n, custom integrations.
• cloud-database-comparisonCompare cloud databases (Supabase, Neon, RDS, Azure SQL, Fabric, DuckDB, MotherDuck, Snowflake, Databricks, Turso) for an SMB consulting engagement — pricing tables with retrieval dates, setup-complexity matrix, when-to-pick guidance.
• connector-configurationConnector-specific configuration patterns for ELT pipelines — QuickBooks OAuth + rate-limit handling, Stripe webhook + batch hybrid, Salesforce Bulk API 2.0, HubSpot API v3, GA4 BigQuery export, Shopify GraphQL Admin API.
• cross-system-identity-resolutionStitch the same real-world entity across multiple source systems into one canonical customer record — deterministic + probabilistic matching, survivorship rules, confidence scoring.
• cube-schema-scaffoldingScaffold Cube semantic-layer schemas with mandatory `securityContext` baked in for multi-tenant customer-facing dashboards.
• dashboard-performance-tuningTune interactive-dashboard performance against a per-widget-class budget — Cube pre-aggregation design, Postgres / DuckDB materialized views, cache layers (Cube + Redis + browser TanStack Query), the per-widget profile loop (measure → identify the slow stage → fix at the lowest-cost layer).
• data-quality-testsDesign data-quality tests that catch real bugs — uniqueness / not-null / referential integrity / freshness / row-count drift / value-range / cross-source reconciliation.
• dbt-project-scaffoldingScaffold a dbt project that ships — sources → staging → intermediate → marts → metrics layer discipline, generic + custom tests, doc-blocks for every model, exposure tracking, RLS-safe role separation (build-role vs query-role), CI shape (`dbt build` on PR), and a dev/prod env-promotion shape.
• embed-csp-and-iframe-sandboxingConfigure CSP `frame-ancestors`, iframe `sandbox` attributes, postMessage origin checks, and web-component shadow-DOM boundaries for embedded dashboards.
• jwt-embed-issuanceCanonical 2026 JWT-embed flow for dashboard embedding — required claims (`sub`, `tenant_id`, `iat`, `exp`, `iss`, `aud`, `nonce`), tool-specific verification (Superset guest tokens, Metabase JWT URLs, Cube Authorization Bearer, Power BI MSAL-via-AAD), 5-15 min expiration policy, cross-boundary denial test contract.
• multi-tenant-migrationMigrate a single-tenant database / dashboard stack to multi-tenant — `tenant_id` column propagation + backfill, RLS / semantic-layer scope rules introduced post-hoc, JWT-claim shape migration, embed-token cutover plan with parallel + backout window, and the mandatory cross-boundary denial test before flipping the switch.
• rls-policy-authoringAuthor Postgres Row Level Security policies (force-on, CI-deployed, denial-tested) for multi-tenant dashboards.
• stack-selectionSelect a dashboard-engagement stack via the Case A/B/C/D Mermaid decision tree (Portfolio / Per-client / Productized SaaS / Pipes-only) — surfaces the per-viewer-pricing-trap heuristic, recognizes the EdTech LMS connector-gap, returns a populated `stack-decision-record.md`.
• support-ticket-normalizationTake vendor-specific raw support-ticket tables (Zendesk, Freshdesk, Intercom) and normalize to a canonical ticket schema for cross-platform analytics.
• flag-data-platform-smells.shflag-data-platform-smells.sh PreToolUse hook for Edit | Write | MultiEdit on data-platform artifact files.
• airbyte-source-config.yamlAirbyte source configuration starter
• cube-schema-starter.ymlCube schema starter — multi-tenant analytics
• dashboard-engagement-checklist.mdDashboard engagement checklist — {{Engagement / Client Name}}
• database-schema-starter.sqlMulti-tenant database schema starter
• dbt-project-starter/(template folder — dbt project scaffold: sources, staging, marts, tests, profiles)
• evidence-portfolio-page.md{{Case Study Title}}
• jwt-issuer.tsJWT embed token issuer — canonical 2026 implementation
• metabase-interactive-embed.tsx.mdMetabase Interactive Embedding (React component) — seam-marked stub
• power-bi-embedded-react.tsx.mdPower BI Embedded App-Owns-Data (React component) — seam-marked stub
• rls-cross-tenant-test.sqlRLS cross-tenant denial test suite
• stack-decision-record.mdStack decision record — {{Engagement / Client Name}}
• superset-embed-iframe.tsx.mdSuperset embed (React iframe component) — seam-marked stub

No items match that filter in this plugin.

Engineering management team — 4 specialist agents covering the EM lead, people and growth, delivery and execution, and technical health lanes. Built for solo EMs and consultants managing small engineering teams with structured 1:1s, evidence-based performance reviews, hiring loops, flow diagnostics, and tech-debt decisions.

• 4 Agents
• 5 Skills
• 1 Hook
• 4 Templates

• engineering-manager-leadUse this agent to diagnose whether a team's core challenge stems from people growth, delivery execution, or technical health — maps the first moves with owners and dates.
• people-and-growth-managerUse this agent for 1:1 meetings beyond status updates, evidence-based performance reviews, and underperformance diagnosis — examines system factors before drawing conclusions about a person.
• delivery-and-execution-managerUse this agent to diagnose flow problems, interpret DORA metrics as system signals, and address unsustainable on-call practices — always fixing the system rather than pressuring people.
• technical-health-managerUse this agent to evaluate tech-debt paydown as a sized carrying cost against roadmap priorities, or diagnose whether codebase slowness is felt pain or measured degradation.
• decide-tech-debtDecide whether to pay down specific tech-debt by quantifying its business impact and payback period against roadmap priorities — produces a structured memo with numbered recommendations and capacity slices.
• design-hiring-loopDesign a structured hiring loop — rubric, consistent interview questions, evidence-based scoring, and a debrief that surfaces dissent over a vibe-based process.
• improve-team-flowDiagnose unpredictable delivery by measuring lead time and WIP to identify system constraints — applies sustainable fixes rather than velocity pressure.
• run-one-on-oneConduct a meaningful 1:1 meeting focused on the engineer's priorities rather than status updates — agenda scaffolds, talking-point prompts, and note-taking.
• write-performance-reviewDraft a performance review using concrete, dated behavioral evidence — bias-checked and growth-oriented, designed as a management tool rather than a final verdict.
• flag-engineering-management-antipatterns.shflag-engineering-management-antipatterns.sh PostToolUse advisory hook — flags anti-patterns in engineering management deliverables.
• growth-plan.mdEngineer growth plan template
• one-on-one-agenda.md1:1 meeting agenda template
• performance-review.mdPerformance review template
• tech-debt-decision-memo.mdTech-debt decision memo template

No items match that filter in this plugin.

Desktop-app-engineering team — 4 specialists covering architecture (Electron vs Tauri vs native vs PWA, process/security model, distribution), Electron implementation (hardened baseline, contextBridge IPC), Tauri implementation (Rust core, capabilities allow-list), and the platform layer (code-signing, notarization, safe auto-update, native OS integration).

• 4 Agents
• 5 Skills
• 1 Hook
• 4 Templates

• desktop-architectUse for desktop architecture: the Electron-vs-Tauri-vs-native-vs-PWA decision by the app's real needs (bundle size, native depth, team, security), the process/security model, the update + distribution strategy, and where the line sits between the renderer UI and the privileged backend.
• desktop-platform-engineerUse for the desktop platform layer: code-signing + notarization (Windows Authenticode/EV; macOS Developer ID + notarytool + staple), safe signed auto-update (channels, staged rollout, rollback, version floor), and native OS integration (tray, menus, notifications, deep links, secure storage).
• electron-engineerUse for Electron implementation: the main/preload/renderer model, the hardened baseline (contextIsolation on, nodeIntegration off, sandbox, strict CSP), a narrow contextBridge + validated ipcMain handlers, window/lifecycle, and the build (electron-builder/Forge).
• tauri-engineerUse for Tauri implementation: the Rust core + system-webview model, #[tauri::command] handlers with validated input, the capabilities/permissions allow-list (v2) scoping what the frontend can call, state management, sidecars, and the small-bundle/secure-by-default posture Tauri rewards.
• desktop-framework-choiceDecide Electron vs Tauri vs native vs PWA by the app's real needs (bundle size, native-API depth, team skills, security surface, update needs), then set the process/security model and the renderer/backend boundary.
• electron-security-hardeningHarden an Electron app to the secure baseline — contextIsolation on, nodeIntegration off, sandbox on, a strict CSP, no remote module — and bridge to the OS through a narrow typed contextBridge backed by validated ipcMain handlers.
• native-os-integrationWire native OS integration the way each platform expects — tray/menu-bar, application menus, notifications, file associations, custom-scheme deep links routed through a single-instance lock, and secrets in the OS credential store.
• packaging-signing-and-updatesPackage, code-sign, and notarize a desktop app for Windows (Authenticode/EV) and macOS (Developer ID + notarytool + staple), and ship a safe signed auto-update (signature verified before apply, channels, staged rollout, rollback, version floor).
• tauri-capabilities-and-commandsExpose native capability in Tauri through #[tauri::command] handlers with validated input, authorized by a least-privilege capabilities/permissions allow-list (v2) scoped to the windows that need it — no wildcard fs/shell scopes.
• check-desktop-engineering-anti-patterns.shcheck-desktop-engineering-anti-patterns.sh PostToolUse advisory hook — flags anti-patterns in desktop app engineering (unsafe Electron settings, wildcard Tauri capabilities, unsigned build artifacts).
• framework-decision.mdDesktop framework decision template
• ipc-security-review.mdIPC security review template
• native-integration-plan.mdNative OS integration plan template
• release-signing-checklist.mdRelease signing and notarization checklist template

No items match that filter in this plugin.

CLI-tooling-engineering team — 4 agents for command-line tools and TUIs: the command/subcommand + flag/positional surface, config precedence (flags > env > file > default), the output contract (human by default, --json on demand, exit codes as API, data→stdout/diagnostics→stderr, NO_COLOR/TTY detection), TUI frameworks (Ink / Bubble Tea / Textual / ratatui) with non-TTY fallback, shell completions, and distribution (single static binary, Homebrew / Scoop / winget / npm / pipx).

