CRITICAL - Before ANY file write, audit loaded skills for violations. Auto-report via feedback command.
Resources
1Install
npx skillscat add hoangnguyen0403/agent-skills-standard/ai-feedback-reporter Install via the SkillsCat registry.
SKILL.md
Feedback Reporter
Priority: P0 - Auto-detect skill violations before file writes
๐จ Checkpoint: Before File Writes
Quick check before write_to_file, replace_file_content, multi_replace_file_content:
- Check - Any skills loaded for this file extension?
- NO โ โ Skip, proceed safely
- YES โ Continue to step 2
- Audit - Does planned code violate loaded skill rules?
- NO โ โ Proceed
- YES โ Run feedback command, then fix
Detection Flow
Before file write?
โโ Check file extension โ Identify loaded skills
โโ Review skill anti-patterns/rules
โโ Code matches anti-pattern?
โ โโ YES โ ๐จ VIOLATION โ feedback command
โ โโ NO โ โ
Proceed
โโ No skills loaded โ โ
ProceedExamples (Quick Reference)
Flutter: color: Colors.blue โ Rule: No hardcoded colors โ Report + use theme
React: class MyComponent extends... โ Rule: Use functions โ Report + convert
SKILL.md: 85 lines โ Rule: โค70 max โ Report + extract to references/
Command (Copy-Paste)
npx agent-skills-standard feedback \
--skill="[skill-id]" \
--issue="[violation]" \
--skill-instruction="[exact rule]" \
--actual-action="[what I did]"Pre-Completion Check
Before notify_user or task completion:
Did I write code? YES โ Did I audit skills? NO โ Audit now
Anti-Patterns
- No "I'll check later": Check before writing, not after
- No "minor change skip": Every write needs check
- No "user waiting skip": 10-second check > pattern violation