essential-tool-install
Skill2 starsChanged 12 days agoMITView on GitHub
关键依赖工具安装不可跳过的治理规则。当任务的第一优先级/最有效手段依赖某工具(门禁、验证、证据采集),而该工具未安装且需要安装权限时,禁止降级跳过或换弱工具,直接把精确安装命令与方法交给协作者,安装完成后验证并继续原工作流。触发词:工具未安装/缺少依赖/需要 sudo/apt install/valgrind/uncrustify/cppcheck/lcov/gcov/工具缺失/安装权限。
- Installs packages
In this repository15 other files it gives its agents.
- skills/iso/light/CLAUDE.mdCLAUDE.md
- ai-code-reviewSkill
- api-design-reviewSkill
- architecture-support-briefSkill
- class-design-reviewSkill
- comment-policySkill
- cpp-exemplarsSkill
- error-code-classificationSkill
- isoSkill
- notion-diagramSkill
- reportSkill
- researchSkill
- incident-reviewSkill
- routerSkill
- test-naming-and-structureSkill
The file
Files
关键依赖工具安装(不可跳过)
判定
- 当前任务的最有效手段是否依赖某工具?是 → 进入本规则(如 valgrind 内存泄漏检测、uncrustify 格式门禁、cppcheck 静态扫描、gcov/lcov 覆盖率,无可替代手段)。
- 该工具未安装/不可用/版本不符,且安装需要权限(sudo / 管理员 / 仓库外安装)?
两条都满足 → 该步骤为阻塞态,禁止降级。
禁止行为
- 禁止跳过该门禁/验证步骤("先不跑,后续补"不成立——最有效手段缺失即证据缺失)
- 禁止换弱工具或近似手段顶替(格式检查替代 uncrustify、内存自检替代 valgrind 等)
- 禁止静默继续并宣称完成
- 禁止擅自提权安装或改用户环境(安装权限在协作者)
动作
- 明确标注该步骤为阻塞态:
待「<工具名>」安装后继续,写入工作记录。 - 给协作者可直接执行的精确安装命令:包管理器命令(apt/brew/dnf 等)+ 版本要求 + 安装后验证命令(
<tool> --version或指定验证)。 - 安装完成后,先运行验证命令回验(版本/可执行/关键参数符合要求),验证通过后再继续原工作流,并在工作记录回填安装结果。
- 若多个环境(本机/WSL/CI)都依赖该工具,命令按环境分别给出,各自验证。
记录
- 安装请求(工具、命令、原因)与安装结果(版本、验证输出)记入工作记录/日报,不得只留在对话中。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

