AI Feedback Reporter
npx machina-cli add skill hoangnguyen0403/agent-skills-standard/feedback-reporter --openclawFeedback Reporter
Priority: P0 - Auto-detect skill violations before file writes
šØ 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 ā ā Skip, proceed safely
- YES ā Continue to step 2
- Audit - Does planned code violate loaded skill rules?
- NO ā ā Proceed
- YES ā Run feedback command, then fix
Detection Flow
Before file write?
āā Check file extension ā Identify loaded skills
āā Review skill anti-patterns/rules
āā Code matches anti-pattern?
ā āā YES ā šØ VIOLATION ā feedback command
ā āā NO ā ā
Proceed
āā No skills loaded ā ā
Proceed
Examples (Quick Reference)
Flutter: color: Colors.blue ā Rule: No hardcoded colors ā Report + use theme
React: class MyComponent extends... ā Rule: Use functions ā Report + convert
SKILL.md: 85 lines ā Rule: ā¤70 max ā 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 ā Did I audit skills? NO ā 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
Source
git clone https://github.com/hoangnguyen0403/agent-skills-standard/blob/develop/.github/skills/common/feedback-reporter/SKILL.mdView on GitHub Overview
AI Feedback Reporter automatically audits loaded skills prior to any file write to detect violations and report them via the feedback command. This helps ensure code adheres to skill rules and reduces risky changes. By enforcing a pre-write checkpoint, teams can maintain quality and consistency across projects.
How This Skill Works
Before a file write, the system identifies loaded skills for the target file extension, reviews anti-patterns, and checks if the planned code matches any rule. If a violation is detected, it issues a feedback command to report the issue; otherwise it proceeds with the write. If no skills are loaded, the write proceeds safely.
When to Use It
- Before writing any file to ensure compliance with loaded skills and anti-patterns.
- When you suspect a violation in the planned code change against skill rules.
- During code reviews to auto-flag potential violations before commits.
- When updating or introducing new skills to ensure existing writes comply.
- To enforce consistency and reduce risky edits across teams.
Quick Start
- Step 1: Before writing, verify the target file extension has loaded skills.
- Step 2: If a potential anti-pattern is detected, run the feedback command with the proper placeholders.
- Step 3: Fix the violation, then re-run the file write.
Best Practices
- Ensure the correct skills are loaded for the target file extension before writing.
- Run the pre-write audit for every write, not just on large changes.
- If a violation is detected, use the feedback command to report and document it.
- Keep skill anti-patterns and rules up to date within SKILL.md and references.
- Review reported issues promptly and fix the root causes before re-writing.
Example Use Cases
- Flutter: color: Colors.blue triggers a rule against hardcoded colors; report and switch to theme-based styling.
- React: Using class-based components when functional patterns are preferred; report and refactor to functions.
- SKILL.md: A document with 85 lines violates the ā¤70 max rule; report and extract references.
- No loaded skills for a file extension: write proceeds safely without checks.
- No violations detected: a clean write that passes all loaded skill checks.
