meta-skill

通过软链接将 .claude/skills 同步到其他 agent 目录（.codex/skills, .cursor/skills 等），自动创建、更新、清理软链接，保持跨环境 skill 即时同步

输入 GitHub skill 仓库 URL，生成 npx skills add 安装命令。涉及'安装 skill'/'skill 安装'时路由至此。

Coordinate software release preparation, rollout readiness, migration notes, rollback planning, stakeholder communication, and final go/no-go release packets. Use when asked to prepare a release packet, review release readiness, or turn scattered launch notes into one reusable release workflow. Do not use for generic project planning, one-off announcement drafting, or high-level release theory.

Review frontend code for accessibility, risky UI security issues, missing states, and common UX regressions. Use when asked to review React, UI, frontend components, forms, a11y, or pre-merge frontend quality.

Review frontend code before merge.

Review frontend code for accessibility, risky UI security issues, missing loading and error states, and pre-merge regressions. Use when asked to review React, UI, forms, frontend components, or merge-readiness for the frontend.

Build governed incident command packets. Use when asked to standardize incident review, run severity assessment, or assemble incident communication.

Clean messy meeting notes into structured markdown summaries. Use when asked to organize meeting notes, extract action items, separate decisions from open questions, or turn rough notes into a clean recap.

Review frontend code for accessibility, UI security, missing states, and UX regressions. Use when asked to review React components, run a pre-merge frontend review, or check a11y and unsafe rendering.

Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.

Test fixture for governance validation.

Broken YAML fixture for packager failure testing.

对抗式审查。强制站在「对立面」对方案、代码、文章、决策或任何产出进行攻击性审查，主动寻找破绽、盲区、漏洞和反例，而不是顺向确认它没问题。与第一性原理（管生成）对称，本 skill 管「验证」——当用户想确认一个东西「真的没毛病」「能扛得住」时使用。典型场景：代码上线前的 BUG 狩猎、文章/方案的逻辑挑刺、商业方案的反驳、决策的风险排查、系统健壮性测试。只要用户提到「审查/Review/找漏洞/挑刺/挑毛病/有没有问题/扛得住/边界情况/反例/攻击/压力测试/能不能上线/确认没毛病」，或表达「帮我看看这东西稳不稳/会不会出错」，就触发本 skill。尤其当用户说「开启多 agent 对抗审查」时，必然触发。

第一性原理解读与分析。把任何复杂的技术栈、新概念/新领域、模糊问题或一段内容，剥离表象拆解到不可再分的「根本问题」，建立可迁移的心智模型。当用户想真正「搞懂」某个东西的本质而不是表面用法时使用——例如理解一个项目的库/框架各自解决什么根本问题、刚转一个新领域想快速建立认知框架、面对复杂问题想找到本质、或想把一篇文章/书的底层逻辑提炼出来。只要用户提到「第一性原理」「本质」「为什么」「根本」「底层逻辑」「拆解」「从零理解」「心智模型」，或表达「看不懂一堆名词想理清」，就触发本 skill。