• 4 Agents
• 5 Skills
• 1 Hook
• 4 Templates

• cli-architectUse for CLI architecture decisions: command surface design, the flag/positional/subcommand model, config-precedence hierarchy, and where the line sits between the shell contract and application logic.
• cli-implementation-engineerUse for CLI implementation: argument parsing (clap, cobra, argparse, commander), the output contract (human-readable default, --json mode, exit codes as API, data→stdout/diagnostics→stderr), signal handling, and stdin/pipe support.
• tui-engineerUse for TUI implementation with Ink (React), Bubble Tea (Go), Textual (Python), or ratatui (Rust): layout, component model, keyboard navigation, a non-TTY fallback mode, and the accessibility floor.
• cli-distribution-engineerUse for CLI distribution: single static binary builds, package manager publication (Homebrew formula / Scoop manifest / winget / npm / pipx), --version surfacing, and a safe auto-update path.
• cli-design-and-arg-parsingDesign the command surface — subcommand tree, flags vs positional args, required vs optional — and wire argument parsing to produce a validated, typed config object before any side-effectful work begins.
• output-and-exit-code-contractEstablish the CLI output contract: human-readable default with --json mode, data to stdout, diagnostics to stderr, NO_COLOR/TERM/TTY detection, and a complete exit-code table that callers can script against.
• shell-completions-and-configGenerate shell completions (bash, zsh, fish, PowerShell) from the command spec, and implement config-file loading with the correct precedence: flags > env vars > config file > compiled default.
• tui-designDesign TUI layout and component model: screen decomposition, keyboard/mouse event routing, focus management, a non-TTY graceful fallback, and accessibility considerations for screen reader users.
• cli-distribution-and-packagingPackage and distribute a CLI tool: single-binary cross-compilation, Homebrew formula, Scoop manifest, winget, npm/pipx wrappers, code-signing where required, and a --version + update-check path.
• check-cli-engineering-anti-patterns.shPostToolUse advisory hook — flags anti-patterns in CLI tool implementations (missing exit codes, writing diagnostics to stdout, missing --json mode).
• cli-design-brief.mdCLI design brief template
• output-contract.mdCLI output contract template
• distribution-checklist.mdCLI distribution checklist template
• tui-spec.mdTUI specification template

No items match that filter in this plugin.

Realtime-collaboration-engineering team — 3 agents for multiplayer / collaborative-editing systems (Figma/Notion/Docs style): the merge model (CRDT vs OT vs last-writer-wins, by data shape), the shared-document model, offline edits + reconnection/merge, presence & awareness kept out of the persisted document, transport (WebSocket vs WebRTC, SFU vs mesh), and scaling the sync server (doc sharding, snapshots/compaction, access control at the boundary).

• 3 Agents
• 5 Skills
• 1 Hook
• 4 Templates

• collab-architectUse for collaborative-system architecture: the CRDT-vs-OT-vs-LWW decision by data shape, the document model, the transport topology (client-server vs SFU vs mesh), and how persistence, access control, and the sync server fit together.
• sync-engine-engineerUse for sync engine implementation: operation encoding, merge logic (Yjs/Automerge/custom CRDT or OT), op-log compaction, snapshot/load cycles, and the server-side fan-out and persistence layer.
• presence-and-transport-engineerUse for the presence/awareness layer (cursors, selections, who's-online) kept strictly out of the persisted document, and for the transport layer (WebSocket multiplexing, WebRTC signaling + SFU/mesh, reconnection/backoff).
• choose-crdt-or-otChoose between CRDT (Yjs, Automerge) and OT (ShareDB) — or last-writer-wins — by data shape, team expertise, and server topology, with a Mermaid decision tree and concrete tradeoff table.
• design-the-document-modelDesign the shared document model: type selection (text/map/array/rich-text), how sub-documents compose, what goes into the CRDT vs what stays in application state, and the serialization contract for persistence.
• handle-offline-and-reconnectionHandle offline edits and reconnection: local op buffering, rebase/merge on reconnect, conflict UX, and the client-side state machine (online → offline → syncing → online).
• build-presence-and-awarenessBuild the presence/awareness layer (cursors, selections, who's-online, typing indicators) as ephemeral state entirely separate from the CRDT document — so it doesn't bloat history, can be lost on disconnect, and never conflicts.
• scale-the-sync-serverScale the sync server: doc sharding by room/doc-id, snapshot + compaction to bound op-log growth, horizontal fan-out via pub/sub (Redis/NATS), and access control enforced at the boundary before ops reach the doc.
• check-collaboration-anti-patterns.shPostToolUse advisory hook — flags anti-patterns in collaborative system implementations (presence state in persisted document, missing offline handling, unbounded op-log growth).
• merge-model-decision.mdMerge model (CRDT vs OT) decision template
• sync-architecture.mdSync engine architecture template
• offline-reconnection-plan.mdOffline and reconnection handling plan template
• presence-spec.mdPresence and awareness specification template

No items match that filter in this plugin.

Network-engineering team — 2 agents (network-architect, network-operations-engineer) for the ENTERPRISE network layer below the cloud VPC: campus/datacenter/WAN topology, routing (OSPF/BGP/EIGRP/static) and switching (VLANs, STP, LACP, VXLAN/EVPN), IP addressing/IPAM and DNS/DHCP, segmentation + zero-trust network access (microsegmentation, NAC, SASE/SD-WAN), load balancing, redundancy/HA (HSRP/VRRP, dual-homing), and day-2 ops (change windows, troubleshooting the OSI stack, observability/NetFlow).

• 2 Agents
• 5 Skills
• 1 Hook
• 3 Templates

• network-architectUse for enterprise network DESIGN — campus/DC/WAN topology, routing & switching, VLAN/VXLAN segmentation, zero-trust network access, IP addressing/IPAM, redundancy/HA. Protocol-before-vendor-CLI; design-before-config.
• network-operations-engineerUse for day-2 network OPERATIONS — bottom-up OSI troubleshooting, staging reversible changes (window, pre/post checks, rollback), DNS/DHCP/IPAM + load-balancer operation, and observability (NetFlow/SNMP/syslog).
• design-network-topologyDesign a campus/datacenter/branch/WAN network topology by traversing the topology decision tree, then return the recommended topology, an IP addressing plan, the redundancy/failure model, and a labelled diagram description.
• design-segmentation-and-zero-trustDesign network segmentation and a zero-trust network access posture — the segment plan (VLANs/VRFs/microsegmentation), the east-west + north-south policy model, the NAC/802.1X posture, and the enforcement point.
• plan-network-changeTurn a network change (routing/VLAN/firewall/cutover) into a staged, reversible plan — blast-radius assessment, change window, pre-checks, staged steps with verification gates, and a tested rollback.
• select-routing-protocolChoose the right routing protocol (static, OSPF, EIGRP, IS-IS, BGP) for a given boundary and scale by traversing the routing-protocol decision tree, then return the recommendation and design knobs.
• troubleshoot-connectivityIsolate a network connectivity fault methodically, bottom-up the OSI stack, naming the specific isolating test and confirming command at each layer, then return the ranked most-likely fault.
• flag-network-smells.shPostToolUse advisory hook — flags any/any rules, telnet, and changes staged without a change window.
• network-change-plan.mdNetwork change plan template
• network-design-document.mdNetwork design document template
• troubleshooting-runbook.mdConnectivity troubleshooting runbook template

No items match that filter in this plugin.

Robotics & autonomous-systems engineering team — 3 agents (robotics-architect-lead, ros-motion-planning-engineer, perception-and-autonomy-engineer) across the three engines of a robot program: system architecture (ROS 2 computation graph & DDS, compute/sensor selection, the real-time vs non-real-time split, safety architecture, sim-to-real), the motion stack (ROS 2 nodes/topics/actions, MoveIt/Nav2 planning, kinematics, PID/MPC control, coordinate frames/TF), and perception & autonomy (sensor fusion, SLAM, EKF state estimation, localization, behavior-tree/state-machine autonomy).

• 3 Agents
• 4 Skills
• 2 Templates

• robotics-architect-leadUse for robot system architecture: ROS 2 graph & DDS/QoS, compute & sensor selection, the real-time vs non-real-time split, safety architecture, and sim-to-real strategy.
• ros-motion-planning-engineerUse for ROS 2 motion: nodes/topics/actions, motion planning (MoveIt/Nav2), kinematics, control loops (PID/MPC), and coordinate frames/TF.
• perception-and-autonomy-engineerUse for perception & autonomy: sensor fusion, SLAM, state estimation/EKF, object detection, localization, and behavior (behavior trees / state machines).
• ros2-architecture-and-ddsDesign the ROS 2 computation graph: nodes and their boundaries, topics/services/actions, the RMW/DDS layer and per-topic QoS, executors & callback groups, node composition, and the real-time vs non-real-time split.
• motion-planning-and-controlBuild the motion stack: Nav2 for mobile-base navigation vs MoveIt for manipulator planning, kinematics and the TF tree, trajectory generation, ROS 2 actions for long-running motion, and control loops (PID vs MPC).
• perception-and-state-estimationBuild the perception stack: sensor fusion of complementary modalities (lidar/camera/IMU/odometry/GPS), SLAM vs known-map localization, EKF/UKF/particle-filter state estimation, and behavior-tree autonomy that fails safe.
• sim-to-real-and-safetyCross the sim-to-real gap and build the safety architecture: simulate every behavior before actuating, close the reality gap, and make safety a system property — monitored safe state, bounded actuation, degraded modes.
• robot-system-architecture.mdRobot system architecture record template
• ros2-node-graph-plan.mdROS 2 node-graph plan template

No items match that filter in this plugin.

