Help us improve
Share bugs, ideas, or general feedback.
From claudemd
Use when checking CLAUDE.md files for anti-patterns, staleness, size budget violations, secrets, or orphaned module files
How this skill is triggered — by the user, by Claude, or both
Slash command
/claudemd:auditingThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Analyze ALL context files in the project: root, module-level, and .claude/rules/. Report health issues with severity and actionable fixes.
Share bugs, ideas, or general feedback.
Analyze ALL context files in the project: root, module-level, and .claude/rules/. Report health issues with severity and actionable fixes.
Scan the full hierarchy Claude Code autoloads:
# All CLAUDE.md files (root + module-level)
find . -name 'CLAUDE.md' -not -path '*/node_modules/*' -not -path '*/venv/*' -not -path '*/target/*' -not -path '*/dist/*' 2>/dev/null
# Rules directory
find .claude/rules -name '*.md' -type f 2>/dev/null
# Local file
ls CLAUDE.local.md 2>/dev/null
# Parent directories (monorepo support)
CURRENT="$(pwd)"
while [ "$CURRENT" != "/" ] && [ "$CURRENT" != "$HOME" ]; do
CURRENT="$(dirname "$CURRENT")"
ls "$CURRENT/CLAUDE.md" 2>/dev/null
done
Classify each file:
| Level | Pattern |
|---|---|
| Root | ./CLAUDE.md or ./.claude/CLAUDE.md |
| Module | ./src/billing/CLAUDE.md (subdirectory) |
| Rule | ./.claude/rules/*.md |
| Local | ./CLAUDE.local.md |
## Files Discovered
Level Path Lines Modified
Root ./CLAUDE.md {N} {DATE}
Module src/billing/CLAUDE.md {N} {DATE}
Module src/auth/CLAUDE.md {N} {DATE}
Rule .claude/rules/testing.md {N} {DATE}
Local CLAUDE.local.md {N} {DATE}
If no files found, suggest running /claudemd:init.
Severity indicators:
| Severity | Symbol | Meaning |
|---|---|---|
| Error | ◆◆ | Must fix - actively hurts performance |
| Warning | ◆ | Should fix - wastes context or misleads |
| Info | ◇ | Consider fixing - minor improvement |
Run checks A through G. Read references/audit-checks.md for detailed criteria for each check.
Read references/report-template.md for the full output format.
The report includes: summary counts, health label, per-finding details with actionable fixes, per-file metrics table, context load map, and recommended skill invocations.
Score = 100
- (errors * 15)
- (warnings * 5)
- (info * 1)
- max(0, (max_loaded - 250) / 5)
| Score | Health | Label |
|---|---|---|
| 80-100 | ▓▓▓▓▓ | HEALTHY |
| 50-79 | ▓▓▓░░ | NEEDS_ATTENTION |
| 0-49 | ▓░░░░ | CRITICAL |
npx claudepluginhub jugrajsingh/skillgarden --plugin claudemdFetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Applies a firm's KYC/AML rules grid to parsed onboarding records: assigns risk rating, checks required documents, outputs rule outcomes with citations, and routes for escalation.
Generates daily or weekly digests of activity from connected sources (chat, email, docs, tasks, CRM), highlighting action items, decisions, mentions, and project updates.