pm-selfcheck
Skill84 starsChanged 8 months agoMITView on GitHub
Use when: 需要检查 super-pm 技能包安装完整性、元数据和体积 Do NOT use when: 正在执行具体 PM 任务且不需要安装诊断
In this repository58 other files it gives its agents.
- llms.txtllms.txt
- pm-evidence-auditSkill
- prompt-peSkill
- pm-brainstormSkill
- pm-clarifySkill
- pm-competitorSkill
- pm-deep-talkSkill
- pm-demandSkill
- pm-interviewSkill
- pm-journeySkill
- pm-marketSkill
- pm-mvpSkill
- pm-poolSkill
- pm-prioritySkill
- pm-searchSkill
- pm-brand-motionSkill
- pm-dataSkill
- pm-docsSkill
- pm-featureSkill
- pm-positionSkill
- pm-prd-reviewSkill
- pm-protoSkill
- pm-techSkill
- pm-user-storySkill
- pm-aarrrSkill
- pm-abtestSkill
- pm-feedbackSkill
- pm-geoSkill
- pm-growthSkill
- pm-iterationSkill
- pm-okrSkill
- pm-reportSkill
- pm-retroSkill
- pm-roadmapSkill
- pm-agileSkill
- pm-changeSkill
- pm-crossSkill
- pm-releaseSkill
- pm-riskSkill
- pm-business-modelSkill
- pm-decisionSkill
- pm-funnelSkill
- pm-portfolioSkill
- pm-resourceSkill
- pm-career-coachSkill
- pm-interview-prepSkill
- pm-resumeSkill
- steve-jobs-perspectiveSkill
- pm-previewSkill
- super-pmSkill
- start-super-pmSkill
- super-pm-upgradeSkill
- analyze-growthSkill
- define-strategySkill
- discoverSkill
- plan-launchSkill
- validate-ideaSkill
- write-prdSkill
The file
Files
super-pm 安装与内容自检
这是显式诊断工具，不是每次技能调用都要运行的更新检查。先从已加载的本 SKILL.md 路径定位同目录下的 scripts/selfcheck.sh，然后执行：
bash "<当前 pm-selfcheck skill 的绝对目录>/scripts/selfcheck.sh"不要把当前业务项目的 VERSION、.git 或工作目录当成技能包根目录。脚本根据自身的真实路径识别两种安装布局：
- 完整 Git 仓库/软链接：扫描包内技能和版本。
npx skills add --copy扁平安装：仅检查该包预期技能名；缺少任一技能时以非零状态报告MISSING，不会把单独安装当作全包健康。
检查元数据（name、description、allowed-tools）和超长技能（>600 行）。把实际输出解释给用户；MISSING 和 BAD_METADATA 不能汇报为通过。单独复制此 skill 时提示安装完整技能包。不要在没有实际运行命令的情况下生成“健康报告”，也不要自动联网或改动业务项目。
需要升级时请另行调用 /super-pm-upgrade；本 skill 只读。
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.