Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".
.claude/skills/secondsky-claude-md-improver/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 36% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 219% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 86% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 59% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 84% | 0% |
Audit, evaluate, and improve CLAUDE.md files across a codebase to ensure Claude Code has optimal project context.
This skill can write to CLAUDE.md files. After presenting a quality report and getting user approval, it updates CLAUDE.md files with targeted improvements.
Find all CLAUDE.md files in the repository:
bashfind . -name "CLAUDE.md" -o -name ".claude.md" -o -name ".claude.local.md" 2>/dev/null | head -50
File Types & Locations:
| Type | Location | Purpose | |------|----------|---------| | Project root | ./CLAUDE.md | Primary project context (checked into git, shared with team) | | Local overrides | ./.claude.local.md | Personal/local settings (gitignored, not shared) | | Global defaults | ~/.claude/CLAUDE.md | User-wide defaults across all projects | | Package-specific | ./packages/*/CLAUDE.md | Module-level context in monorepos | | Subdirectory | Any nested location | Feature/domain-specific context |
Note: Claude auto-discovers CLAUDE.md files in parent directories, making monorepo setups work automatically.
For each CLAUDE.md file, evaluate against quality criteria. See references/quality-criteria.md for detailed rubrics.
Quick Assessment Checklist:
| Criterion | Weight | Check | |-----------|--------|-------| | Commands/workflows documented | High | Are build/test/deploy commands present? | | Architecture clarity | High | Can Claude understand the codebase structure? | | Non-obvious patterns | Medium | Are gotchas and quirks documented? | | Conciseness | Medium | No verbose explanations or obvious info? | | Currency | High | Does it reflect current codebase state? | | Actionability | High | Are instructions executable, not vague? |
Quality Scores:
ALWAYS output the quality report BEFORE making any updates.
Format:
## CLAUDE.md Quality Report
### Summary
- Files found: X
- Average score: X/100
- Files needing update: X
### File-by-File Assessment
#### 1. ./CLAUDE.md (Project Root)
**Score: XX/100 (Grade: X)**
| Criterion | Score | Notes |
|-----------|-------|-------|
| Commands/workflows | X/20 | ... |
| Architecture clarity | X/20 | ... |
| Non-obvious patterns | X/15 | ... |
| Conciseness | X/15 | ... |
| Currency | X/15 | ... |
| Actionability | X/15 | ... |
**Issues:**
- [List specific problems]
**Recommended additions:**
- [List what should be added]
#### 2. ./packages/api/CLAUDE.md (Package-specific)
...After outputting the quality report, ask user for confirmation before updating.
Update Guidelines (Critical):
Diff Format:
markdown### Update: ./CLAUDE.md **Why:** Build command was missing, causing confusion about how to run the project.
+ ## Quick Start + + bash + npm install + npm run dev # Start development server on port 3000 +
After user approval, apply changes using the Edit tool. Preserve existing content structure.
See references/templates.md for CLAUDE.md templates by project type.
When presenting recommendations, remind users:
# key shortcut: During a Claude session, press # to have Claude auto-incorporate learnings into CLAUDE.md.claude.local.md: For personal preferences not shared with team (add to .gitignore)~/.claude/CLAUDE.mdKey principles:
Recommended sections (use only what's relevant):
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-12 | pass→pass | 11,053 | 5,228 | -53% | 1 | 1 | 0% | 1,692 | 2,377 | +40% | 0 | 0 | — |
case-21 | pass→pass | 12,497 | 7,416 | -41% | 1 | 1 | 0% | 2,434 | 2,913 | +20% | 0 | 0 | — |
case-22 | pass→fail | 3,659 | 2,020 | -45% | 1 | 1 | 0% | 488 | 1,768 | +262% | 0 | 0 | — |
case-01 | fail→fail | 5,493 | 4,873 | -11% | 1 | 1 | 0% | 239 | 1,726 | +622% | 0 | 0 | — |
case-11 | pass→pass | 13,408 | 7,674 | -43% | 1 | 1 | 0% | 2,300 | 2,777 | +21% | 0 | 0 | — |
case-02 | fail→fail | 3,418 | 4,192 | +23% | 1 | 1 | 0% | 301 | 1,902 | +532% | 0 | 0 | — |
case-03 | fail→fail | 2,408 | 5,797 | +141% | 1 | 1 | 0% | 262 | 1,800 | +587% | 0 | 0 | — |
case-04 | fail→pass | 11,697 | 7,516 | -36% | 1 | 1 | 0% | 2,104 | 2,863 | +36% | 0 | 0 | — |
case-05 | fail→pass | 3,477 | 2,069 | -40% | 1 | 1 | 0% | 580 | 1,851 | +219% | 0 | 0 | — |
case-06 | pass→pass | 5,449 | 2,173 | -60% | 1 | 1 | 0% | 901 | 1,758 | +95% | 0 | 0 | — |
case-07 | fail→pass | 6,040 | 3,109 | -49% | 1 | 1 | 0% | 1,089 | 2,024 | +86% | 0 | 0 | — |
case-08 | pass→pass | 10,374 | 4,088 | -61% | 1 | 1 | 0% | 1,674 | 2,251 | +34% | 0 | 0 | — |
case-09 | fail→pass | 12,049 | 8,821 | -27% | 1 | 1 | 0% | 1,901 | 3,016 | +59% | 0 | 0 | — |
case-10 | pass→pass | 14,984 | 14,066 | -6% | 1 | 1 | 0% | 2,556 | 3,949 | +54% | 0 | 0 | — |
case-13 | pass→pass | 7,098 | 7,110 | +0% | 1 | 1 | 0% | 958 | 2,560 | +167% | 0 | 0 | — |
case-14 | pass→pass | 10,744 | 8,419 | -22% | 1 | 1 | 0% | 1,714 | 2,785 | +62% | 0 | 0 | — |
case-15 | fail→pass | 6,231 | 1,746 | -72% | 1 | 1 | 0% | 974 | 1,792 | +84% | 0 | 0 | — |
case-16 | fail→pass | 9,742 | 2,177 | -78% | 1 | 1 | 0% | 1,709 | 1,880 | +10% | 0 | 0 | — |
case-17 | pass→pass | 10,199 | 5,009 | -51% | 1 | 1 | 0% | 1,504 | 2,298 | +53% | 0 | 0 | — |
case-18 | pass→pass | 13,258 | 8,503 | -36% | 1 | 1 | 0% | 2,147 | 2,902 | +35% | 0 | 0 | — |
case-19 | pass→pass | 8,983 | 6,327 | -30% | 1 | 1 | 0% | 1,529 | 2,523 | +65% | 0 | 0 | — |
case-20 | pass→fail | 11,547 | 6,897 | -40% | 1 | 1 | 0% | 2,027 | 1,806 | -11% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 19 counted toward the lift figure. The other 3 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +18 percentage points is the difference between those two pass rates over the 19 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.