jev
Skill0 starsChanged 2 months agoMITView on GitHub
Score the changed files of the current branch with Jev (typesafe-ai evaluation model via Vercel AI Gateway) — bug risk, logic in components, missing tests, published-snapshot writes. Triggers — "/jev", "run jev", "jev the diff", «прогони jev», «что скажет jev».
- Reads credentials
32 other projects use a version of this.
Adopted by
Most recently taken up by
- fralapo/awesome-agent-skillstheir own version, first seen Nov 7, 2026
- Lu1sDV/skillsmdtheir own version, first seen Nov 4, 2026
- josecabralf/skillstheir own version, first seen Nov 1, 2026
- dagonet/claude-code-toolkittheir own version, first seen Nov 1, 2026
- connorch/skillstheir own version, first seen Oct 28, 2026
- GastonGelhorn/jevmatetheir own version, first seen Oct 25, 2026
Other versions32 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 32
- wuyoscar/jev-skill★ 665same name
- joetawil7/first-pass★ 128same name
- FrancoisChastel/jev-code★ 44same name
- BorisLeMeec/jev★ 38same name
- flc1125/skills★ 38same name
- pragma-sh/pragma★ 25same name
- ciberjohn/Hermes-Skills★ 17same name
- ratacat/ratacats-skills★ 9same name
- Vincent-the-gamer/skills★ 9same name
- AlexPEClub/Jev-Model-Router-Claude-Code★ 8same name
22 more not listed
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.
The file
Files
jev
Cheap triage of a PR's files before a human or a model reads them. Jev does not read code the way an LLM does: it scores a state against a rubric and returns probabilities. Treat the output as "which files deserve attention", not as findings.
Run
bash "$CLAUDE_PLUGIN_ROOT/skills/jev/scripts/jev-diff.sh" [base-ref]Takes AI_GATEWAY_API_KEY (a Vercel AI Gateway key of the team that pays) from the environment, else from 1Password at op://Personal/Vercel AI Gateway/credential; needs jq, gh, op. Base resolves like all-check: PR base, else the release/* branch, else main. Specs, src/api/ and lockfiles are skipped; each remaining file goes in as its own diff, capped at 60 KB.
Questions live in scripts/questions.json; a repo can override them with .jev-questions.json at its root.
Report
One line per file, sorted by bug_risk.score descending: file → score → the booleans that came back above 0.5. Nothing else. A run costs a fraction of a cent.
Evaluation period
While Jev is on trial, after every run note in memory what it flagged and what the review (human, Copilot, codex) actually found, so the trial ends on data, not on impression.
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.