roli-lpci/quick-gate-js / .agents/skills/quick-gate-js
quick-gate-js
UnverifiedRun the optional KWIK-E-GATE JS/TS adapter or interpret its gate-result/v1 diagnostics. Use for JavaScript/TypeScript project checks; the core owns completion receipts.
Quick Gate JS adapter
Requires Node.js 18+ and explicitly installed project tooling. Standalone use does not require Python.
Use an explicitly installed quick-gate or this checkout's node src/cli.js.
The source candidate is 0.4.0; published 0.3.2 remains compatible for evaluation.
Do not download packages implicitly.
Quick Gate collects the project's lint, typecheck, build and Lighthouse results.
It emits validated gate-result/v1 diagnostics; use the core's kwik-gate run
for content-bound completion receipts. Neither result proves code correctness.
Prepare a changed-files manifest (newline-delimited paths or a JSON array), then run:
npx --no-install quick-gate run --mode quick \
--changed-files /path/to/changed-files.txt \
--output-dir /path/to/external-output
Read stdout's gateResult, artifacts and runId. Run artifacts use an external
temporary directory by default, including failures.json, run-metadata.json
and gate-result.json; follow the returned paths. Missing enabled tools, timeouts,
changed inputs and all-skipped evaluation cannot become a verified pass. full
adds the build stage; explicitly disable inapplicable checks in project config.
Repair is separate and can modify source. In 0.4.0 it defaults to deterministic;
--model-assisted explicitly opts into Ollama. Published 0.3.2 users must request
--deterministic-only. Inspect the repair report and source diff before accepting.
For configuration, exact verdict/exit semantics and complete examples, read the standalone JS guide. The packaged plugin's detailed entrypoint describes its fixtures.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |