link-flame

WHEN to auto-invoke: Creating API routes, building endpoints, adding route.ts files, implementing REST/GraphQL APIs, adding authentication to APIs, rate limiting, API validation with Zod, handling HTTP methods (GET/POST/PUT/DELETE). WHEN NOT to invoke: Pure frontend work, styling, React components without API calls, documentation-only tasks, database migrations without API changes.

WHEN to auto-invoke: Code review requests, refactoring code, cleaning up code, performance optimization, security audits, linting issues, reducing technical debt. WHEN NOT to invoke: Building new features (use domain-specific skills), initial implementation, documentation-only work.

WHEN to auto-invoke: End of productive sessions, after solving difficult problems, after user corrections, after discovering effective workarounds, after establishing project conventions. WHEN NOT to invoke: Trivial sessions, sessions with only exploration, when explicitly told not to learn.

WHEN to auto-invoke: Database schema design, creating migrations, writing SQL queries, query optimization, Supabase operations, Prisma/Drizzle schema changes, PostgreSQL tasks, RLS policies, indexes. WHEN NOT to invoke: Pure frontend work, API logic without database, styling, React components, deployment tasks.

WHEN to auto-invoke: Creating CI/CD pipelines, GitHub Actions workflows, Docker/containerization, Vercel/Netlify deployment, infrastructure as code, environment variables, deployment configurations. WHEN NOT to invoke: Application code changes, UI development, database schema design, testing application logic.

WHEN to auto-invoke: Measuring code quality, testing AI outputs, establishing success criteria, defining acceptance tests, checking implementation correctness. WHEN NOT to invoke: Simple implementations, prototyping, exploration phases, when speed matters more than measurement.

WHEN to auto-invoke: Creating UI components, building React/Vue/Svelte components, Next.js pages, styling with Tailwind/CSS, state management setup, form handling, accessibility improvements, client-side interactivity. WHEN NOT to invoke: API-only work, database operations, backend logic, DevOps/deployment, pure testing without UI.

Use this skill for isolated branch workflows and parallel development. Activates when working on features that need isolation, switching contexts, or managing multiple branches.

WHEN to auto-invoke: Session start, session end, referencing previous work, asking "what did we do before", resuming work, continuing from previous sessions. WHEN NOT to invoke: Fresh starts with no prior context, completely new projects, when user explicitly wants a clean slate.

Use this skill to break work into small, verifiable chunks. Activates when planning implementation, breaking down features, or when tasks seem too large.

Use this skill to coordinate concurrent agent work. Activates when tasks can be parallelized, during multi-agent workflows, or when orchestrating independent work streams.

WHEN to auto-invoke: Debugging issues, fixing bugs, investigating errors, "not working" problems, unexpected behavior, stack traces, error messages, troubleshooting, "why is this happening". WHEN NOT to invoke: Building new features from scratch, documentation, refactoring working code, adding tests to working code.

Use this skill to verify work matches requirements. Activates when checking against specifications, validating acceptance criteria, or ensuring implementation matches design.

WHEN to auto-invoke: After 50+ edit operations, long sessions, before context overflow, when suggested by hooks, transitioning between major task phases. WHEN NOT to invoke: Mid-implementation, during active debugging, when context is critical to current work.

WHEN to auto-invoke: Debugging issues where root-cause-analysis already identified the problem, implementing fixes for diagnosed bugs, applying systematic debugging methodology, stuck on a bug after initial investigation. WHEN NOT to invoke: Initial problem investigation (use root-cause-analysis first), new feature development, refactoring working code.

WHEN to auto-invoke: Finishing tasks, claiming "done" or "complete", before marking work finished, when asserting code works, wrapping up implementations. WHEN NOT to invoke: During active development, exploration phases, planning discussions, research tasks.

WHEN to auto-invoke: Writing E2E tests, browser automation, Playwright tests, visual regression testing, integration testing, test file creation (*.test.ts, *.spec.ts), testing user flows. WHEN NOT to invoke: Unit tests for pure functions, API-only testing, database testing, documentation, non-testing implementation work.