Use whenever the task involves an external integration connected through Executor — Notion, Context7, Supabase, Vercel, or any other MCP surfaced by mcp__executor__execute. Ensures these are always accessed through Executor instead of a direct MCP server, the…
Use whenever the task involves an external integration connected through Executor — Notion, Context7, Supabase, Vercel, or any other MCP surfaced by mcp__executor__execute. Ensures these are always accessed through Executor instead of a direct MCP server, the…
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module…
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow. Spanish triggers: "no funciona", "está roto", "falla", "da error", "revienta", "tira error", "se cae",…
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
Test-driven development — the reference that makes the red→green loop produce tests worth keeping. Use when implementing a feature or fixing a bug test-first, when writing or reviewing tests, on "red-green-refactor", or when integration tests are wanted.…
Writing documents an agent consumes. Use when creating or editing a skill, or modifying AGENTS.md or CLAUDE.md. Spanish triggers: "crea una skill", "edita la skill", "mejora la skill", "escribe una skill", "actualiza el CLAUDE.md", "instrucciones para el…
Taste-level review of a branch's diff for the patterns that mark AI-written code, with a verdict and a ledger of what to strip.