jev-pr-quality
GitHub Action where Jev rates each PR across 19 software-quality dimensions, gates on thresholds and logs to a RawTree dashboard.
Overview
Jev PR Quality adds Jev-assisted pull request reviews and a live quality dashboard to a repository. A GitHub workflow sends the complete PR diff to Jev, which rates it across 19 typed software-quality dimensions. The action posts a review comment, creates a required check, stores an artefact, and fails the PR when any applicable dimension falls below the configured threshold, so a single critical weakness is not averaged away.
Optionally, each result is appended as a structured event to a RawTree database using a write-only key, and a multi-repository dashboard (hosted or self-deployed) shows scores using a separate read-only key or Vercel sign-in. The README argues that prose code reviews are hard to compare and get lost in PR timelines, while typed ratings are both actionable and measurable over time. The main branch is a preview channel until a stable v1 release.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Score | How does this PR rate on each of 19 software-quality dimensions? | — |
| Yes / no | Does this dimension apply to this PR?(inferred) | yes · no |
How it works
- Copy the workflow and add JEV_API_KEY and RawTree write key secrets
- On each PR, Jev rates the full diff on 19 dimensions
- The action comments, sets a required check and fails below threshold
- Events are logged to RawTree for the dashboard
Strengths
- Repeatable, comparable review scores
- Whole diff reviewed, not a sample
- Safe key split between CI and viewers
- Multi-repository dashboard
Caveats
- Preview status until v1
- Dashboard requires a RawTree account
- Ratings are probabilistic signals, not proof
Getting started
Copy examples/jev-review.yml into .github/workflows/ and add JEV_API_KEY and RAWTREE_JEV_API_KEY secrets.At a glance
- Type
- App
- Status
- beta
- Language
- TypeScript
- Runtime
- GitHub Action plus web dashboard
- Has code
- yes
- Has tests
- yes
Use cases and integrations
How curated lists describe it
Jev-assisted pull request quality reviews and a multi-repository RawTree dashboard.
hellogumbo/awesome-jev
Frequently asked questions
What does Jev decide?
A typed rating for each of 19 quality dimensions on the full PR diff.
When does a PR fail?
When any applicable dimension falls below the configured threshold.
Is the dashboard required?
No. RawTree logging is optional; the review and check work without it.
Related projects
Rust code-review gate asking Jev small typed questions about functions and tests, failing CI only on rules measured 80% right.
CLIproductionRustCoding-agent hook that asks Jev one yes/no per project rule on every edit or turn and makes the agent fix any violation.
HookbetaTypeScriptAdvisor for coding agents: git and Stop hooks flag test tampering, secrets and skipped hooks, with optional Jev review findings.
HookbetaRead-only Go CLI that checks files against your plain-language code rules with Jev, locally or in CI.
CLIbetaGoCLI and agent commands auditing a git diff against YAML standards packs, scoring each hunk with Jev so agents fix only flags.
Agent skillbetaTypeScriptFuzzy linter hook for Claude Code and Codex where Jev checks each written file against team rules and reports violations at edit time.
HookbetaTypeScript