How do I install the Cc Audit skill?

Run npx skillmds@latest add thatmike1/cc-audit in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Cc Audit safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Cc Audit?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Cc Audit free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Cc Audit?

thatmike1 (@thatmike1) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Cc Audit by thatmike1 — Agent Skill

Name: Cc Audit
Author: thatmike1

Cc Audit

Audits Claude Code setup and usage patterns, flagging anti-patterns (wrong launch dirs, context bloat, orphaned memories, missing CLAUDE.md) with severity-ranked fixes. Use when user says audit, health check, setup check, cc audit, or wants to improve their Claude Code workflow.

thatmike1 Updated Sep 21, 2026

File contents

/cc-audit

Analyze Claude Code usage patterns and produce a severity-ranked audit report with actionable fixes.

Workflow

Step 1: Gather data

Run the gathering script from this skill's scripts/ directory:

node <skill-dir>/scripts/gather-audit-data.mjs [--days 30] [--repos-dir ~/git]

--days controls the lookback window for session pattern analysis (default: 30)
--repos-dir points to where git repos live (default: ~/git)
Script outputs structured markdown with session stats, directory analysis, memory org, and CLAUDE.md coverage

Step 2: Synthesize

Read the gathered data and produce an audit report. See references/output-format.md for the template and references/anti-patterns.md for the full catalog.

Key synthesis tasks:

Map raw data to the anti-pattern catalog — match findings to known issues
Assign severity: critical (actively degrading output quality), warning (suboptimal, noticeable impact), suggestion (nice-to-have improvement)
Write a specific fix for each finding — not generic advice, but the exact command or action
Identify the top 2-3 "quick wins" — changes with the best effort-to-impact ratio
If data is thin (few sessions, new install), say so — don't manufacture issues

Step 3: Present

Show the report. Offer to:

Walk through fixing the top issues right now
Generate a CLAUDE.md for repos that are missing one
Help reorganize orphaned memories

Rules

Never read conversation content — this is a metadata-only audit
Be specific: "launch from ~/git/my-project instead of ~" beats "use project directories"
If the setup is actually healthy, say so — don't find problems where there aren't any
Adapt thresholds to the user's volume — 50 sessions/month is different from 5

---name: cc-auditdescription: Audits Claude Code setup and usage patterns, flagging anti-patterns (wrong launch dirs, context bloat, orphaned memories, missing CLAUDE.md) with severity-ranked fixes. Use when user says audit, health check, setup check, cc audit, or wants to improve their Claude Code workflow.---# /cc-auditAnalyze Claude Code usage patterns and produce a severity-ranked audit report with actionable fixes.## Workflow### Step 1: Gather dataRun the gathering script from this skill's `scripts/` directory:```bashnode <skill-dir>/scripts/gather-audit-data.mjs [--days 30] [--repos-dir ~/git]```- `--days` controls the lookback window for session pattern analysis (default: 30)- `--repos-dir` points to where git repos live (default: ~/git)- Script outputs structured markdown with session stats, directory analysis, memory org, and CLAUDE.md coverage### Step 2: SynthesizeRead the gathered data and produce an audit report. See [references/output-format.md](references/output-format.md) for the template and [references/anti-patterns.md](references/anti-patterns.md) for the full catalog.Key synthesis tasks:- Map raw data to the anti-pattern catalog — match findings to known issues- Assign severity: **critical** (actively degrading output quality), **warning** (suboptimal, noticeable impact), **suggestion** (nice-to-have improvement)- Write a specific fix for each finding — not generic advice, but the exact command or action- Identify the top 2-3 "quick wins" — changes with the best effort-to-impact ratio- If data is thin (few sessions, new install), say so — don't manufacture issues### Step 3: PresentShow the report. Offer to:- Walk through fixing the top issues right now- Generate a CLAUDE.md for repos that are missing one- Help reorganize orphaned memories## Rules- Never read conversation content — this is a metadata-only audit- Be specific: "launch from ~/git/my-project instead of ~" beats "use project directories"- If the setup is actually healthy, say so — don't find problems where there aren't any- Adapt thresholds to the user's volume — 50 sessions/month is different from 5

Frequently asked questions