About project-min-evaluation
project-min-evaluation is a skill for verifying project quality before implementation is reported complete or committed. It discovers the package manager and runs only applicable scripts defined by the project, stopping at the first failure.
Key features
- 01Package manager detection
- 02Discovery of defined quality scripts
- 03Ordered script execution
- 04Stop-on-failure checks
- 05Structured verification reporting
Use cases
- 01Checking work before marking it complete
- 02Verifying changes before a commit
- 03Reporting missing or failed checks
- 04Selecting project-defined test commands
Install
Copy the command and run it in a terminal.
$
npx skills add https:/After installing, type/project-min-evaluationin Claude Code to confirm it loaded.
Bundled filesreferences/script-discovery.md
Details
From the project READMEProject Minimum Evaluation
Activation Contract
Load this skill before reporting implementation work as complete, before committing, or when asked to verify quality.
Hard Rules
- Detect the package manager from the project; never hardcode a runner.
- Run only scripts defined in
package.jsonscripts; report expected scripts that are missing instead of inventing commands. - Run from the repository root, in the order below, and do not skip a failing step to reach a later one.
- Never claim completion while a check fails or was not run.
Decision Gates
| Project signal | Runner |
|---|---|
packageManager field in package.json | use the manager it names |
pnpm-lock.yaml | pnpm run <script> |
bun.lock or bun.lockb | bun run <script> |
package-lock.json, or no other signal | npm run <script> |
| Script | Run when |
|---|---|
lint | always, if defined |
typecheck | always, if defined |
format:check | always, if defined |
test | always, if defined |
doctor | always, if defined |
check | always, if defined (aggregate gate) |
test:e2e | only when end-to-end behavior changed |
Execution Steps
- Read
package.jsonand the lockfiles to choose the runner. - Collect the scripts from the table that exist in
scripts. - Run each existing script in table order with the chosen runner.
- Stop at the first failure, fix it, and rerun from that script.
Output Contract
Report each script as passed, failed, or not defined. For a failure or a check that cannot run, give the exact command, the exact error, and the unverified scope.
References
- references/script-discovery.md — detection edge cases.
Comments
Markdown supported