hidden-assumption-audit
Skill4 starsChanged 40 days agoNo licenceView on GitHub
Audit code for decisions nobody made: places where the author (often an AI) hit an open question and answered it in code instead of asking. Six families: invented values (hardcoded timezones, magic defaults), invented behavior (silent fallbacks, made-up failure handling), misplaced robustness (guards against the impossible), invented structure (needless wrappers, premature abstraction, dead code), invented interpretation (ambiguous requirements read one way), and invented duplicates (re-answering what the codebase already answered). Report only, never auto-fix; confirmed choices are recorded in ASSUMPTIONS.md and never re-asked. Use whenever the user asks to review code for assumptions, hardcoded values, fallbacks, defensive bloat, over-engineering, or unnecessary nesting; says "会不会有问题 / 是不是写死了 / 逻辑对不对 / 这里为什么这么写"; after landing a large AI-written change; or when one suspicious pattern is spotted and the user wants to know what else was decided without them.
In this repository4 other files it gives its agents.
- apple-chinese-typographySkill
- consistency-auditSkill
- design-md-creatorSkill
- general-writing-styleSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
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.