Desenvolvimento

Use when a concept is too abstract for the learner's current level and needs analogy-first teaching before complexity re-injection.

When ending a work session and wanting to capture what was accomplished, what was learned, and what to do next. Use when the user says "session review," "what did we do," "wrap up," "summarize session," "weekly review," "retrospective," "what happened today," "debrief," or at natural session endings. Reviews the session transcript, extracts learnings, identifies patterns, and produces an actionabl

Commit staged git changes w/ descriptive Conventional Commits message. Triggers when user asks to commit, save changes, ∨ mentions GitHub commits. Phrasings: "commit", "save my changes", "commit this".

Enable JavaScript grid extensions for a listing page. Extensions add sorting, filtering, bulk actions, column toggling, position reordering, and other interactive behaviors to the grid. Trigger: "add grid extensions for {Domain}", "enable grid extensions for {Domain}", "initialize grid JS for {Domain}".

Use ao adicionar novas mensagens de erro ao React, ou ao ver avisos de "código de erro desconhecido".

Framework health check：validate / 檢查 isolation 與 mechanisms；支援 "validate isolation", "validate mechanisms", "檢查隔離", "檢查機制", health check。

Analisa as mudanças de sessão para detectar habilidades de validação ausentes. Explora dinamicamente as habilidades existentes, cria novas ou atualiza as existentes, e então gerencia o CLAUDE.md do projeto.

TDD-first spec management for AI coding workflows. Use this skill when the user explicitly mentions specs, forging, or structured planning: says "forge", "forge a spec", "write a spec for X", "create a spec", "plan X as a spec", "resume", "what was I working on", "spec list/status/pause/switch/activate", "implement the spec", "implement phase N", "implement all phases", "red green refactor", "run

Resolução competitiva de problemas multiagente: Esta skill gera múltiplos subagentes Claude Code em worktrees git paralelos para resolver independentemente a mesma tarefa de programação. As soluções são polinizadas cruzadamente através de rodadas de melhoria onde cada agente vê e aprende com os diffs dos outros, e a melhor solução é selecionada por votação de consenso Borda com juízes independentes.

Use when creating debian/ directories for Python projects, modifying debian/control or debian/rules, building .deb packages with dh-virtualenv or dpkg-buildpackage, debugging dh_shlibdeps or dh_strip errors, fixing postinst/prerm/postrm scripts, writing systemd .service files for Python daemons, auditing existing debian/ packaging against Debian policy, troubleshooting conffile overwrites on upgra

Parameterized single-question intent-sharpening gate. ⊥ user-invoked — invoked from consumer cmd pre-apply gate (/gh:issue, /sdd:spec).

SAST orchestration for Semgrep, CodeQL and SonarQube. Covers tool selection, ruleset curation, PR-comment integration, noise reduction with baselines, and language-specific linters (bandit, gosec, brakeman, eslint-security) when they add coverage.