paulasilvatech

"Use when validating requirements against EARS notation patterns. Triggers on "EARS", "requirement review", "requirement quality", "shall statement", "REQ-ID"."

"Use when mapping business capabilities, identifying overlap or gaps across the enterprise, or aligning IT investments to business outcomes. Triggers on "capability map", "business capability", "domain map", "enterprise architecture"."

"Use when drafting Architecture Decision Records, evaluating alternatives, or documenting technical trade-offs. Triggers on "ADR", "architecture decision", "trade-off", "pick between", "why did we choose"."

"Use when a new engineer joins the team, when onboarding to an unfamiliar codebase, or when auditing whether the team has shared understanding. Triggers on "onboard", "context", "knowledge gap", "bus factor", "team understanding"."

Use when refactoring legacy code, extracting a service, or making behavior-preserving changes. Triggers on 'refactor', 'legacy code', 'strangler fig', 'characterization test', 'mikado method'.

Use when practicing test-driven development, writing a failing test first, or coaching red-green-refactor. Triggers on 'TDD', 'red-green-refactor', 'test first', 'failing test', 'write a test'.

Use when investigating slow queries, designing indexes, or reviewing execution plans. Triggers on 'slow query', 'explain plan', 'index', 'query tuning', 'N+1', 'table scan'.

Use when planning an online schema change, zero-downtime migration, or rolling back a deploy that changed a table. Triggers on 'migration', 'ALTER TABLE', 'zero-downtime', 'expand-contract', 'backfill'.

Decision framework for designing production agentic systems on GitHub platform and Azure AI Foundry. Covers model routing tiers (mini to frontier), prompt caching and semantic caching, short and long term memory, context curation and RAG, tools and MCP, identity and guardrails, evaluation, observability (OpenTelemetry GenAI), and cost control. Use when architecting an AI agent or multi-agent system, choosing a model router, deciding a caching or memory strategy, planning context windows, or reviewing an agent design for reliability, security, and cost. Pairs with azure-managed-redis-cache, foundry-agent-blueprint, azure-api-center, apim-ai-gateway, and azure-architecture-diagrams.

Front model and tool backends with Azure API Management as an AI gateway: token rate limiting (token-per-minute and quota), multi-backend load balancing and circuit breaker across model deployments, semantic caching, token metric emission for cost attribution, managed identity to backends, and content safety integration. Use when designing the runtime gateway for an agentic platform, enforcing token budgets, load balancing across model endpoints, adding a semantic cache at the gateway, or governing tool API calls. Routes to the installed azure-aigateway skill for policy detail. Pairs with azure-api-center (governance), azure-managed-redis-cache (cache backend), and agentic-architecture-patterns.

Validate an architecture document (the {app}_Architecture.md produced by the Senior Cloud Architect agent) against a hard Definition of Done: required sections, the five required diagrams, well-formed Mermaid, the seven explanation parts per diagram, and the repository copy conventions. Use when producing, reviewing, or finishing an architecture document, or whenever you need to confirm a Mermaid-based architecture deliverable is complete and will render before presenting it.

Govern APIs and agent tools at enterprise scale with Azure API Center: a central catalog of APIs, versions, definitions (OpenAPI), environments, and deployments, plus registration of agent tools and MCP servers for discovery and reuse. Use when designing API governance for an agentic platform, building a tool or MCP registry for agents, enforcing API standards with the API Center linter, or making backend APIs discoverable to agent builders. Pairs with apim-ai-gateway (runtime gateway), foundry-agent-blueprint (tool consumption), and agentic-architecture-patterns (tools and MCP).

Produce complete, professional architecture diagrams that use the official Azure, Microsoft, and GitHub (Octicons) icon sets, output as editable draw.io (.drawio) files and exported SVG. Covers the official icon catalogs and their terms of use, the draw.io mxGraph file format, layout and connector conventions, and a bundled draw.io MCP server (Python FastMCP) that creates and edits .drawio diagrams programmatically (add nodes with official icons, connect edges, group, and lay out). Use whenever the deliverable includes an architecture diagram, a system context, a component or deployment diagram, or any cloud diagram that must use official vendor icons. Pairs with ai-native-engineer and agentic-architecture-patterns, and complements svg-professional for hand-crafted SVG.

Design and provision Azure Managed Redis as the cache, semantic cache, vector store, session store, and agent memory backend for AI-native systems. Covers SKU selection (Balanced, MemoryOptimized, ComputeOptimized, FlashOptimized), the fact that Redis Enterprise is retired for new creations, vector search and RedisVL for semantic caching and long term memory, session and short term state, tenant isolation, managed identity (Entra) access, private networking, and a Bicep sample. Use when an agent design needs caching, a semantic cache, a vector memory store, or session state on Redis. Pairs with agentic-architecture-patterns and apim-ai-gateway.