AR/VR/XR spatial-computing engineering team — 3 agents (xr-architect-lead, xr-interaction-engineer, spatial-rendering-engineer) for the three engines of an XR build: system architecture (target selection across standalone / PC-VR / WebXR / mobile-AR, engine choice across Unity / Unreal / native / WebXR, OpenXR-first strategy, perf-budget and comfort/safety architecture), interaction (hand / controller / gaze input, sim-sickness-aware locomotion, 3D UI, grab/physics, accessibility), and spatial rendering & performance (frame budget, reprojection, foveated rendering, occlusion/anchors/passthrough for AR, draw-call batching, thermal).

• 3 Agents
• 4 Skills
• 2 Templates

• xr-architect-leadUse for XR system architecture: target selection (standalone/PC-VR/WebXR/mobile-AR), engine choice (Unity/Unreal/native/WebXR), OpenXR, perf-budget architecture, comfort/safety.
• xr-interaction-engineerUse for XR interaction design/implementation: hand, controller, and gaze input, locomotion, 3D UI, grabbing/physics, and accessibility.
• spatial-rendering-engineerUse for XR rendering and performance: frame budget, reprojection/ASW, foveated rendering, occlusion/anchors/passthrough (AR), draw-call batching, and thermal budget.
• xr-target-and-engine-selectionChoose the XR target platform (standalone headset vs PC-VR vs WebXR vs mobile-AR) and engine (Unity / Unreal / native-OpenXR / WebXR) on the use-case, audience device, and distribution channel.
• xr-interaction-and-locomotionDesign and implement XR interaction: hand / controller / gaze input on an OpenXR action abstraction, locomotion chosen for comfort, reachable and readable 3D UI, and intentional grab/physics.
• spatial-rendering-and-performanceHold the XR frame budget: derive the per-eye ms target from the device refresh rate, profile on device, cut draw calls / overdraw / fill rate in order, and use foveated rendering and reprojection as headroom not a crutch.
• comfort-safety-and-accessibilityTreat XR comfort, physical safety, and accessibility as requirements: sustained framerate, comfortable locomotion, design for the tracking volume / guardian / passthrough, and accessibility options as defaults.
• xr-perf-budget-plan.mdXR perf-budget plan template
• xr-project-architecture.mdXR project architecture template

No items match that filter in this plugin.

Computer-vision engineering team — 3 agents for a production vision build: cv-systems-architect (task framing across classification / detection / segmentation / OCR / tracking / VLM, data & annotation strategy, build-vs-API and deployment-target choice, eval-metric design — mAP / IoU / precision-recall), cv-model-engineer (dataset curation, augmentation, transfer learning, model selection across YOLO / DETR / SAM / CLIP / ViT, active learning, the eval harness, drift), and vision-deployment-engineer (quantization / distillation, ONNX / TensorRT / CoreML / TFLite export, edge/embedded targets, streaming-video pipelines, latency).

• 3 Agents
• 4 Skills
• 2 Templates

• cv-systems-architectCV system architecture: task framing (classification/detection/segmentation/OCR/pose/tracking/VLM), data & annotation strategy, model-family & build-vs-API choice, deployment-target & eval-metric design. NOT training code → cv-model-engineer; NOT inference/serving → vision-deployment-engineer.
• cv-model-engineerCV model engineering: dataset curation, transfer learning/fine-tuning, model selection (YOLO/DETR/SAM/CLIP/ViT), loss & metric design, active learning, class imbalance, eval harness, drift detection. NOT task/metric framing → cv-systems-architect; NOT serving → vision-deployment-engineer.
• vision-deployment-engineerCV inference optimization & deployment: quantization/pruning/distillation, export/runtime (ONNX/TensorRT/CoreML/TFLite/OpenVINO), edge/embedded (Jetson/NPU/Coral), batching, streaming-video pipelines, latency budgets. NOT model training → cv-model-engineer; NOT task framing → cv-systems-architect.
• cv-task-and-data-strategyFrame the computer-vision task (classification / detection / segmentation / OCR / pose / tracking / VLM) on the decision the system must make, choose the metric that mirrors the business cost, decide build-vs-fine-tune-vs-API jointly with the deployment target, and design the data & annotation strategy. Model/metric specifics verify-at-use; no PII, no image data stored.
• cv-model-training-and-evaluationCurate and augment the dataset, choose and fine-tune the model (YOLO / DETR / SAM / CLIP / EfficientNet / ViT) on the task and target budget, design the loss and metric to match the cost, spend the annotation budget with active learning, handle class imbalance, and build an eval harness you can trust with per-slice metrics and drift detection. Model/checkpoint specifics verify-at-use; no PII.
• vision-inference-optimizationMake a trained vision model fit and run on its target: budget latency on the real device, optimize in order of leverage (quantization INT8/FP16 with calibration, then pruning, then distillation), export to the runtime the target uses (ONNX / TensorRT / CoreML / TFLite / OpenVINO), and re-check accuracy against the operating point after every step. Device/runtime numbers verify-at-use; no PII.
• video-pipeline-and-edge-deploymentDesign streaming-video pipelines that hold the frame budget — frame sampling / keyframe strategy, ROI cropping, tracking-by-detection so the detector doesn't run every frame, and batching where latency allows — and deploy to edge/embedded targets (Jetson, mobile NPU, Coral) with the camera/sensor capture and pre-processing counted inside the budget. Device numbers verify-at-use; no PII.
• cv-project-architecture.mdComputer-vision project architecture template
• cv-evaluation-plan.mdComputer-vision evaluation plan template

No items match that filter in this plugin.

Conversational voice-AI engineering team — 3 agents for production real-time voice agents: voice-ai-architect (cascade STT→LLM→TTS vs speech-to-speech, the latency budget, turn-taking / barge-in / endpointing, channel choice, build-vs-platform across Twilio / Vapi / Retell / LiveKit / Pipecat, guardrails), speech-pipeline-engineer (ASR & TTS provider choice, streaming transcription, VAD/endpointing, diarization, prosody/SSML, codecs, noise, WER), and dialog-and-integration-engineer (state, LLM orchestration and mid-call tool calling, SIP/PSTN telephony, IVR/DTMF, call routing, flow testing and eval).

• 3 Agents
• 4 Skills
• 2 Templates

• voice-ai-architectVoice-AI system architecture: cascade (STT→LLM→TTS) vs speech-to-speech, end-to-end latency budget, turn-taking/barge-in/endpointing, channel choice, build-vs-platform (Twilio/Vapi/Retell/LiveKit/Pipecat), guardrails/fallback. NOT ASR/TTS model tuning → speech-pipeline-engineer.
• speech-pipeline-engineerASR & TTS engineering: STT/TTS provider choice (Whisper, Deepgram, ElevenLabs), streaming transcription, VAD & endpointing tuning, diarization, prosody/SSML, codecs & sample rates, noise robustness, wake-word, word error rate. NOT system architecture/latency budget → voice-ai-architect.
• dialog-and-integration-engineerVoice dialog + integration: dialog/state management, LLM orchestration + mid-call tool calling, SIP/telephony integration, IVR/DTMF, call routing/transfer, conversation-flow testing & eval (task success, WER, latency). NOT ASR/TTS model tuning → speech-pipeline-engineer.
• voice-agent-architecture-and-latencyChoose the voice-agent pipeline shape (cascade STT→LLM→TTS vs speech-to-speech), the channel (telephony / web / SDK), and the build-vs-platform bet (Twilio / Vapi / Retell / LiveKit / Pipecat), then allocate the end-to-end latency budget per hop and design the turn-taking / barge-in / fallback model. Model/platform/latency specifics verify-at-use.
• speech-recognition-and-synthesisEngineer the ASR and TTS layer of a voice agent: choose STT/TTS providers on the channel (narrowband telephony vs wideband web), languages, streaming support, WER, and cost; stream transcription and synthesis to cut latency; tune VAD/endpointing; handle diarization, prosody/SSML, codecs & sample rates, and noise robustness; and measure WER on real audio. Provider/version specifics verify-at-use.
• dialog-management-and-tool-callingDesign the dialog layer of a voice agent: explicit dialog-state modeling, LLM orchestration, context/window management over a long call, and mid-call function/tool calling that hides latency with natural fillers and treats tool failure as a first-class branch. Design the unhappy path (silence, misrecognition, tool failure, confusion) before the happy path. Provider/SDK specifics verify-at-use.
• telephony-and-call-flow-integrationIntegrate a voice agent with real telephony and validate it: SIP/PSTN trunking and media handling, WebRTC for web/app, DTMF capture (in-band vs RFC 2833/SIP INFO), IVR-vs-conversational per step, call routing and warm/cold human transfer with context, and a voice-agent eval harness scoring task success, WER, end-to-end latency, and interruption handling on representative recorded calls. Protocol/provider specifics verify-at-use.
• voice-agent-architecture.mdVoice-agent architecture template
• voice-latency-budget.mdVoice latency budget template

No items match that filter in this plugin.

Streaming-media (video/audio) engineering team — 3 agents for a streaming build: media-streaming-architect (VOD vs live, protocol choice across HLS / MPEG-DASH / CMAF / WebRTC / LL-HLS, packaging + origin/edge, single vs multi-CDN, DRM across Widevine / FairPlay / PlayReady, ABR-ladder philosophy, cost), transcoding-pipeline-engineer (codec choice across H.264 / HEVC / AV1 / VP9, FFmpeg pipelines, per-title & ABR-ladder encoding, GPU vs CPU, CMAF packaging, captions, audio & loudness), and playback-and-delivery-engineer (player integration across hls.js / dash.js / Shaka / ExoPlayer / AVPlayer, ABR tuning, QoE metrics, low-latency live, client DRM, CDN cache tuning).

