vet-review
Skill1 starsChanged 3 months agoMITView on GitHub
Critically review the current code-review result - validate every finding against the real code, catch false positives and misses, and recalibrate severity
In this repository4 other files it gives its agents.
- better-documentsSkill
- deslopSkill
- vet-planSkill
- vet-testsSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Check, validating every finding with tools (read the file, reproduce the failure scenario - never take the description at face value):
- Distinctive: line 27
Keep it tight. No extra prose, no severity catalog.
≈ “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.
Files
Critically review the current code-review result (findings from a code-review command or similar). Do not edit the code or the review - return recommendations only, so they can be relayed to whoever owns it.
Check, validating every finding with tools (read the file, reproduce the failure scenario - never take the description at face value):
- Is each finding actually correct?
- Is the severity right for the verified impact, not just how alarming it reads?
- Anything the review should have caught but missed, given what you now know about the code?
Then report exactly this, and nothing extra:
Verdict - one line: does the review hold up, or does the finding set need changes first? Call out up front if nothing changed.
Checked - a compact table, one row per finding:
| Finding | How checked | Holds? |
| ... | read foo.ts / reproduced X | yes / no / severity wrong |
Revised findings - one numbered list, most-important-first, including anything the review missed. Each item:
N. [blocking|minor] <finding> -> <what changed: kept / dropped / re-severitized / added, and why>
Keep it tight. No extra prose, no severity catalog.
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.