CI/CD

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Complete Godot Engine knowledge base combining official documentation and source code analysis

Verify deployments on Hostinger VPS srv759970 after code changes. Checks HTTP status, PM2 processes, takes screenshots, and generates deployment reports.

Specialized knowledge for working with Angular 19 and Nx in the Sentinel monorepo. Use when generating components, running tests/builds, or working with the frontend workspace structure.

Generative UI implementation patterns for AI SDK RSC including server-side streaming components, dynamic UI generation, and client-server coordination. Use when implementing generative UI, building AI SDK RSC, creating streaming components, or when user mentions generative UI, React Server Components, dynamic UI, AI-generated interfaces, or server-side streaming.

Manage exercise data, validate schemas, sync with Supabase, and maintain the Exicon database. Use when adding exercises, validating data, debugging data issues, or syncing. Keywords: exercise, exicon, supabase, data, json, validation, sync.

Comprehensive Ruby and Rails code review using Sandi Metz rules and SOLID principles. Automatically runs rubycritic and simplecov, analyzes changed files in current branch vs base branch, identifies OOP violations, Rails anti-patterns, security issues, and test coverage gaps. Outputs REVIEW.md with VSCode-compatible file links. Use when reviewing Ruby/Rails code, conducting code reviews, checking for design issues, or when user mentions code review, pull request review, or code quality analysis.

Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Includes tech debt analyzer, team scaling calculator, engineering metrics frameworks, technology evaluation tools, and ADR templates. Use when assessing technical debt, scaling engineering teams, evaluating technologies, making architecture decisions, establishing engineering metrics, or when user mentions CTO, tech debt, technical debt, team scaling, architecture decisions, technology evaluation, engineering metrics, DORA metrics, or technology strategy.

Specialized codebase understanding agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search.

Searches and analyzes bash command history using Atuin CLI integration. Use when finding previously-run commands, analyzing command patterns, searching for cloud/deployment commands, or when mentioned 'bash history', 'atuin', 'command history', 'what command did I use', 'find command'.

Enable stricter TypeScript and linting checks to catch bugs early, especially useful when iterating with AI assistance.

Auditar segredos e variáveis na esteira CI/CD (GitHub Actions) e no runtime (Docker Swarm), verificando integração via OIDC com Azure Key Vault e paridade de ambientes. Use quando houver falhas por falta de segredos, variáveis ausentes, “id-token: write” ausente, ou inconsistência entre Key Vault, Swarm e workflows.

Comprehensive REST and GraphQL API design patterns, best practices, OpenAPI specifications, versioning, authentication, error handling, pagination, rate limiting, and security. Use when designing APIs, creating endpoints, reviewing specifications, implementing authentication, or building scalable backend services.

Expertise in CI/CD pipeline creation, process automation, and team workflow optimization. Activates when working with "automate", "pipeline", "workflow", "CI/CD", "process", or automation tools.

Build context-efficient, reusable skills using graph-based workflow orchestration with Claude Code subagents. Combines PocketFlow-inspired graph abstraction with multi-model optimization (Haiku for exploration, Sonnet for analysis). Use when building complex workflows, converting external frameworks to Claude skills, or optimizing for cost and context efficiency.

Research latest library documentation, industry best practices, and technical knowledge to automatically generate project-level skills. Use when asked to: (1) Research and create a skill for a library/framework, (2) Build a skill based on architectural patterns, (3) Generate skills from technical research, (4) Create domain-specific technical skills from web research, or (5) Any request combining research with skill creation.

Review and score engineering specs against a startup-focused quality rubric. Penalize over-engineering and reward simplicity.

Review a PR created through the spec/plan/implement flow. Analyzes changes against specification and provides actionable feedback. Only invoke when user explicitly requests to review a PR or review changes.

Ruthless concision for AI prompts and context - "Not One Word Wasted"

Create a new Architectural Decision Record (ADR) with automatic numbering and standard template. Use when documenting significant architectural or design decisions in the mlir-sem project.