i-onlabs/claude-code-skills/quality-gates

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use before claiming any task complete. Enforces verification steps, test execution, and proof of success. Prevents premature completion claims and ensures work is actually done.

Install

npx vskill@latest install i-onlabs/claude-code-skills/quality-gates

SKILL.md

Quality Gates Before Completion

Iron Rule

NEVER claim completion without evidence.

This skill activates before ANY "done", "complete", "finished", or "ready" statement.

When This Skill Activates

  • About to say "done" or "complete"
  • Task appears finished
  • User asks "is this done?"
  • Before creating a PR
  • Before merging code

Mandatory Quality Checks

1. Tests Pass
bash
# Run relevant tests
pytest tests/
npm test
cargo test

Show the output. Don't just say "tests pass."

2. No Regressions
  • Run the FULL test suite, not just new tests
  • Existing functionality still works
  • No new warnings or errors
3. Type Checks (if applicable)
bash
# Python
mypy src/
pyright src/
# TypeScript
tsc --noEmit
4. Linting Clean
bash
# Python
ruff check .
# JavaScript/TypeScript
eslint .
# Rust
cargo clippy
5. Manual Verification

Actually TEST the feature:

  • Run the code
  • Check the output
  • Verify expected behavior

Evidence Format

Before claiming "done", provide:

## Verification Evidence
### Tests
Command: pytest tests/test_feature.py -v
Result: 5 passed in 0.23s
### Type Check
Command: mypy src/
Result: Success: no issues found
### Manual Test
Action: Called API endpoint with test data
Result: Returned expected response {status: "ok"}

Quick Checklist

[ ] Tests written and passing
[ ] Existing tests still pass
[ ] Type checks clean
[ ] Linting clean
[ ] Manually verified behavior
[ ] Showed evidence in response

Integration

This skill combines with:

  • verification-before-completion (from Superpowers)
  • test-driven-development (ensures tests exist)
  • Project-specific test commands

Common Excuses (Don't Accept)

  • "It should work" → Run it and prove it
  • "Tests aren't set up" → Set them up first
  • "Minor change, doesn't need tests" → It always needs verification
  • "I'll add tests later" → No, add them now

Anti-Patterns

  • Claiming done without running code
  • Running only new tests, not regression suite
  • Ignoring linting warnings
  • Saying "I tested it" without showing output

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/i-onlabs/claude-code-skills/quality-gates/badge)](https://verified-skill.com/skills/i-onlabs/claude-code-skills/quality-gates)

Something wrong with this skill or its page? Tell us.