audit-friction
Scan Claude Code project logs for friction patterns — repeated failures, approach loops, tool errors, misunderstanding cycles, and stuck workflows. Categorizes and counts friction events to surface what causes the most resistance. Use when user says "audit friction", "find friction", "friction audit", or "what keeps going wrong".
npx skills add majiayu000/claude-skill-registry --skill audit-friction --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Friction Audit Skill Mine Claude Code conversation logs to identify and categorize friction — repeated failures, stuck loops, tool errors, and misunderstanding cycles that cost the most effort. Surfaces patterns causing the most resistance and recommends concrete mitigations. ## When to Use - User says "audit friction", "find friction", "friction audit", or "what keeps going wrong" - User wants to know where workflows repeatedly stall or fail - User wants to identify systemic tooling or workflow issues across sessions ## Arguments The user may provide a "since" date (e.g., `2/7`, `2026-02-07`, `last month`). If not specified, use `AskUserQuestion` to ask what the earliest lookback date should be before proceeding. If the resulting window contains no logs, fall back to the last 30 days and note the adjustment. ## Critical Constraints **NEVER:** - Modify any source code files - Create files outside `temp/audit-friction/` directory - Have subagents write files — they return all findings in response text only - Analyze subagent log subdirectories (`*/subagents/`) — top-level session files only **ALWAYS:** - Use subagents heavily for parallel log analysis - All output goes under `temp
- When to Use
- Arguments
- Critical Constraints
- Friction Categories
- Friction Signal Patterns
- Workflow
- Step 1: Locate Project Logs
- Step 2: Filter by Date and Count
- Step 3: Haiku Batch Scan
- Step 4: Sonnet Deep Analysis per Category
- Step 5: Synthesize Findings
- Step 6: Write Report
- Step 7: Terminal Summary
Tool errors — direct flag
grep -n '"is_error".*true' FILE | head -100
Error keywords in content
Human correction language (look inside "type":"human" lines)
grep -n '"type":"human"' FILE | grep -i 'wrong\|"no,\|try again\|you already\|that.s not\|incorrect\|revert\|undo\|stop' | head -50
Test / build failures
grep -in 'FAILED\|test.*failed\|build.*failed\|compile.*error\|syntax error' FILE | head -100
Consecutive tool call loops — extract tool names in document order, show runs of 2+ back-to-back
grep -o '"name":"[^"]*"' FILE | awk -F'"' '{print $4}' | uniq -c | awk '$1>=2' | head -30
Once you know which tool is looping, get its line numbers to find the range:What does the audit-friction skill do?
Scan Claude Code project logs for friction patterns — repeated failures, approach loops, tool errors, misunderstanding cycles, and stuck workflows. Categorizes and counts friction events to surface what causes the most resistance. Use when user says "audit friction", "find friction", "friction audit", or "what keeps going wrong".
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill audit-friction --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.