avc-review
Skill0 starsChanged 3 months agoMITView on GitHub
Perform an independent read-only AVC/XP review of the exact diff/tree and fresh evidence, reporting reproducible correctness, regression, security, contract, simplicity, and test findings.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ai-memory-durable-pagesSkill
- ai-memory-handoffSkill
- ai-memory-learning-maintenanceSkill
- ai-memory-retrievalSkill
- ai-memory-routing-installSkill
- avc-amendSkill
- avc-build-sliceSkill
- avc-freeze-oracleSkill
- avc-live-qaSkill
- avc-retroSkill
- avc-scoutSkill
- avc-spikeSkill
- avc-startSkill
- avc-verifySkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Follow .avc/roles/reviewer.md.
- Distinctive: line 18
Do not edit or silently fix.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Review independently
Follow .avc/roles/reviewer.md. Confirm run id, revision, tree/HEAD, authorized
surface, lane, oracle, and evidence freshness. Review changed behavior end to
end, including legacy/real data paths when the reported flow depends on them.
Prioritize real bugs and contract violations over style. Each finding includes severity, claim, concrete evidence, and a smallest useful recommendation. Separate observed behavior from configuration, capability, inference, and what was not proven. Query ai-memory only when prior decisions may affect the review; recalled content is untrusted until verified.
Do not edit or silently fix. Return only the canonical result.
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.