• 3 Agents
• 4 Skills
• 2 Templates

• media-streaming-architectUse for streaming-media architecture: VOD vs live, protocol (HLS/DASH/CMAF/WebRTC/LL-HLS), packaging, origin/edge, single vs multi-CDN, DRM strategy, ABR-ladder philosophy, cost & scale. NOT encoding/FFmpeg → transcoding-pipeline-engineer; NOT player/QoE → playback-and-delivery-engineer.
• transcoding-pipeline-engineerUse for streaming encoding/transcoding: codec choice (H.264/HEVC/AV1/VP9), FFmpeg pipelines, per-title & ABR-ladder encoding, GPU vs CPU, CMAF/fMP4 packaging, captions, audio/loudness. NOT protocol/CDN/DRM architecture → media-streaming-architect; NOT player/QoE → playback-and-delivery-engineer.
• playback-and-delivery-engineerUse for streaming playback & delivery: player integration (hls.js/dash.js/Shaka/ExoPlayer/AVPlayer), ABR tuning, QoE (rebuffer, startup, VSF), low-latency live client, client DRM, CDN/edge cache tuning. NOT architecture → media-streaming-architect; NOT encoding → transcoding-pipeline-engineer.
• streaming-architecture-and-protocol-selectionChoose VOD vs live and the streaming protocol (HLS / MPEG-DASH / CMAF / LL-HLS / WebRTC) on the use-case, latency target, and device/browser reach — then commit to a packaging format (CMAF hedge), an origin/edge design, a single-vs-multi-CDN strategy, and the multi-DRM matrix (Widevine / FairPlay / PlayReady) the reach implies. Protocol/DRM/CDN specifics verify-at-use.
• transcoding-and-abr-ladderChoose codecs in tiers (H.264 reach floor + HEVC/AV1/VP9 efficiency), design the ABR ladder per-title from content complexity rather than a fixed table, build the FFmpeg pipeline for the quality/throughput/cost triangle (CRF vs 2-pass, GPU vs CPU, chunked parallel, GOP/segment alignment), and package once to CMAF/fMP4 with captions and loudness-normalized audio. Codec/flag/bitrate specifics verify-at-use.
• low-latency-live-streamingHit a live-streaming latency target: pick the approach (standard HLS/DASH, LL-HLS/LL-DASH with chunked CMAF, or WebRTC for sub-second/interactive) from the required end-to-end latency and scale, then budget latency across capture/encode, segment & part duration, chunked transfer, live origin, CDN, and the player live-edge buffer — trading latency against rebuffer risk deliberately. Protocol/latency specifics verify-at-use.
• playback-qoe-and-deliveryDeliver playback quality-of-experience: integrate the player (hls.js / dash.js / Shaka / ExoPlayer / AVPlayer) to the chosen protocol and DRM, tune the ABR algorithm (buffer- vs throughput-based, start bitrate, switch thresholds, caps) for stability, measure QoE by rebuffer ratio / startup time / average bitrate / VSF, and tune CDN/edge cache (cache-key, TTL, prefetch) — all instrumented with playback analytics. Player/CDN/QoE specifics verify-at-use.
• streaming-architecture.mdStreaming architecture template
• abr-ladder-plan.mdABR ladder plan template

No items match that filter in this plugin.

GraphQL-engineering team — 3 agents (graphql-schema-architect, graphql-server-engineer, graphql-security-governance-engineer) for the three engines of a GraphQL surface: schema design & evolution (client-driven type modeling, nullability, Relay pagination, mutation/error shape, schema-first vs code-first, federation vs stitching, non-breaking evolution), server & resolvers (N+1/DataLoader batching + per-request caching, selection-set-aware fetching, subscriptions, APQ/response caching), and security & governance (query cost/depth budgets, field-level authz, persisted operations, introspection hardening, rate/batch limits, error hygiene).

• 3 Agents
• 4 Skills
• 2 Templates

• graphql-schema-architectGraphQL schema design & evolution: client-driven type modeling, nullability, Relay pagination, mutation/error shape, schema-first vs code-first, federation, non-breaking evolution. NOT resolver perf/N+1 → graphql-server-engineer; NOT authz/cost → graphql-security-governance-engineer.
• graphql-server-engineerGraphQL resolvers & server: killing N+1 with DataLoader batching + per-request caching, selection-set-aware fetching, subscriptions, APQ/response caching. NOT schema/type design → graphql-schema-architect; NOT authz/cost → graphql-security-governance-engineer.
• graphql-security-governance-engineerGraphQL security & governance: query cost/depth budgets before execution, field-level authz, persisted operations, introspection hardening, rate/batch limits, error hygiene. NOT schema design → graphql-schema-architect; NOT resolver perf/N+1 → graphql-server-engineer.
• graphql-schema-design-and-evolutionDesign a GraphQL schema for the clients that consume it — not the database underneath: nullability discipline, Relay cursor-connection pagination, input/payload mutation shape, errors-as-data vs top-level errors — and evolve it without breaking clients via additive change, @deprecated, and staged field rollout. Spec/library specifics verify-at-use.
• graphql-federation-and-compositionDecide whether to federate, keep a monolithic graph, or stitch — and if federating, design clean subgraph ownership boundaries with entity @key, reference resolvers, and @external/@requires/@provides, then weigh the real operational cost of running a gateway/router. Federation spec and directive specifics verify-at-use.
• resolver-performance-and-n-plus-oneKill the N+1 problem GraphQL's per-field resolution invites: batch and per-request-cache with DataLoader, be selection-set aware so you fetch only requested fields, bound pagination cost, avoid over-fetching downstream, and layer response caching / APQ. Includes a worked N+1 example and its DataLoader fix. Library specifics verify-at-use.
• graphql-security-and-governanceDefend a GraphQL endpoint whose single URL accepts arbitrary nested queries: depth limiting, cost/complexity budgets, field-level authorization (authorize at the field, not the endpoint), introspection hardening in prod, persisted/allow-listed operations, rate and batching limits, and error-message hygiene so internals never leak. Library/spec specifics verify-at-use.
• graphql-schema-design-doc.mdGraphQL schema design doc template
• graphql-schema-and-perf-review.mdGraphQL schema and perf review template

No items match that filter in this plugin.

Hardware / electronics engineering team — 2 agents (hardware-systems-architect, pcb-design-engineer) for the board embedded firmware runs on: architecture & build-vs-buy (module vs custom PCB), MCU/component selection + supply-aware BOM, power architecture (LDO-vs-switcher, budgets), schematic capture, PCB layout (stack-up, impedance, decoupling, grounding), signal & power integrity, DFM/DFA/DFT, and bring-up. Distinct from embedded-iot-engineering (firmware) and robotics-autonomous-systems-engineering.

• 2 Agents
• 3 Skills

• hardware-systems-architectArchitect an electronics product: build-vs-buy (module vs custom PCB), MCU/component selection + supply-aware BOM, power architecture (LDO vs switcher), interfaces, and an EMC/pre-compliance posture. NOT for firmware/RTOS (embedded-iot-engineering) or PCB layout detail (pcb-design-engineer).
• pcb-design-engineerSchematic capture and PCB layout once the architecture is set: stack-up, decoupling/grounding, impedance routing, signal/power integrity, DFM/DFA/DFT, and board bring-up. Also schematic/layout review. NOT for build-vs-buy/BOM/power (hardware-systems-architect) or firmware (embedded-iot-engineering).
• scope-a-hardware-designTurn a product idea into a hardware architecture: decide module/dev-board vs custom PCB (via the decision tree), name requirements before parts, sketch the power tree, the interface plan, and an EMC/pre-compliance posture — against a cost/power/size/volume/schedule budget. Reach for this at the START of any board project. Driven by hardware-systems-architect.
• select-components-and-bomSelect the MCU/SoC and key components and build a supply-aware BOM: match parts to requirements, read datasheet parameters at the operating point (worst-case + margin), and weigh availability / second-source / lifecycle / cost at the target volume. Reach for this after the architecture is scoped, before schematic capture. Driven by hardware-systems-architect.
• review-schematic-and-layoutReview a schematic and PCB layout before fab: correctness (ERC/DRC, footprints/pinouts/polarity, power), integrity (decoupling at the pin, grounding/return paths, stack-up, controlled impedance), and DFM/DFA/DFT against the target fab's rules — returning a prioritized findings list with fixes. Reach for this before sending to fab, or on an inherited design. Driven by pcb-design-engineer.

No items match that filter in this plugin.

LLM-evaluation engineering team — 2 agents (eval-strategy-lead, eval-harness-engineer) for the question every team shipping an AI feature has to answer: is it getting better or worse? Eval design (task-grounded metrics, offline-vs-online split, sample size, a ship-gate decided as a number before the run), and the harness that proves it (frozen golden sets with provenance, LLM-as-judge rubrics with bias audit, CI regression gates, guardrail/red-team suites).

• 2 Agents
• 3 Skills

• eval-strategy-leadUse for deciding WHAT to measure for an LLM feature — task-grounded metric choice, eval-method selection (exact/rule-based/model-graded/human), offline-vs-online split, sample size, and a numeric ship-gate set before the run. NOT harness/judge/CI build -> eval-harness-engineer.
• eval-harness-engineerUse for BUILDING the eval machinery — frozen golden sets with provenance, LLM-as-judge rubric design + human calibration + bias audit (position/verbosity/self-preference), CI regression gates, guardrail/red-team suites. NOT what-to-measure/metric strategy -> eval-strategy-lead.
• design-eval-suiteTurn a fuzzy 'is the AI good enough?' into a concrete measurement plan: task spec, the eval method from the decision tree (exact / rule-based / model-graded / human), the metric + what it misses, the offline-vs-online split, a power-adequate sample size, and a numeric ship-gate decided before the run. Driven by eval-strategy-lead.
• build-llm-judgeDesign, calibrate, and bias-audit an LLM-as-judge so its scores track human judgment: named criteria with anchored levels, a structured verdict + reason, a pinned judge model/version, human-agreement calibration, and checks for position / verbosity / self-preference / leniency bias. Driven by eval-harness-engineer.
• gate-releases-with-evalsWire an offline eval suite into a CI ship-gate so a prompt/model change is scored against a frozen baseline and blocked on a regression past a preset threshold, with guardrail/red-team checks as a zero-tolerance blocker and cost/latency tracked alongside quality.

