decision-review
Skill1 starsChanged 7 months agoMITView on GitHub
Audit the quality of reasoning, not just code — problem framing, hypothesis quality, risk estimation
Files
decision-review
Reviews the thinking process that led to the code, not the code itself.
What it scores (1–5 each)
- Problem framing — was the right problem solved?
- Hypothesis quality — were alternatives considered before committing?
- Risk estimation — were risks accurately scoped?
- Decision under uncertainty — was overconfidence present?
- Verification quality — was success defined before starting?
Why it exists
@review checks correctness. @decision-review checks judgment.
A system that only checks correctness will repeat the same reasoning failures. A system that checks judgment improves over time.
Patterns are persisted to memory and can be encoded into rules.
Example
@decision-review "the auth middleware incident from this session"Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- WupfAGI/claude-investment-skills★ 14same name
- jack4world/auditstack★ 9same name
- CN-WenYu/skills★ 2same name
- DerivativeLabs/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.