Skip to content
Back to skills

Vibe Quality Loop

ASecurity

Runs the Implement→Review→Test→Fix cycle until the work is actually clean, with evidence. Use after any non-trivial implementation and before claiming it is done.

  • 85 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 25, 2026
ai-agentsgocode-reviewdocumentation

Works with

  • claude code

Security analysis

A100/100

Scanned September 25, 2026

npx -y skills add ash1794/vibe-engineering --skill vibe-quality-loop --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Vibe Quality Loop?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Vibe Quality Loop
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ash1794-vibe-quality-loop/badge)](https://www.skillsdirectory.com/skills/ash1794-vibe-quality-loop)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: vibe-quality-loop
description: Runs the Implement→Review→Test→Fix cycle until the work is actually clean, with evidence. Use after any non-trivial implementation and before claiming it is done.
user-invocable: true
---

# vibe-quality-loop

The quality loop prevents premature "done" declarations. Keep iterating until the review is clean and the tests pass, and show the evidence.

## When to Use This Skill

- After an implementation that touches more than a couple of files or any non-trivial logic
- After implementing a feature with tests
- Before creating a commit or PR on completed work

## When NOT to Use This Skill

- Single-line fixes or typo corrections
- Documentation-only changes (use `vibe-doc-quality-gate`)
- When the user says "just get it working, we'll clean up later"

## The Loop

```
Implement → Self-review diff → Run checks ─┬─ clean + green → EXIT
                ↑                           │
                └──────── Fix issues ←──────┘
```

## Steps

1. **Review the diff** — Read the whole diff as a reviewer would. If the harness has a built-in review command (for example `/code-review` in Claude Code or `/review` in Codex), run it. Otherwise check for:
   - Bugs: wrong conditions, off-by-one errors, unhandled error paths, broken edge cases
   - Leftovers: unused imports and variables, debug output, commented-out code
   - Consistency: does it match the naming and idioms of the surrounding code?
   - Scope: anything not requested (`vibe-scope-guard`)
   - Test integrity: were any tests weakened to pass? (`vibe-anti-rationalization-check`)

2. **Run the project's own checks** — Use what the repo defines (Makefile, `package.json` scripts, CI workflow) rather than guessing:
   - Full test suite, not just the tests you wrote
   - Linter, formatter, type checker
   - The race detector for concurrent code where the language has one (e.g., `go test -race`)

3. **Fix** only the issues found. Don't add features while fixing.

4. **Loop** back to step 1. Track the iteration count.

5. **Exit** when the review is clean and all checks pass. Quote the final check output. Don't paraphrase it.

## Stop Conditions

- After 5 iterations without converging, stop and report what's stuck rather than looping further.
- A failure that also happens on the base branch is pre-existing. Report it; don't "fix" it silently in this change.

## Output Format

### Quality Loop: [Feature Name]

**Iterations**: X · **Final status**: CLEAN / KNOWN_ISSUES

| Iteration | Issues found | Fixed |
|-----------|-------------|-------|
| 1 | [list] | [list] |

**Final checks**: `[command]` → [result]

**Remaining known issues** (if any):
- [issue deliberately deferred, with justification]

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.