Design and provision agents on Azure AI Foundry Agent Service: model catalog and deployments, connections (Azure AI Search, Azure Managed Redis, Bing, storage), threads and runs for short term memory, tools (function, OpenAPI, MCP, code interpreter, file search), evaluation, and tracing. Use when the target runtime is Azure AI Foundry, when choosing models from the Foundry catalog, when wiring agent tools and connections, or when planning Foundry evaluation and observability. Routes to the installed microsoft-foundry, azure-ai, and vscode-microsoft-foundry skills for provisioning detail. Pairs with agentic-architecture-patterns, azure-managed-redis-cache, azure-api-center, and apim-ai-gateway.

Creates professional Markdown documents with YAML frontmatter, versioning, author attribution, table of contents, and consistent formatting. Use for Markdown documents, README, ADR, spec, guide, changelog, runbook, RFC, technical docs, and converting PPTX or PowerPoint files to narrative Markdown reading editions with markitdown. Trigger on 'md file', 'markdown', '.md', 'documento markdown', 'criar um readme', 'escrever documentação', 'write a spec', 'draft a guide', 'convert PPTX to Markdown', 'extract PPTX', or 'PowerPoint to Markdown'. Do not use for creating PPTX presentations, Word documents, diagrams, or PDFs.

This skill should be used when the user asks to 'research codebase', 'scan tech stack', 'import documents', 'discovery questions', or needs guidance on Phase 1 research. Also trigger on 'sdd research', 'brownfield scan', 'import transcript', or 'check ecosystem'.

Use for Phase 2 (Specify): write SPECIFICATION.md with EARS, REQ-IDs, and acceptance criteria. Trigger on sdd_write_spec, sdd_turnkey_spec, sdd_validate_ears, or /specky-specify.

Use for Phase 4 (Design): produce DESIGN.md with architecture, API contracts, data model, and Mermaid diagrams. Trigger on sdd_write_design, sdd_generate_all_diagrams, or /specky-design.

Use for contracted implementation planning, executable TDD bindings, IaC, Docker, devcontainer, local environment, or Codespaces tools after an APPROVE analysis gate.

Use when starting or resuming Specky work, selecting lifecycle/workload/mode/capabilities, diagnosing config/state, or choosing an agent/tool.

This skill should be used when the user asks to 'orchestrate pipeline', 'run full pipeline', 'coordinate phases', 'advance phase', or needs guidance on end-to-end pipeline execution. Also trigger on 'specky orchestrate', 'phase transition', 'LGTM gate', 'pipeline status', or 'which agent for this phase'.

Use for Phase 6 (Analyze): completeness audit, cross-analysis, compliance, and ANALYSIS.md gate decision. Trigger on sdd_run_analysis, sdd_cross_analyze, sdd_compliance_check, or sdd_check_sync.

Use after verification to generate contracted documentation, PR, and work-item payloads under the persisted release policy.

Use ao validar requisitos contra padrões da notação EARS. Aciona com "EARS", "requirement review", "revisão de requisitos", "requirement quality", "shall statement", "REQ-ID".

Use ao mapear capacidades de negócio, identificar sobreposições ou lacunas na empresa, ou alinhar investimentos de TI a resultados de negócio. Aciona com "capability map", "mapa de capacidades", "business capability", "domain map", "enterprise architecture".

Use ao rascunhar Architecture Decision Records, avaliar alternativas ou documentar trade-offs técnicos. Aciona com "ADR", "architecture decision", "decisão arquitetural", "trade-off", "pick between", "why did we choose".

Use quando uma nova pessoa de engenharia entra no time, durante onboarding em um codebase desconhecido, ou ao auditar se o time tem entendimento compartilhado. Aciona com "onboard", "onboarding", "context audit", "knowledge gap", "bus factor", "team understanding".

Use ao investigar consultas lentas, desenhar índices ou revisar planos de execução. Aciona com 'slow query', 'consulta lenta', 'explain plan', 'index', 'query tuning', 'N+1', 'table scan'.

Use ao planejar uma mudança de schema online, migração com zero downtime ou rollback de um deploy que alterou uma tabela. Aciona com 'migration', 'migração', 'ALTER TABLE', 'zero-downtime', 'expand-contract', 'backfill'.

Use quando um teste for intermitente, ao investigar instabilidade no CI, ao colocar um teste em quarentena, ou ao criar um dashboard de flaky tests. Aciona com 'flaky test', 'teste intermitente', 'flaky', 'quarantine', 'CI instável', 'flaky dashboard'.

Use ao desenhar uma estratégia de testes, escolher o formato da pirâmide de testes, definir metas de cobertura ou avaliar investimentos nas camadas unit / integration / E2E. Aciona com 'test strategy', 'estratégia de testes', 'test pyramid', 'pirâmide de testes', 'coverage target', 'meta de cobertura'.

Orchestrates the production of all client-ready report deliverables for the AI Maturity Assessment Platform. Wraps the lower-level skills /preencher-planilha + /calcular-scores + /gap-analysis + /recomendar-estrategias + /wizard-implementacao + /gerar-relatorio. Renders 5 PDFs (Score Justification + 3 Pillar Roadmaps + Implementation Guide) using Jinja2 + WeasyPrint with paulasilva-ms branding (Microsoft 4-color palette). Mirror of the global skill `~/.github/skills/ai-maturity-reports/` adapted to this self-service kit. Use when the user asks for "pacote completo de relatórios", "gerar todos os PDFs", "todos os 5 PDFs", "rodar tudo de ponta a ponta", "rodar pipeline de reports", "AI Maturity report", "Score Justification", "Transformation Roadmap", "render the assessment PDFs", "ai-maturity-reports", "full reports pipeline", "complete pack", "all pdfs", "generate the bundle".

Computes capability/pillar/overall scores from respostas.json applying the official SUMPRODUCT algorithm from the platform. Generates saida/scores.json. Use when the user asks to "calcular scores", "computar pontuação", "rodar o scoring".

Computes gap (target − current) per capability and priority P0-P3 (weight × gap). Reads saida/scores.json and respostas.json::target_overrides. Generates saida/gaps.json. Use when user asks for "gap analysis", "priorização", "onde estão minhas lacunas".

Renders 5 client-ready PDF reports (Score Justification + 3 Pillar Roadmaps + Implementation Guide) by invoking relatorios/scripts/build_payload_and_render.py. The script merges sample_payload.json (rich structure) with client data from saida/scores.json + gaps.json + recomendacoes.json + respostas.json + implementation-guide-inputs.json. Output is identical-quality to the platform's production PDFs. Use when the user asks to "gerar relatório", "produzir o report executivo", "gerar PDFs", "PDF final", "consolidar resultados", "executive report", "final report", "render PDF", "generate report PDFs", "produzir o PDF executivo".

Converts an Excel exported from Microsoft Forms (or Google Forms / multi-respondent spreadsheet) into structured respostas.json for the AI Maturity Assessment, aggregating multiple respondents via mean per question. Use when the client collected responses via Forms and wants to run the pipeline. Trigger on "importar respostas", "import Forms", "converter Excel para JSON", "respostas-forms.xlsx", "Microsoft Forms para o assessment", "agregar respondentes". Looks for respostas-forms.xlsx at workspace root or path passed by the user.

Imports the Developer Survey results (Microsoft Forms export .xlsx) into structured JSON. The survey has 75 questions across 9 sections (Profile, Copilot adoption + modes, MS/GitHub tools, AI dev practices, Agent concepts, Markdown/Instructions, Usability, Security/Governance, Pain points). Different from /importar-respostas-excel which handles the maturity assessment. Use when user has respostas-survey-devs.xlsx and wants to analyze it.

Imports the Learning & Growth Survey results (Microsoft Forms export .xlsx, IDENTIFIED with name+email) into structured JSON. The survey has 32 questions across 7 sections (identification, self-perception of maturity, growth priorities, topics to learn, formats/cadence, champions, barriers/wishlist). Different from /importar-survey-devs (anonymous). Use when the user has respostas-survey-learning.xlsx and wants to generate the capacitation plan, or asks "importar survey de aprendizado", "importar Learning & Growth", "respostas-survey-learning.xlsx", "survey de treinamento", "survey-learning", "import learning survey", "import training survey", "learning & growth import".

Generates aggregated insights report from imported Developer Survey responses. Reads survey-devs/respostas-devs.json and produces saida/insights-developer-survey-<DATE>.md with: respondent demographics, Copilot adoption + mode usage, agent/MCP awareness, governance gaps, pain points (anonymized quotes), and prioritized recommendations linked to the maturity assessment capabilities (P1-C1, P1-C5, P1-C8, P2-C4, P3-C6). Use after /importar-survey-devs.

Workflow de implementação de features para o TodoApp. Define as fases Plan → Implement → Review → Verify, critérios de aceite por fase, e quais subagentes usar. Invocada pelo agente orchestrator quando o tipo de tarefa é "feature" ou "nova funcionalidade".

