find-blind-spots
Skill2 starsChanged 44 days agoNo licenceView on GitHub
Use when the user asks for consequential knowledge, assumption, implementation, or verification gaps in accessible chats and current projects, including architecture, technology selection, completed changes, post-launch operations, and peer practices. Also use a lightweight pass at consequential decision checkpoints when a specific unexamined assumption could change the recommendation. 适用于“结合我们可访问的聊天和当前项目，找出一个我最有必要知道、但可能尚未考虑或落实的关键点”“重点检查这次改造上线后的问题，给出证据和最小验证动作”“基于所有聊天说一个我必要但可能不知道的知识”“我没想到什么”“还有什么坑”“同行做了什么而我没做”等请求；不要求出现“盲点”或四象限术语。普通事实问答、翻译、窄范围编辑和仅解释概念不触发。
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- before-git-pushSkill
- file-singlifySkill
- find-a-bugSkill
- git-commit-messageSkill
- google-stitch-extract-frontend-design-systemSkill
- google-stitch-frontend-brief-enhancerSkill
- google-stitch-frontend-taste-designSkill
- google-stitch-shadcn-uiSkill
- i-have-adhd-actionable-outputSkill
- project-bug-huntingSkill
- prompt-polishSkill
- superpowers-brainstormingSkill
- superpowers-systematic-debuggingSkill
- superpowers-test-driven-developmentSkill
- superpowers-using-git-worktreesSkill
- superpowers-verification-before-completionSkill
- superpowers-writing-skillsSkill
- yc-rejection-simulatorSkill
The file
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.