quality-gates
Skill2 starsChanged 7 months agoMITView on GitHub
Use when a lint, test, or build gate fails during the VERIFY phase and you need the auto-fix procedure, when you need to classify an error and choose a fix strategy, or when WebSearch fallback is needed after repeated gate failures.
27 other projects use a version of this.
Adopted by
Most recently taken up by
- oze-xxbumpxx/cookpittheir own version, first seen Nov 16, 2026
- cormacc/dotagentstheir own version, first seen Nov 8, 2026
- pentoai/quality-gates-skillstheir own version, first seen Nov 8, 2026
- MMACABRE/SKILLStheir own version, first seen Nov 8, 2026
- mxrsv/agents-skillstheir own version, first seen Nov 1, 2026
- NoobyGains/godmodetheir own version, first seen Nov 1, 2026
Used with
Projects with it also use plan.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 3 projects that use this
Other versions27 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 27
- andymai/gridfinity-layout-tool★ 556same name
- typv/nest-turbo-starter★ 224same name
- andymai/brepjs★ 142same name
- NoobyGains/godmode★ 120same name
- cubetribe/ClaudeCode_GodMode-On★ 55same name
- Kanevry/session-orchestrator★ 53same name
- microsoft/github-copilot-modernization★ 48same name
- NikiforovAll/lazyclaude★ 41same name
- sampleXbro/agentsmesh★ 27same name
- mxrsv/agents-skills★ 11same name
17 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- .claude/commands/CLAUDE.mdCLAUDE.md
- .claude/hooks/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/claude-sentient.mdcCursor rule
- profile-detectionSkill
- team-orchestrationSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
18 rules. 0 are common, 14 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 24 edited versions we read keep these.
14
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
When a gate fails, attempt automatic repair (max 3 attempts per gate):
- Very specific: line 39
If profile has fix_command for this gate: run it, re-verify
- Very specific: line 40
If no fix_command or it didn't resolve: read error, apply manual fix, re-verify
- Distinctive: line 42
If error count increases after any attempt: revert changes and stop
- Distinctive: line 43
If all 3 attempts fail: fall through to WebSearch strategy
- Distinctive: line 47
Never modify test assertions or expected values to make tests pass
- Distinctive: line 48
Never skip or disable quality gates
- Distinctive: line 49
If fix introduces new errors, revert immediately
- Distinctive: line 54
When auto-fix exhausts 3 attempts:
- Distinctive: line 58
If solution found: apply fix automatically
- Distinctive: line 59
If still failing after 2 WebSearch attempts: stop and report
- Very specific: line 64
GitHub: Check CI status on PRs (passing/failing/pending)
- Distinctive: line 69
After committing on a branch with a PR:
- Distinctive: line 70
Check if current branch has an open PR
- Distinctive: line 71
If PR exists, monitor CI:
- Very specific: line 80
Default is atomic (single checkpoint commit).
- Distinctive: line 92
Never modify test assertions: When tests fail, fix the source logic, not the expected values.
- Distinctive: line 95
Error count regression: If auto-fix attempt increases the error count, revert immediately.
“Common” is measured: kept by at least 6 in 10 of the 24 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Quality Gates Skill
Reference material for executing quality gates during /cs-loop VERIFY phase.
Gate Execution Order
| Gate | Action | Pass Criteria |
| LINT | Run lint command from profile | Zero errors |
| TEST | Run test command from profile | All tests pass |
| BUILD | Run build command if defined | Clean compilation |
| GIT | Check git status | Clean working state |
Advisory gates (report only, non-blocking): TYPE, DOCS, SECURITY.
Auto-Fix Sub-Loop
When a gate fails, attempt automatic repair (max 3 attempts per gate):
Error Classification
| Error Type | Fix Strategy |
| Lint (auto-fixable) | Run fix_command from profile gates (e.g., ruff check . --fix) |
| Import ordering | Run format/sort command from profile gates |
| Type errors | Read file at error location, fix type annotations |
| Test failures | Read failing test + source under test, fix logic in source |
| Build errors | Read compiler output, fix compilation issues |
Procedure
- Gate fails -> classify error type from output
- If profile has
fix_commandfor this gate: run it, re-verify - If no
fix_commandor it didn't resolve: read error, apply manual fix, re-verify - Maximum 3 attempts per gate. Track:
[VERIFY] Auto-fix attempt {n}/3: {gate} - If error count increases after any attempt: revert changes and stop
- If all 3 attempts fail: fall through to WebSearch strategy
Hard Constraints
- Never modify test assertions or expected values to make tests pass
- Never skip or disable quality gates
- If fix introduces new errors, revert immediately
- Report each attempt:
[VERIFY] Auto-fix attempt {n}/3: {gate} -- {strategy}
WebSearch Fallback
When auto-fix exhausts 3 attempts:
- Extract error message from gate output
- WebSearch("{language} {error_message} fix 2026")
- If solution found: apply fix automatically
- If still failing after 2 WebSearch attempts: stop and report
MCP Integration
- Puppeteer (web projects): Navigate -> screenshot after UI changes
- GitHub: Check CI status on PRs (passing/failing/pending)
- Vision: Capture and analyze error screenshots for UI test failures
CI Monitoring (Post-Commit)
After committing on a branch with a PR:
- Check if current branch has an open PR
- If PR exists, monitor CI:
- Passing ->
[COMMIT] CI passed - Pending ->
[COMMIT] CI running...(continue) - Failing -> Auto-fix if lint/test/type error (max 2 attempts)
- Infrastructure failure -> Report for manual review
- Passing ->
Commit Strategies
See references/commit-strategies.md for per-file and per-task commit strategies.
Default is atomic (single checkpoint commit). Override via --commit-strategy argument or CLAUDE.local.md.
Advisory: Browser Verification (web projects)
Trigger: Web project profile AND Playwright/puppeteer MCP connected
Action: Navigate to dev server, take screenshot, validate against task intent
Blocking: No (advisory only)
Gotcha: Dev server must be running. If not, attempt npm run dev or equivalent in background, wait 5s, then screenshot.
Gotchas
- Never dismiss errors as "pre-existing": Fix ALL lint issues during VERIFY — even if they existed before your changes. If ruff reports it, fix it. This is an Integrity Rule.
- Never modify test assertions: When tests fail, fix the source logic, not the expected values. If tests are genuinely wrong, report to the user rather than "fixing" assertions.
- post-tool-observer null exit_code: Claude Code's PostToolUse may omit
exit_code(yields null). post-tool-observer treats null as inconclusive (passed: null), not failure. Don't log spurious "Gate failed (exit null)" entries. - Large gate output truncation: Stdout > 8000 chars is saved to
.claude/state/gate-output/and replaced with a reference. If you seeoutputRefin gate_history.json instead of raw output, read the referenced file. - Error count regression: If auto-fix attempt increases the error count, revert immediately. Don't try to "fix forward" — the fix introduced new problems.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