Workflow de correção de bugs para o TodoApp. Define as fases Reproduce → Debug → Fix → Test para correção sistemática. Invocada pelo agente orchestrator quando o tipo de tarefa é "bug", "fix", "corrigir" ou "erro".

Workflow de code review para o TodoApp. Define as fases Lint → Security → Review → Approve com checklist completo. Invocada pelo agente orchestrator quando o tipo de tarefa é "review", "code review" ou "revisar código".

Workflow de deploy e validação de release para o TodoApp. Define as fases Build → Test → Lint → Verify para garantir que o ambiente Docker Compose está saudável. Invocada pelo agente orchestrator quando o tipo de tarefa é "deploy", "build" ou "release".

Domain knowledge for the {{client_name}} client engagement — stakeholders, technology stack, and editorial standards. USE FOR: client deliverables, agent specs, architecture docs, status reports, any client-specific content. DO NOT USE FOR: generic documents not related to the client.

Creates professional, interactive multi-page websites from project documentation using React 18 + TypeScript + Tailwind CSS. Features landing page with hero and KPI cards, dark sidebar navigation, hash-based routing, full trilingual i18n (EN/PT-BR/ES), Microsoft+GitHub logo branding, and end-to-end storytelling. Develops with Vite (hot reload), bundles to single portable HTML via Parcel. USE FOR: create interactive site, project portal, documentation site, interactive dashboard, transform .md deliverables into website, create landing page, build project visualization, interactive architecture site, client-facing web portal. DO NOT USE FOR: FigJam/Mermaid diagrams (use figjam-diagrams), presentations (use pptx-creator), Word documents (use docx-creator), Excel (use xlsx-creator), PDF (use pdf-creator).

Creates professional Microsoft PowerPoint (.pptx) presentations with Microsoft branding, 16:9 format, 10-slide structure, and executive-grade content. USE FOR: create PowerPoint, generate pptx, build presentation, Microsoft branded slides, executive deck, technical presentation. DO NOT USE FOR: diagrams (use figjam-diagrams), Word documents (use docx-creator).

Create publication-quality SVG diagrams, charts, and infographics with professional connector routing, pixel-perfect alignment, and polished visual design. Covers all SVG types: flowcharts, architecture diagrams, quadrant charts, scatter plots, timelines, org charts, matrices, process maps, and any data visualization rendered as SVG. Use this skill whenever the user asks to create, improve, or fix any SVG file — even if they just say "diagram", "chart", "visual", "infographic", "fluxo", "diagrama", "quadrante", or "make me an SVG". Also trigger when the user shares an existing SVG and asks to improve its quality, fix alignment, or make it look more professional. This skill is specifically for hand-crafted SVG markup (not libraries like D3 or chart.js); for interactive HTML dashboards, use a dashboard skill instead.

Creates professional, well-structured Markdown documents with YAML frontmatter, versioning, author attribution, table of contents, and consistent formatting. USE FOR: create markdown document, write markdown, generate md file, create README, write technical doc, create ADR, architecture decision record, write changelog, create specification, write guide in markdown. DO NOT USE FOR: Word documents (use docx-creator), presentations (use pptx-creator), diagrams (use figjam-diagrams).

Gera PDFs profissionais Microsoft-branded via HTML intermediario + WeasyPrint com CSS Paged Media. Cores do logo ciclam por secao (Red→Green→Blue→Yellow), TOC clicavel, status badges, cover full-bleed. Script batch: sources/scripts/generate_all_pdfs.py. USE FOR: criar PDF, gerar pdf, batch PDF, PDF executivo, PDF com tabelas. DO NOT USE FOR: Word (docx-creator), PowerPoint (pptx-creator), Excel (xlsx-creator), diagramas (figjam-diagrams).

Create publication-quality SVG diagrams, charts, and infographics with professional connector routing, pixel-perfect alignment, and polished visual design. Covers all SVG types: flowcharts, architecture diagrams, quadrant charts, scatter plots, timelines, org charts, matrices, process maps, and any data visualization rendered as SVG. Use this skill whenever the user asks to create, improve, or fix any SVG file — even if they just say "diagram", "chart", "visual", "infographic", "fluxo", "diagrama", "quadrante", or "make me an SVG". Also trigger when the user shares an existing SVG and asks to improve its quality, fix alignment, or make it look more professional. This skill is specifically for hand-crafted SVG markup (not libraries like D3 or chart.js); for interactive HTML dashboards, use a dashboard skill instead.