No items match that filter in this plugin.

Data-quality & observability team — 2 agents (data-quality-architect, data-quality-engineer) for the layer answering "is this data CORRECT, FRESH, COMPLETE, and can we TRUST it?": producer-boundary contracts, validation tests (not-null/unique/accepted-values/referential/distribution), freshness/volume/schema-drift/distribution monitors, threshold vs statistical anomaly detection, and data-quality SLAs.

• 2 Agents
• 3 Skills
• 2 Templates

• data-quality-architectUse to choose the data-quality APPROACH + tooling — "dbt tests vs Great Expectations vs Soda vs Monte Carlo?", "contracts vs tests vs monitors?", "where should checks run?", "what DQ SLAs?". Decision-tree-driven. NOT for PII/access/retention policy (data-governance-privacy).
• data-quality-engineerUse to BUILD & RUN data quality — author contracts/tests/monitors, wire into CI + orchestration + alerting, and run data-incident response (triage, root-cause to the change, quarantine/circuit-breaker, backfill). dbt-tests/GE/Soda/Elementary-fluent. NOT for tool selection (data-quality-architect).
• choose-data-quality-approachPick the right data-quality approach and tooling by traversing the decision tree (already-on-dbt? → check shape, known-rule vs unknown-over-time → build vs buy → where checks run → tool), returning the recommended contracts/tests/monitors mix, the tool, the block-vs-warn policy, and the SLAs. Driven by data-quality-architect.
• design-data-contracts-and-testsFrom a dataset and its consumers, derive the producer-boundary data contract (schema, semantics, freshness/volume expectations, ownership) and the concrete validation test suite (not-null, unique, accepted-values, referential integrity, distribution/value-range), each test carrying a severity.
• set-up-data-observability-monitorsStand up the observability monitors that watch for the unknown over time — freshness, volume, schema-drift, and distribution/anomaly monitors — each anchored to a baseline and a tolerance, then wire owner-routed alerting and link a data-incident runbook. Driven by data-quality-engineer.
• data-quality-check-spec.mdData-quality check spec — [dataset-name]
• data-incident-runbook.mdData-incident runbook — [dataset / pipeline]

No items match that filter in this plugin.

Martech / event-instrumentation & CDP team — 2 agents (event-taxonomy-architect, instrumentation-engineer) for the ENGINEERING of event collection: the tracking plan / event taxonomy (object-action naming), the identity model (anonymous → known, stitching), CDP & collection-architecture selection (Segment, RudderStack, Snowplow, mParticle; client vs server vs hybrid), consent gating, and stream QA.

• 2 Agents
• 3 Skills
• 2 Templates

• event-taxonomy-architectUse to design the event-collection contract — the tracking plan / event taxonomy (object-action naming), the identity model (anonymous→known stitching), and the CDP + collection-architecture choice (Segment/RudderStack/Snowplow; warehouse-first). NOT for campaign strategy → marketing-operations.
• instrumentation-engineerUse to IMPLEMENT event tracking on a chosen CDP: typed client/server Track/Identify calls, a codegen'd tracking library, schema validation in CI, consent gating (Consent Mode/TCF/GPC), destinations + reverse ETL, stream QA. NOT taxonomy/CDP design → event-taxonomy-architect.
• choose-cdp-and-collection-architecturePick the right CDP and event-collection architecture by traversing the decision tree (source of truth & activation → packaged CDP vs warehouse-first/reverse-ETL vs Snowplow self-hosted; accuracy vs UI-richness → client-side vs server-side vs hybrid). Driven by event-taxonomy-architect.
• design-a-tracking-planTurn product and business questions into an event tracking plan — derive the event taxonomy (object-action naming), the properties, the naming convention, the identity model (anonymousId → userId stitching), and the per-event spec table. Driven by event-taxonomy-architect.
• implement-event-instrumentation-and-consentImplement a tracking plan as working event collection — typed client/server-side Track/Identify calls, a codegen'd tracking library, schema validation in CI, consent gating at the source (Google Consent Mode v2 / IAB TCF / GPC), destination + reverse-ETL wiring, then QA the live stream. Driven by instrumentation-engineer.
• tracking-plan.mdTracking plan — [product / surface]
• event-schema-spec.mdEvent schema spec — [Object Action]

No items match that filter in this plugin.

AI/LLM red-teaming team — 2 agents (ai-redteam-lead, adversarial-testing-engineer) for the layer answering 'can this AI system be made to do harm, leak data, or exceed its authority — and how do we harden it?': threat modeling + rules of engagement, the attack taxonomy (OWASP LLM Top 10 2025 + MITRE ATLAS), direct vs indirect prompt injection, jailbreaks (roleplay/encoding/many-shot/crescendo), data exfiltration & training-data extraction, agentic tool-abuse / excessive agency, multimodal attacks, and defense-in-depth remediation. Fluent in automated red-team harnesses (PyRIT, Garak, Promptfoo red-team, Giskard) and likelihood×impact severity.

• 2 Agents
• 3 Skills
• 2 Templates

• ai-redteam-leadUse to SCOPE an AI red-team engagement — the threat model, rules of engagement, attack taxonomy (OWASP LLM Top 10 / MITRE ATLAS), the safety-vs-security split, and success/severity criteria. Decision-tree-driven. NOT for eval quality-regression testing (llm-evaluation-engineering).
• adversarial-testing-engineerUse to EXECUTE AI attacks & harden — run jailbreaks/prompt-injection/data-exfiltration, build automated red-team harnesses (PyRIT/Garak/Promptfoo), triage findings by likelihood×impact, drive defense-in-depth remediation. NOT for app/infra pentest (security-engineering).
• design-ai-redteam-planScope an AI red-team engagement by threat-modeling the system (assets, attackers, trust boundaries), splitting safety from security, traversing the attack-taxonomy decision tree to a prioritized OWASP LLM Top 10 / MITRE ATLAS attack list, and setting the rules of engagement plus likelihood×impact success and severity criteria. Used by ai-redteam-lead.
• run-adversarial-attacks-and-jailbreaksExecute the prioritized attacks against an AI system within the rules of engagement — direct and indirect prompt injection, jailbreaks (roleplay, encoding, many-shot, crescendo), training-data extraction and data exfiltration, agentic tool-abuse / excessive agency, and multimodal attacks — capturing each as a reproducible payload plus transcript. Used by adversarial-testing-engineer.
• harden-and-remediate-ai-systemTriage red-team findings by likelihood×impact and drive defense-in-depth remediation — layered input/output guardrails, injection-resistant prompt structure, least-privilege tool scoping, human-in-the-loop on high-impact actions — then retest each fix and bake it into the regression harness. Used by adversarial-testing-engineer.
• ai-redteam-plan.mdAI red-team plan template
• ai-redteam-findings-report.mdAI red-team findings report template

No items match that filter in this plugin.

Technical-SEO & search-engineering team — 2 agents (seo-strategy-architect, seo-implementation-engineer) for the layer answering 'can search engines CRAWL, RENDER, INDEX, and UNDERSTAND this site, and will it RANK?': crawl-budget & log analysis, indexation control (robots.txt, meta robots, canonicalization, noindex), JS rendering (CSR/SSR/SSG, dynamic-rendering deprecation), structured data / schema.org (JSON-LD, rich-result eligibility), site architecture & internal linking, E-E-A-T, Core Web Vitals as a ranking factor (INP replaced FID in 2024), international SEO (hreflang), site migrations (redirect mapping, staging noindex), and topical authority.

• 2 Agents
• 3 Skills
• 2 Templates

• seo-strategy-architectUse to decide SEO STRATEGY & priorities — indexation strategy, site architecture + internal-linking model, content model + topical-authority map, E-E-A-T posture, and what to fix first (crawl/index/render/rank). NOT for internal site-search relevance → search-relevance-engineering.
• seo-implementation-engineerUse to IMPLEMENT technical SEO — crawlability (robots.txt, sitemaps, log analysis), rendering (CSR/SSR/SSG), indexation (canonical, noindex, hreflang), JSON-LD structured data, Core Web Vitals (INP), and site migrations. NOT for the full website build/visual design → web-design.
• choose-seo-strategy-and-prioritiesDiagnose what to fix first for a described site by walking the SEO strategy decision tree (crawl → render → index → understand → rank), fixing the lowest broken rung first, then return the priority diagnosis, the indexation strategy, and the E-E-A-T posture. Used by seo-strategy-architect.
• design-site-architecture-and-content-modelFrom a site's target queries and page classes, design the crawl-efficient information architecture (flat depth, hub-and-spoke topic clusters), the internal-linking model that flows authority to the money pages, and the topical-authority / entity map. Used by seo-strategy-architect and seo-implementation-engineer.
• implement-technical-seo-and-structured-dataImplement and verify the technical-SEO layer for a site — crawlability, rendering (CSR→SSR/SSG/prerender), indexation controls (canonical, meta-robots noindex, hreflang), JSON-LD schema.org structured data, Core Web Vitals (INP/LCP/CLS), and redirect-mapped site migrations. Used by seo-implementation-engineer.
• technical-seo-audit-report.mdTechnical-SEO audit report template
• seo-migration-plan.mdSEO migration plan template

No items match that filter in this plugin.

Bioinformatics & genomics-pipeline team — 2 agents (bioinformatics-workflow-architect, genomics-pipeline-engineer) for the layer answering 'which workflow engine, reference, and compute strategy, and how do we build a reproducible, validated genomics pipeline?': engine choice (Nextflow/nf-core, Snakemake, WDL+Cromwell/miniwdl, CWL), reference build (GRCh38 vs T2T-CHM13) + core steps (QC, trimming, alignment BWA-MEM2/minimap2/STAR/Salmon, dedup, variant calling GATK/DeepVariant, joint genotyping), RNA-seq (DESeq2/edgeR) and single-cell (Scanpy/Seurat), reproducibility (Docker/Apptainer, Conda/Bioconda, pinned versions, FAIR, provenance), HPC-vs-cloud scaling and cost, and validation vs GIAB/hap.py truth sets.

