claude-md-auditor

Included with Lifetime

$97 forever

Audit CLAUDE.md files for redundancy, verbosity, and adherence to best practices. This skill should be used when reviewing, improving, or cleaning up CLAUDE.md files to ensure they remain effective and concise.

Security

What this skill does

# CLAUDE.md Auditor

Audit and improve CLAUDE.md files based on Claude Code Best Practices.

## Audit Process

### Step 1: Read the Target CLAUDE.md

Read the CLAUDE.md file specified by $ARGUMENTS. If no path is provided, look for CLAUDE.md in the current working directory.

### Step 2: Load Best Practices Reference

Read `references/best-practices.md` to understand the evaluation criteria.

### Step 3: Analyze Each Section

For each section in CLAUDE.md, evaluate:

1. **Necessity**: Would removing this cause Claude to make mistakes?
2. **Redundancy**: Can Claude infer this from the codebase?
3. **Accuracy**: Is this still accurate and relevant?
4. **Specificity**: Is this actionable or too vague?
5. **Length**: Is this concise or overly verbose?

### Step 4: Generate Audit Report

Output a structured report in this format:

```markdown
# CLAUDE.md Audit Report

## Summary
- Total lines: X
- Lines to remove: Y
- Lines to improve: Z
- Health score: X/10

## Issues Found

### Redundant Content
[List items that Claude can infer from code]

### Overly Verbose
[List sections that should be condensed]

### Stale/Outdated
[List references to old patterns or removed features]

### Vague Instructions
[List non-actionable guidance]

### Missing Information
[List recommended additions based on codebase analysis]

## Recommended Changes

### Remove
[Specific lines/sections to delete]

### Condense
[Suggestions for making sections more concise]

### Add
[Recommended additions with rationale]
```

### Step 5: Offer to Apply Changes

After presenting the report, ask the user if they want to apply the recommended changes automatically.

## Quality Targets

- **Ideal length**: 50-200 lines
- **Maximum length**: 500 lines (beyond this, Claude may ignore instructions)
- **Focus**: Actionable, specific, non-obvious information only

Files: 2

Size: 3.9 KB

Complexity: 22/100

Category: Security

Source: https://github.com/xmgrex/ccx-arsenal/tree/main/plugins/claude-md-auditor/skills/audit

Related in Security

mac-ops

Included

Comprehensive macOS workstation operations — diagnose kernel panics, identify failing drives, audit launchd startup items, decode wake reasons, triage TCC permission denials, manage APFS snapshots, recover from no-boot. Use for: Mac is slow, slow bootup, won't boot, kernel panic, kernel_task hot, mds_stores CPU, photoanalysisd, cloudd, login loop, gray screen, sleep wake failure, drive failing, IO errors, APFS snapshots eating space, Time Machine local snapshots, Spotlight indexing, launchd, LaunchAgent, LaunchDaemon, login items, TCC permissions, Full Disk Access, Screen Recording denied, Gatekeeper, quarantine, com.apple.quarantine, app is damaged, helper tool, /Library/PrivilegedHelperTools, pmset, wake reasons, dark wake, sysdiagnose, panic.ips, DiagnosticReports, configuration profile, MDM profile, remote diagnostics over SSH.

Securityscripts

a11y-audit

Included

Run accessibility audits on web projects combining automated scanning (axe-core, Lighthouse) with WCAG 2.1 AA compliance mapping, manual check guidance, and structured reporting. Output is configurable: markdown report only, markdown plus machine-readable JSON, or markdown plus issue tracker integration. Use this skill whenever the user mentions "accessibility audit", "a11y audit", "WCAG audit", "accessibility check", "compliance scan", or asks to check a web project for accessibility issues. Also trigger when the user wants to verify WCAG conformance or map findings to a specific standard (CAN-ASC-6.2, EN 301 549, ADA/AODA).

Securityscripts

erpclaw

Included

AI-native ERP system with self-extending OS. Full accounting, invoicing, inventory, purchasing, tax, billing, HR, payroll, advanced accounting (ASC 606/842, intercompany, consolidation), and financial reporting. 413 actions across 14 domains, 43 expansion modules. Constitutional guardrails, adversarial audit, schema migration. Double-entry GL, immutable audit trail, US GAAP.

Securityscripts

assess

Included

Assesses and rates quality 0-10 across multiple dimensions (correctness, maintainability, security, performance, testability, simplicity) with pros/cons analysis. Compares against project conventions and prior decisions from memory. Produces structured evaluation reports with actionable improvement suggestions. Use when evaluating code, designs, architectures, or comparing alternative approaches.

Securityscripts

spring-boot-security-jwt

Included

Provides JWT authentication and authorization patterns for Spring Boot 3.5.x covering token generation with JJWT, Bearer/cookie authentication, database/OAuth2 integration, and RBAC/permission-based access control using Spring Security 6.x. Use when implementing authentication or authorization in Spring Boot applications.

Securityscripts

code-hardcode-audit

Included

Detect hardcoded values, magic numbers, and leaked secrets. TRIGGERS - hardcode audit, magic numbers, PLR2004, secret scanning.

Securityscripts

Detect hardcoded values, magic numbers, and leaked secrets. TRIGGERS - hardcode audit, magic numbers, PLR2004, secret scanning.

Securityscripts