auto-fix
Skill2 starsChanged 8 months agoMITView on GitHub
Auto-fix simple issues found by SQWR audit agents — console.log, unused imports, missing ARIA attributes, TODO format.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- onegunsamurai/OpenLearningtheir own version, first seen Nov 8, 2026
- sonusz/skills-pubtheir own version, first seen Sep 18, 2026
- IvanSkainet/arena-agenttheir own version, first seen Aug 13, 2026
- jeff-yiii/claude-code-reviewtheir own version, first seen May 12, 2026
- tae0y/python-project-templatetheir own version, first seen Mar 7, 2026
- PingPingE/ai-content-agentstheir own version, first seen Feb 18, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- tae0y/python-project-template★ 14same name
- IvanSkainet/arena-agent★ 8same name
- sonusz/skills-pub★ 8same name
- PingPingE/ai-content-agents★ 2same name
- jeff-yiii/claude-code-review★ 1same name
- onegunsamurai/OpenLearning★ 1same name
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 repository11 other files it gives its agents.
- global/CLAUDE.mdCLAUDE.md
- templates/CLAUDE.mdCLAUDE.md
- audit-runnerSkill
- brainstormSkill
- compliance-checkSkill
- contract-lookupSkill
- monthly-reviewSkill
- new-featureSkill
- pre-deploymentSkill
- project-setupSkill
- risk-scoreSkill
The file
Files
/auto-fix — Auto-Fix Audit Issues
Usage: /auto-fix [domain]
Reads audit findings and automatically applies fixes that are unambiguous, low-risk, and reversible.
Examples:
/auto-fix quality→ removes console.log, fixes TODO format/auto-fix accessibility→ adds missing alt text, aria-label on buttons/auto-fix all→ all safe auto-fixes across domains
Safe auto-fix scope
This skill ONLY fixes issues that are:
- Unambiguous — one correct fix exists (e.g. remove
console.log) - Low-risk — fix cannot break functionality
- Reversible — undoable via
git diff/git checkout
NEVER auto-fix:
- Security architecture changes (require human review)
- Performance refactoring
- Accessibility issues requiring content decisions
- Any touch to auth, payments, or data handling logic
Phase 1 — Scan for fixable issues
echo "=== QUALITY SCAN ==="
# console.log in production code (excluding tests)
grep -rn "console\.log\|console\.debug\|console\.info" src/ --include="*.ts" --include="*.tsx" | grep -v "test\|spec\|\.d\.ts" | head -30
echo "=== ACCESSIBILITY SCAN ==="
# Images without alt text
grep -rn "<img " src/ --include="*.tsx" --include="*.jsx" | grep -v 'alt=' | head -20
# Buttons without accessible name
grep -rn "<button" src/ --include="*.tsx" | grep -v "aria-label\|aria-labelledby\|>.*</button>" | head -20
echo "=== TODO FORMAT SCAN ==="
# TODOs without ticket reference
grep -rn "TODO[^(#]" src/ --include="*.ts" --include="*.tsx" | head -20Observable truth: Scan completes, list of fixable issues produced.
Phase 2 — Apply fixes
For each issue found, apply the appropriate fix:
console.log → remove the line. Skip if // eslint-disable comment present.
Images without alt → add alt="" for decorative images. For informational images, infer alt text from filename/context, flag for review if unclear.
TODO without ticket → change TODO something to TODO(#?) something and add a comment // Add ticket number.
After each fix:
npm run build 2>&1 | tail -5Observable truth: Build passes after each fix applied.
Phase 3 — Final verification
npm run build && npm test -- --passWithNoTestsObservable truth: Full build and test suite passes.
Post-fix report
AUTO-FIX REPORT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Fixed : X issues
Skipped: Y issues (require human review)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
FIXED:
✅ Removed console.log — src/lib/api.ts:42
✅ Added alt="" — src/components/Logo.tsx:8
[...]
REQUIRES HUMAN REVIEW:
⚠️ src/auth/middleware.ts:89 — Security pattern
[...]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━Reference
Contracts enforced: contracts/CONTRACT-TYPESCRIPT.md, contracts/CONTRACT-ACCESSIBILITY.md, contracts/CONTRACT-TESTING.md
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.