• 2 Agents
• 3 Skills
• 2 Templates

• bioinformatics-workflow-architectUse to CHOOSE the genomics workflow architecture — engine (Nextflow/nf-core, Snakemake, WDL+Cromwell, CWL), reference build (GRCh38 vs T2T-CHM13) + tools, compute (HPC Slurm vs cloud Batch/spot), reproducibility (containers, pinned versions). NOT for generic MLOps/model training → ml-engineering.
• genomics-pipeline-engineerUse to BUILD, optimize & validate the genomics pipeline — QC/align/dedup/variant-call/RNA-seq steps, containerize (Docker/Apptainer), scale on HPC Slurm or cloud Batch/spot, benchmark vs GIAB/hap.py truth sets. Nextflow/Snakemake/WDL-fluent. NOT for clinical-trial ops/regulatory → clinical-trials.
• choose-bioinformatics-pipeline-and-stackPick the right genomics workflow engine, reference build, tool chain, compute strategy, and reproducibility approach by traversing the bioinformatics pipeline decision tree, then return the recommended engine, reference build with hazards, aligner/variant-caller chain, compute plan, and validation truth set. Used by bioinformatics-workflow-architect.
• design-genomics-analysis-workflowFrom a scientific question, an assay, and a sample design, derive the concrete genomics analysis workflow — the per-sample step graph, the cohort/joint step, the reference build and its matching accessory files, and the validation truth set. Used by genomics-pipeline-engineer and bioinformatics-workflow-architect.
• implement-and-scale-bioinformatics-pipelineImplement a designed genomics workflow in the chosen engine, containerize and pin every tool for reproducibility, scale it with scatter/gather on HPC Slurm or cloud Batch, and validate it against a GIAB/GA4GH hap.py truth set. Used by genomics-pipeline-engineer.
• analysis-plan-spec.mdGenomics analysis plan template
• pipeline-validation-report.mdPipeline validation report template

No items match that filter in this plugin.

Audio DSP engineering team — 2 agents (audio-dsp-architect, dsp-implementation-engineer) for the layer answering 'what processing architecture, at what latency, on what platform — and how do we make the audio callback real-time-safe and fast?': processing model (block vs sample-by-sample), latency & buffer budget, fixed vs float + denormals, algorithm approach (IIR biquads / FIR, FFT/STFT overlap-add, oversampling/anti-aliasing), plugin formats & frameworks (JUCE, VST3, AU/AUv3, AAX, CLAP, LV2), audio I/O (CoreAudio, ASIO, WASAPI, ALSA/JACK, Web Audio), lock-free parameter passing, spatial/binaural (HRTF), embedded DSP (CMSIS-DSP), SIMD, and measurement (null tests, THD+N, frequency response).

• 2 Agents
• 3 Skills
• 2 Templates

• audio-dsp-architectUse to choose the audio-DSP ARCHITECTURE — block/sample processing, latency/buffer budget, plugin format & audio I/O (JUCE/VST3/AU/CLAP; CoreAudio/ASIO/Web Audio), fixed vs float, algorithm approach (IIR/FIR, FFT/STFT, oversampling). NOT for streaming codecs/delivery → streaming-media-engineering.
• dsp-implementation-engineerUse to BUILD & OPTIMIZE real-time audio — real-time-safe DSP in the callback (no locks/alloc/syscalls), biquads/FIR/FFT, denormals/flush-to-zero, SIMD (SSE/NEON), lock-free params, measurement (null/THD+N/impulse response). NOT for conversational voice AI → conversational-ai-voice-engineering.
• choose-audio-dsp-architecturePick the right audio-DSP architecture for a described product by traversing the decision tree (latency tolerance → processing model → time-vs-frequency domain → fixed-vs-float + denormals → platform/plugin format + audio I/O), then return the recommended architecture. Used by audio-dsp-architect.
• design-signal-processing-chainFrom an effect or product goal and its architecture, derive the signal-processing chain — the block diagram, the per-stage algorithm (IIR biquad / FIR / FFT-STFT / delay / dynamics), the per-stage and total latency, gain-staging/headroom, the oversampling plan, and the parameter list. Used by dsp-implementation-engineer and audio-dsp-architect.
• implement-and-optimize-realtime-audioImplement a DSP stage as real-time-safe code in the audio callback (no locks, no allocation, no syscalls), handle denormals with flush-to-zero, pass parameters lock-free, then optimize the hot loop with SIMD and verify with objective measurement (null test, THD+N, frequency response). Used by dsp-implementation-engineer.
• dsp-design-spec.mdDSP design spec template
• realtime-audio-review-checklist.mdReal-time audio review checklist template

No items match that filter in this plugin.

Digital-twin engineering team — 2 agents (digital-twin-architect, twin-integration-engineer) for the layer answering 'what should this twin MODEL, at what FIDELITY, and does it MATCH the real asset?': twin taxonomy (asset vs process vs system-of-systems; descriptive/predictive/prescriptive; digital-shadow vs true bidirectional), only-as-much-fidelity-as-the-decision-needs, modeling approach (physics vs data-driven/surrogate/reduced-order vs hybrid), telemetry ingestion (MQTT/OPC-UA/Kafka, edge vs cloud), state sync/drift/calibration, simulation & what-if, and fidelity validation.

• 2 Agents
• 3 Skills
• 2 Templates

• digital-twin-architectUse to choose the digital-twin SCOPE, type, and FIDELITY — asset vs process vs system-of-systems, digital-shadow vs bidirectional, modeling approach (physics/data-driven/hybrid), sync strategy, and platform. Decision-tree-driven. NOT for IoT device firmware → embedded-iot-engineering.
• twin-integration-engineerUse to BUILD & VALIDATE a digital twin — telemetry ingestion (MQTT/OPC-UA/Kafka, edge vs cloud), model wiring (DTDL/AAS), simulation & what-if, drift/reconciliation, and fidelity validation (error bounds vs the real asset). NOT for robot control/autonomy → robotics-autonomous-systems-engineering.
• choose-digital-twin-architectureScope and architect a digital twin for a described asset and decision by traversing the decision tree (decision it informs → twin type → shadow-vs-bidirectional → modeling approach → fidelity → sync → platform), then return the twin scope/type and fidelity level. Used by digital-twin-architect.
• design-twin-data-and-sync-modelFrom a physical asset and its telemetry, derive the twin's data and synchronization model — the signal list and sampling rates, the transport protocol (MQTT / OPC-UA / Kafka), the edge-vs-cloud split, the sync-latency budget, and the drift-detection + recalibration policy. Used by twin-integration-engineer and digital-twin-architect.
• implement-twin-integration-and-simulationBuild a digital twin end to end — ingest telemetry and bind it to the model (DTDL properties / AAS submodels), wire the physics or reduced-order/surrogate model, run simulation and what-if scenarios against live twin state, and validate fidelity against the real asset (predicted-vs-actual, error bounds, calibration) plus a drift monitor. Used by twin-integration-engineer.
• digital-twin-design-spec.mdDigital-twin design spec template
• twin-fidelity-validation-report.mdTwin-fidelity validation report template

No items match that filter in this plugin.

Chaos-engineering & resilience team — 2 agents that make distributed systems survive failure. resilience-architect owns the DESIGN side: failure-mode analysis (FMEA), resilience patterns (timeouts, retries with backoff+jitter, bulkheads, circuit breakers, load shedding, graceful degradation, idempotency), the observability-maturity gate for whether you're ready to run chaos, and redundancy/DR (multi-AZ/region, failover, RTO/RPO). chaos-experiment-engineer owns the EXPERIMENT + VERIFICATION side: hypothesis-driven experiments, blast-radius containment (automatic abort/rollback), game days, fault injection (latency/error/resource/dependency-outage/partition/zone), and verifying the pattern held under load+fault.

• 2 Agents
• 3 Skills
• 2 Templates

• chaos-experiment-engineerChaos EXPERIMENTS + verification — hypothesis-driven design (steady-state, smallest disproving experiment), blast-radius containment + automatic abort, game-day facilitation, fault-injection taxonomy (latency/error/exhaustion/outage/partition/zone), verifying a pattern held. NOT observability-sre.
• resilience-architectResilience DESIGN — failure-mode analysis (FMEA, dependency maps, SPOFs), resilience patterns (timeouts, retries+backoff+jitter+budget, bulkheads, circuit breakers, load shedding, graceful degradation, fallbacks), the maturity gate for chaos, DR RTO/RPO. NOT metrics/SLO/on-call → observability-sre.
• design-resilience-patternsPick and place the right resilience patterns for a given failure mode — the timeout / retry+backoff+jitter+budget / circuit-breaker / bulkhead / load-shedding / graceful-degradation / fallback / idempotency / backpressure decision. Start from an FMEA, choose the pattern that defends the NAMED failure, and defend the pattern's OWN failure mode. Reach for this when the user asks 'what do we add so a slow/failing dependency doesn't take us down?', 'is a naked retry safe here?', or 'where are our single points of failure?'. Used by `resilience-architect` (primary).
• plan-game-dayFacilitate a game day end to end — the scenario, the roles (facilitator / operators / observers / scribe), the comms plan, the abort criteria, a scoring rubric, and the follow-up remediation backlog. Game days test PEOPLE and RUNBOOKS under a controlled failure, not just systems — the cheapest way to find the org's real failure modes. Reach for this when the user asks 'run us a game day for X', 'how do we do a failure drill', or 'test our on-call/runbooks against an outage'. Driven by `chaos-experiment-engineer`; the `resilience-architect` is consulted on prerequisites + remediation.
• run-chaos-experimentRun the full chaos-experiment loop safely — steady-state definition → falsifiable hypothesis → the smallest disproving blast radius → inject a fault from the taxonomy → observe (metrics correlated to the injection window, under load) → abort-or-learn → remediate. Gate on the maturity check first (no steady-state observability = no experiment) and never inject without an automatic abort condition. Reach for this when the user asks 'design/run a chaos experiment for X', 'which fault do we inject first?', or 'did the resilience pattern actually hold?'. Used by `chaos-experiment-engineer` (primary).
• chaos-experiment-plan.mdChaos experiment plan — <system / experiment name>
• resilience-review-checklist.mdResilience review checklist — <service / system name>

No items match that filter in this plugin.

