Explorar skills

Use when: 需要检查super-pm更新、升级到新版本、回退到旧版本 Do NOT use when: 正常使用skill无需版本管理、首次安装而非升级

This skill should be used when the user asks to "generate tests", "write unit tests", "analyze test coverage", "scaffold E2E tests", "set up Playwright", "configure Jest", "implement testing patterns", or "improve test quality".

Orquestre múltiplos LLMs como um conselho, gerando inteligência coletiva através de revisão por pares e síntese do presidente.

GitHub Actions deployment — workflows, releases, GHCR, CI/CD with safety gates.

Removes AI artifacts, cleans comments, simplifies documentation in code. Use when - humanizing code, removing AI comments, cleaning docs, fixing unicode, making code human-readable. Trigger keywords - humanize, human, ai artifacts, ai comments, clean comments, simplify docs, unicode fix, remove generated, make readable.

Disables or enables individual plugin skills by writing skillOverrides to ~/.claude/settings.json (survives plugin updates). Modes: off, user-invocable-only, name-only. Triggers: disable skill, enable skill, toggle skill, hide skill, skill-toggle.

Para trabalho GTM com Deepline SDK/CLI, use para gerenciar plays, encontrar e enriquecer dados de empresas/contatos, dimensionar TAMs, controlar gastos e exportar CSVs.

Loop autorreferencial até a conclusão da tarefa com verificação do arquiteto.

Use when: 需要进行市场调研数据收集、竞品信息采集、行业舆情监控、合规政策检查 Do NOT use when: 已有完整数据无需补充、仅需内部数据分析无需外部信息

Creates brewcode execution PLAN.md from a SPEC file or Plan Mode file with phases, tasks, agents, and dependencies. Part of brewcode workflow (spec -> plan -> start). Triggers: create PLAN.md, brewcode plan, generate execution plan from spec, build plan from SPEC.md, task plan from requirements, brewcode:plan.

Orchestrates Claude Code skill management — lists skills, improves existing skills, or creates new ones with activation optimization and triggers. Triggers: create skill, new skill, improve skill, fix skill activation, skill doesn't trigger, list skills, skill management, optimize skill.

Use when the user wants to improve a specific article under a fixed viral-scoring rubric, iterate on one article to raise its score, or run single-article scoring plus rewrite loops. Best for content optimization experiments where the scoring prompt stays fixed and the article text is the thing being changed.