Evaluate GitHub issues against the repository's code of conduct. Use when: (1) A new issue is created and needs conduct review, (2) Part of issue intake pipeline, (3) Evaluating whether issue content violates community guidelines. If violations are found, sanitizes offending content (including title, body, and comments) while preserving technical substance and notifies the author. Intelligently replaces titles when sanitization renders them meaningless.
72
71%
Does it follow best practices?
Impact
60%
1.07xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/code-of-conduct-check/SKILL.mdBody violation with technical content preservation
Violation detected
100%
100%
Exact placeholder used
0%
0%
Technical content preserved
100%
100%
Title unmodified
100%
100%
gh issue edit command
100%
100%
gh issue comment command
100%
100%
Exact notice text
0%
0%
No extra notice content
0%
0%
Sanitized body in report
100%
100%
Summary section present
50%
40%
Meaningless title replacement from body
Title violation identified
100%
100%
Meaningless-after-sanitize check
0%
10%
New title generated from body
100%
100%
New title conciseness
0%
0%
gh issue edit for title
100%
100%
gh issue comment for notice
100%
100%
Exact notice text
0%
0%
Body status PASS
50%
100%
Title status REPLACED
0%
20%
Summary comment count
0%
33%
Notice same for title violations
50%
66%
Comment violation with reply-based notification
All comments reviewed
100%
100%
Correct comment flagged
100%
100%
Exact placeholder in comment
0%
0%
Technical workaround preserved
100%
100%
PATCH API for comment update
85%
100%
Reply to comment for notice
0%
0%
Exact notice text in reply
0%
0%
Title and body PASS
100%
100%
Summary comment counts
100%
100%
Sanitized comment in report
100%
100%
6b797b3
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.