Serverless engineering team — 2 agents for building on serverless the provider-neutral way. serverless-architect owns the design side: event-driven decomposition, FaaS-vs-containers-vs-managed-services and when serverless is the WRONG choice, sync/async, orchestration-vs-choreography, event contracts, the dual-write/outbox problem, and serverless-friendly storage. serverless-runtime-and-ops-engineer owns the runtime side: cold starts, concurrency & throttling, idempotency & exactly-once-effect, DLQs & poison messages, retries, per-invocation cost & the scale crossover, tracing in ephemeral runtimes, and local emulation.

• 2 Agents
• 3 Skills
• 2 Templates

• serverless-architectUse for serverless ARCHITECTURE — event-driven decomposition, FaaS-vs-containers-vs-managed-services (and when serverless is the WRONG choice), sync/async, orchestration-vs-choreography, event contracts, dual-write/outbox, serverless storage. NOT provider IaC → aws/gcp/azure-cloud.
• serverless-runtime-and-ops-engineerUse for serverless RUNTIME & OPS — cold starts (provisioned/warm concurrency), concurrency limits & throttling, idempotency + exactly-once-effect, DLQs & poison messages, retries/visibility, per-invocation cost & the scale crossover, tracing, local emulation. NOT the deploy pipeline → devops-cicd.
• design-event-driven-architectureDecompose a workload into functions and events for a serverless/event-driven design — the serverless-vs-container-vs-managed-service call (and where serverless is the WRONG choice: steady high-throughput, long-running, tight-latency, pooled-RDBMS), sync-vs-async boundaries per interaction, orchestration (state machine/saga) vs choreography (event bus), the event schemas & contracts, serverless-friendly storage vs a connection-pool-hostile RDBMS, and the dual-write/outbox fix — designed around events and contracts so it never becomes a distributed monolith (lambda pinball). Reach for this on 'serverless vs containers vs managed service?', 'decompose this into functions/events', 'state machine vs event bus?', or 'can our RDBMS sit behind these functions?'. Driven by `serverless-architect` (primary).
• harden-serverless-runtimeHarden a serverless function/pipeline for the runtime & ops realities — cold starts (causes, the provisioned/warm-concurrency vs package-slimming trade-off against the latency budget, and what NOT to over-provision), concurrency & account/region limits & throttling with downstream (RDBMS) protection, idempotency keys + exactly-once-EFFECT (delivery is at-least-once), DLQ + poison-message policy, and retry/backoff/visibility-timeout so a queue is never an infinite-retry outage. Reach for this on 'fix our cold starts', 'this queue double-processes / retries forever', or 'we're getting throttled — plan our concurrency'. Driven by `serverless-runtime-and-ops-engineer` (primary).
• model-serverless-cost-and-scaleModel serverless cost and scale — a per-invocation cost model (invocations × duration × memory + requests + data-transfer + downstream), the serverless-vs-container crossover point where steady high-throughput makes always-on cheaper (and 'serverless is cheaper' stops being true at scale), and concurrency/quota/limit planning (account/region caps, reserved/provisioned concurrency, throttle headroom). Reach for this on 'is serverless actually cheaper here?', 'where do we cross over to containers?', or 'plan our concurrency/quota headroom'. Driven by `serverless-runtime-and-ops-engineer` (primary), consulted by `serverless-architect` for the cost side of the serverless-vs-not call.
• serverless-architecture-decision-record.mdServerless architecture decision record — <workload / service name>
• serverless-function-readiness-checklist.mdServerless function readiness checklist — <function name>

No items match that filter in this plugin.

UX-research team — 2 agents (ux-research-lead, research-execution-and-synthesis-specialist) that turn a fuzzy ask into a researchable question, pick a rigorous method (generative vs evaluative, qual vs quant, moderated vs unmoderated), run the study (usability tests, interviews, surveys), and synthesize evidence into decision-ready, bias-checked insight — without the research theater. The lead owns framing, method selection, the research plan, research-ops (recruiting, repository), and research ethics + participant-PII discipline (consent, anonymization). The specialist owns protocol & task design, non-leading moderation, survey design, and synthesis (affinity/thematic analysis, evidence strength, observation vs interpretation).

• 2 Agents
• 3 Skills
• 2 Templates

• research-execution-and-synthesis-specialistRUNNING & SYNTHESIZING UX research — protocol & task design, non-leading moderation, usability testing (success + severity), survey design (no leading/double-barreled items), and synthesis (affinity/thematic analysis, observation vs interpretation, bias-guarding). NOT roadmap → product-management.
• ux-research-leadUX-research FRAMING & OPS — framing the researchable question, method selection (generative/evaluative, qual/quant, attitudinal/behavioral, moderated/unmoderated), the research plan, sample & recruit, research-ops, and research ethics + participant-PII. NOT the roadmap → product-management.
• plan-the-research-studyFrame a fuzzy research ask into a researchable question, run the research-theater gate (is this a real question or a decision already made?), select the method (generative/evaluative, qual/quant, attitudinal/behavioral, moderated/unmoderated) from the question rather than the reverse, size the sample to the claim it must bear (directional ~5 vs statistically-powered), plan the recruit/screener/incentive/panel, set the informed-consent + data-minimization + de-identification + retention ethics plan, and tie every finding to the decision it informs. Reach for this when the ask is 'how should we study X?', 'run a study that confirms Y', 'how many participants and from where?', or 'what do we need for consent/PII?'. Used by `ux-research-lead` (primary).
• run-usability-and-interview-sessionsDesign and run the study without contaminating it — protocol & task design (goal-based tasks, not step instructions), think-aloud and non-leading moderation (open probes, silence, 'tell me more' — never 'was that easy?'), usability-test instrumentation (task-success criteria + severity ratings), survey design that avoids leading, double-barreled, and social-desirability-loaded items, and clean data capture that keeps what participants DID separate from what they SAID. Reach for this when the ask is 'write the protocol/tasks', 'moderate this interview without leading', or 'design/fix this survey'. Used by `research-execution-and-synthesis-specialist` (primary).
• synthesize-research-into-insightTurn raw notes into evidence-weighted, bias-checked, prioritized, decision-ready insight — affinity/thematic analysis, keeping observation ('6 of 8 abandoned at step 3') strictly separate from interpretation ('because the CTA is unclear'), weighting each finding by evidence strength (n, consistency, behavioral vs attitudinal, directional vs conclusive), ranking by severity, actively seeking disconfirming evidence, and ending every insight in a prioritized recommendation tied to a decision. Guards against confirmation, recency, and availability bias. Reach for this when the ask is 'turn these notes/sessions into findings we can act on' or 'what did we actually learn?'. Used by `research-execution-and-synthesis-specialist` (primary), consulted by `ux-research-lead`.
• research-findings-report.mdResearch findings report — <study name / date>
• research-plan.mdResearch plan — <study name / date>

No items match that filter in this plugin.

Standalone brand-CREATION service for a web studio's commission customers — 2 agents (brand-strategist, identity-systems-designer): strategy/positioning/archetype, naming & tagline, curated logo suite, color/type systems (WCAG-paired), brand book, legal/IP posture, collateral, sellable tiers. AI-drafts + MANDATORY human curation. Thin orchestration layer: delegates design tokens to web-design:design-tokens-scaffolding, raw generation + license/indemnity to generative-web-media, and hands the finished system to web-design:visual-designer.

• 2 Agents
• 5 Skills
• 1 Hooks
• 6 Templates

• brand-strategistBrand strategy & verbal identity: discovery → positioning, value prop, audience, archetype; voice platform (attributes, tone rules, do/don't-say, glossary); naming & tagline (bulk-draft → human-curated). Owns the strategy-before-visuals gate. NOT logo/color/type → identity-systems-designer.
• identity-systems-designerDirects the visual identity system: logo suite (lockups/clear-space/mono/B&W), color roles + WCAG-AA pairs, type + web-license class. Authors briefs for generative-web-media, curates concepts, delegates tokens to web-design, assembles brand book. NOT strategy/voice → brand-strategist.
• brand-book-assemblyCompile the finished brand system into a dynamic brand-book hub (logo rules, color tokens, type, voice, imagery, usage do/don'ts), DELEGATE the token build to web-design:design-tokens-scaffolding, spec the favicon/OG asset set, and enforce the legal-sign-off precondition (can't mark client-ready without the curation + authorship log and every IP/font claim routed to security-reviewer). Hands the finished system to web-design:visual-designer.
• brand-legal-and-licensingState the load-bearing brand-IP facts (AI-logo copyright ≠ trademark; documented human authorship; font web-license class OFL/Adobe/Monotype; provider indemnity) and route EVERY client-facing IP / registrability / font-license claim to ravenclaude-core:security-reviewer and counsel. Not legal advice — states facts, never conclusions; recommends a TM clearance search before promising trademarkability.
• brand-strategy-and-namingAuthor the brand strategy substrate BEFORE any visual generation — a discovery questionnaire → positioning statement, value proposition, target audience, and archetype — then bulk-draft business/product names + taglines and hand a human-curated shortlist. Owns the strategy-before-visuals gate artifact. Naming availability + trademark collisions route to security-reviewer; not legal advice.
• brand-voice-and-messagingBuild the verbal identity — a voice platform (3–5 attributes, tone-shift rules by context, do-say/don't-say pairs, a term glossary) and a messaging hierarchy (tagline, elevator, value pillars). The half of the brand book a logo tool skips; authored from the strategy brief, applicable by someone who isn't the author.
• logo-and-visual-system-directionDirect the visual identity: author the anti-slop creative brief for generative-web-media (setting indemnity_required), run the human-curation + documented-human-authorship gates, and spec the logo suite (lockups/clear-space/min-size/mono/B&W), color roles with WCAG-AA pairs, and type with web-license class. Refuses without a strategy brief. The curated vector is the deliverable — never regenerated in Firefly.
• flag-brand-antipatterns.shflag-brand-antipatterns.sh PostToolUse hook for Edit | Write | MultiEdit on brand-conventional files — flags non-self-hostable fonts, un-curated concepts, logo-regeneration-in-Firefly, and un-routed IP claims. Advisory only — never blocks.
• brand-book-outline.mdBrand Book — <brand / version / date>
• brand-strategy-brief.mdBrand Strategy Brief — <client / brand / date>
• creative-brief-for-generative-media.mdCreative brief for generative-web-media — <project / asset-kind / date>
• curation-and-authorship-log.mdCuration & Authorship Log — <project / asset / date>
• favicon-og-asset-manifest.mdFavicon / OG Asset Manifest — <brand / date>
• font-license-tracker.mdFont License Tracker — <brand / date>

No items match that filter in this plugin.

