CO

common-feedback-reporter

Automated audit tool to prevent skill violations before code commits.

Install

mkdir -p .claude/skills/common-feedback-reporter && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14803" && unzip -o skill.zip -d .claude/skills/common-feedback-reporter && rm skill.zip

Installs to .claude/skills/common-feedback-reporter

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Pre-write audit for skill violations. Checks planned code against loaded skill anti-patterns before any file write. Use when writing Flutter/Dart code, editing SKILL.md files, or generating any code where project skills are active. Load as composite alongside other skills. When a violation is detected and Auto-fixed: YES, also load +common/common-learning-log to record the mistake.
384 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • Audit planned code for skill rule violations
  • Detect oversized SKILL.md drafts
  • Identify outdated framework paths or APIs
  • Report root cause, user intent, and skill gap for violations
  • Apply automatic fixes for detected violations

How it works

Before any file write, the skill audits the planned code against loaded skill rules and outputs a structured violation report if a rule is broken, then applies an automatic fix.

Inputs & outputs

You give it
Planned code or SKILL.md content
You get back
A violation block with fix, or silently proceeds if no violation

When to use common-feedback-reporter

  • Audit code before commit
  • Check SKILL.md for rule violations
  • Ensure adherence to project standards

About this skill

Feedback Reporter

Priority: P0 (CRITICAL) — Auto-detect skill violations before file writes.

Mandatory execution contract

For any request that writes code or edits SKILL.md, treat the requested change as a planned write. Before showing code, run this audit and emit the complete violation block when a loaded skill rule is violated. The block must include these exact labels: SKILL VIOLATION DETECTED, Auto-fixed, Root Cause, User Intent, and Skill Gap. Then apply the fix and show the corrected result. Do not silently produce the violating implementation, and do not replace the required block with a summary.

Apply the same contract to these cases:

  • If a draft SKILL.md exceeds the 100-line limit, report the 100-line violation, move large examples to references/, and include Root Cause, User Intent, and Skill Gap before rewriting it.
  • If a skill recommends an obsolete framework path or API, report OUTDATED_GUIDANCE and include User Intent and Skill Gap before giving the current replacement.

For the oversized-draft case, include this exact sentence pattern before the rewrite: SKILL.md is 100+ lines; extract large examples to references/. Root Cause: ... User Intent: ... Skill Gap: ....

🚨 Checkpoint: Before File Writes

Quick check before write_to_file, replace_file_content, multi_replace_file_content:

  1. Check - Any skills loaded for this file extension?
  • NO → ✅ Proceed silently
  • YES → Continue to step 2
  1. Audit - planned code violate loaded skill rules?
  • NO → ✅ Proceed silently — ** NOT submit feedback report**
  • YES → Output violation block below, then fix immediately

Violation Report Format

When violation detected, output this block before fixing:

🚨 SKILL VIOLATION DETECTED
Skill:        [skill-id]
File:         [relative/path/to/file.ext]:[line-range]
Rule:         [exact rule text from SKILL.md]
Violation:    [what planned code does — up to 5-line offending snippet]
Fix:          [corrected approach — up to 5-line corrected snippet]
Auto-fixed:   YES / NO
Root Cause:   [AMBIGUOUS_RULE | MISSING_COVERAGE | OUTDATED_GUIDANCE | COMPETING_RULES | PATTERN_MISMATCH]
User Intent:  [1 sentence: what the user was trying to achieve]
Skill Gap:    [1–2 sentences: what change to the SKILL.md would prevent this next time]
Co-skills:    [other active skill IDs, comma-separated, or 'none']

Root Cause Guide

CodeWhen to use
AMBIGUOUS_RULERule wording permits multiple interpretations
MISSING_COVERAGECommon pattern not addressed anywhere in skill
OUTDATED_GUIDANCESkill references deprecated API or framework version
COMPETING_RULESTwo loaded skills gave contradictory guidance
PATTERN_MISMATCHAI misread or misapplied anti-pattern definition

Then apply fix immediately — not wait for user confirmation.

Pre-Completion Check

Before notify_user or task completion:

** I write code?** YES → ** I audit skills?** NO → 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
  • No "clean-pass report": If no violation found, proceed silently — NOT submit report
  • No "shallow report": Always populate Root Cause, User Intent, and Skill Gap — these drive improvement

Use report labels SKILL VIOLATION DETECTED, Auto-fixed, Root Cause, User Intent, and Skill Gap; move oversized examples to references/.

When not to use it

  • No skills are loaded for the file extension
  • No violation is detected in the planned code
  • The user wants to skip the audit for minor changes

Limitations

  • Does not submit a feedback report if no violation is found
  • Does not proceed without a fix for detected violations
  • Does not allow skipping checks for minor changes

How it compares

This skill proactively checks for rule violations and applies fixes before code is written, preventing non-compliant code from being generated, unlike a manual review after the fact.

Compared to similar skills

common-feedback-reporter side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
common-feedback-reporter (this skill)01moNo flagsIntermediate
dependency-upgrade265moReviewIntermediate
validate-typescript59moReviewBeginner
ts-testing68moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry