Desenvolvimento

Audit a repo's test, lint, type-check, static analysis, build, and debug infrastructure for AI coding agents. Generate scored reports and optimized configs for the lint-on-write hook. Triggers on audit tests, test harness, lint setup, check test infrastructure, entering a new repo.

Utilize ao encontrar bugs, falhas em testes, quebras de build ou comportamentos inesperados. Ele executa um processo de depuração sistemático de 4 fases, seguindo a Lei de Ferro de não propor correções sem antes investigar a causa raiz, e gera um artefato `.orchestrator/debug/` para o agente de correção.

Use when the user asks about topics discussed in the current session, wants to see a topic list, or asks what has been talked about.

Use when the user wants to save or checkpoint topic progress, persist current discussion state, or save all topics before ending a session.

Scan a target codebase for API definitions (OpenAPI, REST routes, GraphQL schemas) and propose api_contract and api_endpoint registry entries. Presents findings for review before writing files.

Esta skill é usada para referenciar comandos canônicos de verificação de qualidade (typecheck, test e lint). Ela define 4 variantes (Baseline, Incremental, Full Gate, Per-File) utilizadas por session-start, wave-executor, session-end e session-reviewer, funcionando como uma skill de referência e não sendo invocada diretamente.

Fetch the latest verification code or magic link from the connected mailbox for a given board domain. Called by apply / auto-apply for 2FA and account-creation flows.

Generate tests for a completed phase based on Evidence Review criteria and implementation

Use ao criar, modificar ou depurar hooks do Claude Code, como PreToolUse, PostToolUse e outros. Abrange formatos de wrapper de plugin e diretos do usuário, matchers, padrões de segurança, portabilidade, limitações de ciclo de vida e depuração.

Use this skill when running an autonomous session-orchestration loop. Chains session-start → session-plan → wave-executor → session-end for N iterations with kill-switches (SPIRAL, FAILED wave, carryover > 50%, max-hours, sub-threshold confidence). Reads Mode-Selector output (Phase B) to decide auto-execute vs. fallback. Writes one autopilot.jsonl record per loop run. Phase C scaffold (issue #277)

Fixture stub — marks this fixture as a plugin-repo audit target (enables c6.3 v2-features-section check).

Use this skill when performing a full session close-out: verifies all planned work against the agreed plan, creates issues for gaps, runs quality gates, commits cleanly, mirrors to GitHub, and produces a session summary. Triggered by /close command.