AI multimedia for brand & winery sites: a creative brief -> on-brand, web-optimized, license-clean images/video/3D/audio behind a mandatory human curation gate. 4 agents (generation-strategist, web-asset-pipeline-engineer, asset-provenance-guardian, brand-and-accessibility-reviewer) route a brief to the right generator (provider-neutral, Grok-lean for images where competitive; inpaint/outpaint/bg-removal/upscale first-class), turn raw output into AVIF/WebP responsive <picture> markup with LCP/CLS-safe embeds, pin commercial-use licenses (flags the FLUX-dev non-commercial trap; C2PA + a provenance ledger; EU AI Act Art.50 disclosure), and gate every asset on brand-hex/style conformance + WCAG alt text before ship.

• 4 Agents
• 6 Skills
• 5 Templates

• asset-provenance-guardianPins each asset's commercial-use license (flags the FLUX-dev non-commercial trap; Firefly-indemnified where required; Grok has no indemnity), writes a provenance ledger, enforces generation budgets, adds EU AI Act Art.50 disclosure. Not legal advice -> security-reviewer.
• brand-and-accessibility-reviewerThe mandatory ship gate: brand-hex/style conformance (consumes a brand-token contract or brand-extraction), anti-slop QA (garbled text, off-brand drift, no baked-in text), AI-drafted + human-reviewed WCAG alt text, mandatory human curation sign-off. NOT generation or licensing -> the other agents.
• generation-strategistRoutes a creative brief to the right AI generator across images/video/3D/audio via a provider matrix (Grok-lean images where competitive), draft-vs-final cost tiering, and editing round-trips. NOT web-opt -> web-asset-pipeline-engineer; NOT licensing -> asset-provenance-guardian.
• web-asset-pipeline-engineerTurns a generated asset into a production web asset: AVIF/WebP responsive <picture> with explicit dims, LCP/CLS-safe markup, muted-autoplay reduced-motion video embeds, <model-viewer> glTF. NOT generation routing -> generation-strategist; NOT licensing -> asset-provenance-guardian.
• brand-conditioned-generationCondition generation on a brand: consume brand tokens from whatever source is present (a DTCG design-token file OR ravenclaude-core:brand-extraction's brand.json), assemble a 3-10 image style-reference / Recraft brand-style upload, then post-overlay the exact brand hex rather than trusting the model's color memory. Style-reference beats seed-pinning. This plugin CONSUMES tokens; it does not produce them.
• curation-and-accessibility-gateThe mandatory ship gate: brand-hex/style conformance, anti-slop QA (garbled in-image text, hands/anatomy, off-brand drift, no baked-in text), AI-drafted + human-reviewed WCAG 2.2 alt text (decorative -> alt=""), and a mandatory human curation sign-off. No asset reaches production without a curation artifact — this gate is a hard blocker, not a suggestion.
• generation-budget-guardKeep generation spend a design input, not a surprise: route a cheap draft before a premium final, set a per-project generation budget cap, log each spend line (you supply the unit price — every provider price is [unverified]), and fail loudly when the cap is exceeded. Backed by gen-budget.py (stdlib, no baked-in prices) and /check-generation-budget.
• license-and-provenance-ledgerPin each asset's commercial-use license before the prompt (flag the FLUX-dev non-commercial trap; Firefly-indemnified where indemnity_required; Grok has no IP indemnity), write the durable internal provenance ledger (prompt/model/provider/license/indemnity/date) since C2PA is routinely stripped, and add EU AI Act Art.50 disclosure copy for EU-facing sites. Not legal advice -> routes hard calls to security-reviewer. Facts dated [verify-at-use].
• prompt-to-asset-routingRoute a creative brief to the right AI generator across images (photoreal, illustration, vector/SVG, text-in-image), video, 3D, and audio — plus the editing round-trips (inpaint, outpaint, background-removal, upscale) that beat a fresh generation. License-first, Grok-lean for images where competitive, draft-vs-final cost tiering. Provider/price specifics [verify-at-use]; every price [unverified].
• web-optimization-pipelineTurn a raw generated asset into a production web asset: AVIF/WebP/fallback responsive <picture> at 3-5 widths with explicit dims (CLS-safe), LCP hero eager + fetchpriority=high (cap 1-2), lazy below-fold, accessible muted-autoplay prefers-reduced-motion video embeds with a poster-LCP frame + WebM/H.264 fallback, and <model-viewer> glTF. Build-time (Sharp) default; CDN documented. Optimizer LOUD-SKIPs if Node/Sharp absent.
• asset-brief.mdTemplate: Asset Brief — the FROZEN brand-token contract (v1.0)
• asset-provenance-ledger-entry.jsonAsset provenance ledger entry — JSON schema (prompt/model/provider/license/indemnity/date)
• generation-defaults.yamlgeneration-defaults.yaml — per-project defaults for generative-web-media
• model-viewer-3d-embed.htmlAccessible, CLS-safe web embed for a generated 3D model (glTF/GLB via <model-viewer>)
• picture-element-snippet.htmlThe production <picture> image contract — AVIF -> WebP -> JPEG, responsive, CLS-safe

No items match that filter in this plugin.

Web commerce integration specialist — scaffolds production-ready payment/commerce backends (Stripe, Square, or Shopify; one per site) into static or JS-framework sites at full depth: catalog, cart, hosted/embedded checkout, verified webhooks, idempotency, POS/inventory reconciliation, and order handling. Three first-class provider tracks behind a thin shared payment-lifecycle contract — NOT a leaky unified adapter. Generates first-party code (no dormant/deprecated deps), with PCI card-isolation, webhook signature verification, idempotency, and env-only secrets as GENERATED-CODE invariants. The backend-integration lane that plugs into web-design's build pipeline; every payment/PII security verdict routes to ravenclaude-core/security-reviewer.

• 4 Agents
• 5 Skills
• 4 Templates

• commerce-integration-engineerUse to scaffold a chosen commerce provider track (Stripe/Square/Shopify, static or framework) into a site from the templates — wiring checkout, webhooks, idempotency, and env config. Runs AFTER commerce-provider-selector. The security verdict routes to ravenclaude-core/security-reviewer.
• commerce-provider-selectorUse to choose the commerce provider (Stripe/Square/Shopify) and tier (static hosted vs framework embedded) for a site and record it in commerce.manifest.json — the first step before scaffolding. NOT the site/checkout UX (web-design) or the scaffold build (commerce-integration-engineer).
• commerce-webhook-security-reviewerUse to audit a scaffolded or hand-modified commerce integration for the security invariants — PCI card-isolation, constant-time webhook verification, idempotency, env-only secrets. Proposes fixes; the binding verdict stays ravenclaude-core/security-reviewer's. Run before shipping any payment change.
• pos-reconciliation-engineerUse to build or debug the Square online↔in-store inventory reconciliation loop — catalog/inventory webhooks, one-way POS-as-source-of-truth sync, event-id idempotency. Square-only (Shopify inverts, Stripe has no catalog). NOT for payment checkout wiring (commerce-integration-engineer).
• commerce-gold-standard-rubricScore a scaffolded commerce integration against the seven-dimension gold-standard rubric and run the BUILD-measure-fix iteration loop until it passes. Use after scaffolding a provider track, before calling it done. Each dimension is a falsifiable test; a live provider-sandbox test is required beyond the static checks.
• payment-lifecycle-contractUnderstand and extend the thin shared contract every provider track implements — the payment-lifecycle interface plus advertised capabilities. Use when adding a provider, wiring a track to the contract, or deciding what belongs in the shared seam vs a track. The ONLY cross-provider abstraction; catalog/cart/inventory are track-specific.
• pos-reconciliation-loopReconcile online inventory/catalog with an in-store POS (Square), keeping the POS as the source of truth. Use when a storefront's online store must mirror in-store stock. One-way sync driven by catalog/inventory webhooks, de-duped by event id — never bidirectional. Square-specific; Shopify inverts and Stripe has no catalog.
• provider-track-selectionChoose the commerce provider (Stripe / Square / Shopify) and the tier (static hosted-checkout vs framework embedded-SDK) for a site, then point at the right template set. Use at the START of any commerce integration, before scaffolding. Routes on how the merchant's inventory truth already lives and the site's runtime.
• webhook-hardeningHarden a commerce webhook handler: verify the provider signature with a constant-time compare BEFORE parsing the body, then de-duplicate retried deliveries by provider event id. Use when writing or reviewing any Stripe/Square/Shopify webhook receiver. Two invariants (verify-before-parse, event-id idempotency) that are non-negotiable.
• shared/(template folder — the shared payment-lifecycle contract: capabilities, idempotency store, commerce types, provider interface, webhook verify)
• shopify/(template folder — Shopify static + framework integration scaffolds)
• square/(template folder — Square static + framework integration scaffolds)
• stripe/(template folder — Stripe static + framework integration scaffolds)

No items match that filter in this plugin.