claude-audit
Claude Audit Skill
Analyze all .claude/ configuration files to find optimization opportunities.
Workflow
- Scan files: Find all
.mdfiles in.claude/directory (rules/, commands/, agents/, skills/) - Analyze each file for:
- Redundant instructions: Rules that repeat across multiple files
- Verbose phrasing: Overly wordy explanations that can be concise
- Move to memory candidates: Content rarely needed in context but referenced
- Present findings in a structured format
- Ask user: Which optimizations to implement?
Analysis Criteria
Redundant Instructions
- Same rule mentioned in multiple files
- Overlapping scope between rules and agents/skills
- Duplicate workflow descriptions
Verbose Phrasing
- Long paragraphs that can be shortened
- Redundant examples
- Over-explanation of obvious concepts
Memory Candidates
- Static reference material rarely changing
- Detailed examples not needed in every session
- Background context that can be loaded on-demand
Output Format
# Claude Audit Report
## Files Analyzed
- [file count] files reviewed
## Findings
### Redundant Instructions
| File | Issue | Recommendation |
|------|-------|-----------------|
| file.md | Description | Action |
### Verbose Phrasing
| File | Section | Suggestion |
|------|---------|------------|
| file.md | section | concise version |
### Memory Candidates
| File | Content | Rationale |
|------|---------|-----------|
| file.md | section | why to move |
## Summary
- X redundant rules
- Y verbose sections
- Z candidates for memory
## Action Items
[ ] Implement specific fix
Present findings to the user and ask which to implement
More from jochenyang/jochen-ai-rules
ui-ux-pro-max
UI/UX design-system reasoning and UX quality audit skill. Use when user needs style direction, palette/typography selection, UX review, or design optimization before implementation. Do NOT use for backend logic or database design.
24devops-engineer
CI/CD pipeline design, containerization, and infrastructure management. Handles Docker, Kubernetes, monitoring setup (Prometheus/Grafana), and infrastructure-as-code (Terraform/Pulumi). Use when user asks to deploy, configure CI/CD, set up Docker/K8s, or manage infrastructure.
19handoff
Create and resume structured manual session handoffs for long-running development work. Use when approaching context limits, before manual reset, before switching models or IDEs, after a milestone, or when automatic compact would lose important implementation state.
1reflect
Review current conversation, analyze tasks, errors, and user feedback, extract learning opportunities for skill improvement. Use when user says "reflect", "review session", "what did we learn", "session summary", or after completing a complex task.
1mcp-builder
MCP server development for AI agents. Designs tool schemas, implements Python/TypeScript servers, creates evaluation tests. Use when user asks to build MCP server, create tool integration, or develop Claude plugins. Supports GitHub/Notion/Slack integrations.
1miloya-codebase
Project context engine for repo orientation, cached handoff, and task-focused code retrieval.
1