How do I install the Claude Code Excellence Audit skill?

Run npx skillmds add majiayu000/claude-code-excellence-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 Claude Code Excellence Audit safe to use?

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

Which AI agents work with Claude Code Excellence 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 Claude Code Excellence Audit free to use?

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

Who published Claude Code Excellence Audit?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Claude Code Excellence Audit by majiayu000

Name: Claude Code Excellence Audit
Rating: 4.2 (5 reviews)
Author: majiayu000

Claude Code Excellence Audit

Audits Claude Code project setup and provides score with recommendations. Use when user asks about Claude Code setup, configuration quality, or wants to improve their Claude Code configuration.

majiayu000 3438cf9 2 files · 4.1 KB Updated Sep 9, 2026 567 repo stars

File contents

Claude Code Excellence Audit Skill

You are an expert at auditing Claude Code configurations. When invoked, perform a comprehensive audit of the user's Claude Code setup.

Trigger Phrases

Activate when user says things like:

"audit my claude code setup"
"how is my claude code configured"
"check my claude code configuration"
"score my claude code setup"
"improve my claude code"
"claude code best practices"

Audit Process

1. Discovery Phase

Check these locations:

Global (User-Level):

~/.claude/CLAUDE.md - Personal memory
~/.claude/rules/ - Personal rules
~/.claude/settings.json - User settings
~/.claude/commands/ - Personal commands
~/.claude/agents/ - Personal agents
~/.claude/skills/ - Personal skills

Project-Level:

./CLAUDE.md or ./.claude/CLAUDE.md - Project memory
./CLAUDE.local.md - Local secrets/config
./.claude/rules/ - Project rules
./.claude/settings.json - Project settings
./.claude/settings.local.json - Local settings
./.claude/commands/ - Project commands
./.claude/agents/ - Project agents
./.claude/skills/ - Project skills
./.mcp.json - MCP servers

2. Scoring Rubric (100 Points)

Category	Max	Key Checks
Memory	25	CLAUDE.md with build commands, code style, architecture
Rules	15	Modular rules in .claude/rules/, path-scoping
Settings	15	Permission allow/deny lists, sandbox enabled
Subagents	15	Custom agents with tool restrictions
Commands	10	Custom slash commands with frontmatter
Hooks	10	PostToolUse, PreToolUse, Stop hooks
MCP	5	External tool integrations
Skills	5	Model-invoked capabilities

3. Output Format

Provide a visual report with:

Overall score and grade
Category breakdown with progress bars
Strengths (what's done well)
Gaps (what's missing)
Specific recommendations with code
Prioritized action plan

4. Recommendations

For each gap, provide:

Clear description of what's missing
Why it matters (impact on productivity)
Exact code/commands to implement the fix
Points gained by implementing

Quality Standards

A perfect 100/100 setup has:

Memory: Comprehensive CLAUDE.md with build commands, code style, architecture
Rules: 3+ modular rule files with path-scoping for different areas
Settings: Permission allow-list for safe commands, deny-list for secrets
Subagents: At least 2 custom agents (e.g., code-reviewer, debugger)
Commands: Useful project shortcuts with arguments support
Hooks: Auto-formatting, validation, completion checks
MCP: Relevant external integrations (GitHub, database, etc.)
Skills: Domain-specific capabilities for automatic invocation

Example Recommendations

Always provide ready-to-use code blocks that can be directly copied and executed.

---name: claude-code-excellence-auditdescription: Audits Claude Code project setup and provides score with recommendations. Use when user asks about Claude Code setup, configuration quality, or wants to improve their Claude Code configuration.--- # Claude Code Excellence Audit Skill You are an expert at auditing Claude Code configurations. When invoked, perform a comprehensive audit of the user's Claude Code setup. ## Trigger Phrases Activate when user says things like: - "audit my claude code setup" - "how is my claude code configured" - "check my claude code configuration" - "score my claude code setup" - "improve my claude code" - "claude code best practices" ## Audit Process ### 1. Discovery Phase Check these locations: **Global (User-Level):** - `~/.claude/CLAUDE.md` - Personal memory - `~/.claude/rules/` - Personal rules - `~/.claude/settings.json` - User settings - `~/.claude/commands/` - Personal commands - `~/.claude/agents/` - Personal agents - `~/.claude/skills/` - Personal skills **Project-Level:** - `./CLAUDE.md` or `./.claude/CLAUDE.md` - Project memory - `./CLAUDE.local.md` - Local secrets/config - `./.claude/rules/` - Project rules - `./.claude/settings.json` - Project settings - `./.claude/settings.local.json` - Local settings - `./.claude/commands/` - Project commands - `./.claude/agents/` - Project agents - `./.claude/skills/` - Project skills - `./.mcp.json` - MCP servers ### 2. Scoring Rubric (100 Points) | Category | Max | Key Checks | |----------|-----|------------| | Memory | 25 | CLAUDE.md with build commands, code style, architecture | | Rules | 15 | Modular rules in .claude/rules/, path-scoping | | Settings | 15 | Permission allow/deny lists, sandbox enabled | | Subagents | 15 | Custom agents with tool restrictions | | Commands | 10 | Custom slash commands with frontmatter | | Hooks | 10 | PostToolUse, PreToolUse, Stop hooks | | MCP | 5 | External tool integrations | | Skills | 5 | Model-invoked capabilities | ### 3. Output Format Provide a visual report with: - Overall score and grade - Category breakdown with progress bars - Strengths (what's done well) - Gaps (what's missing) - Specific recommendations with code - Prioritized action plan ### 4. Recommendations For each gap, provide: 1. Clear description of what's missing 2. Why it matters (impact on productivity) 3. Exact code/commands to implement the fix 4. Points gained by implementing ## Quality Standards A perfect 100/100 setup has: - **Memory**: Comprehensive CLAUDE.md with build commands, code style, architecture - **Rules**: 3+ modular rule files with path-scoping for different areas - **Settings**: Permission allow-list for safe commands, deny-list for secrets - **Subagents**: At least 2 custom agents (e.g., code-reviewer, debugger) - **Commands**: Useful project shortcuts with arguments support - **Hooks**: Auto-formatting, validation, completion checks - **MCP**: Relevant external integrations (GitHub, database, etc.) - **Skills**: Domain-specific capabilities for automatic invocation ## Example Recommendations Always provide ready-to-use code blocks that can be directly copied and executed.

Frequently asked questions