plugins/developer-kit-core/skills/memory-md-management/SKILL.md
Provides comprehensive memory file management capabilities including auditing, quality assessment, and targeted improvements for files such as CLAUDE.md. Use when user asks to check, audit, update, improve, fix, maintain, or validate project memory files. Also triggers for "project memory optimization", "CLAUDE.md quality check", "documentation review", or when a project memory file needs to be created from scratch. This skill scans memory files, evaluates quality against standardized criteria, outputs detailed quality reports with scores and recommendations, then makes targeted updates with user approval.
npx skillsauth add giuseppe-trisciuoglio/developer-kit memory-md-managementInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Provides comprehensive project memory file management capabilities including auditing, quality assessment, and targeted improvements. This skill ensures the coding agent has optimal project context by maintaining high-quality documentation files such as CLAUDE.md.
Project memory files such as CLAUDE.md are the primary mechanism for providing project-specific context to coding agent sessions. This skill manages their complete lifecycle: discovery, quality assessment, reporting, and improvement. It follows a 5-phase workflow that ensures documentation is current, actionable, and concise.
The skill evaluates CLAUDE.md files against standardized quality criteria across 6 dimensions: Commands/Workflows, Architecture Clarity, Non-Obvious Patterns, Conciseness, Currency, and Actionability. Each file receives a score (0-100) and letter grade (A-F) with specific improvement recommendations.
Use this skill when:
# during a session to incorporate learnings into a memory fileTrigger phrases: "audit CLAUDE.md", "check documentation quality", "improve project context", "review CLAUDE.md", "validate documentation"
Find all CLAUDE.md files in the repository:
find . -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 |
For each CLAUDE.md file, read references/quality-criteria.md and evaluate against these criteria:
| Criterion | Weight | What to Check | |-----------|--------|---------------| | Commands/workflows | 20 pts | Are build/test/deploy commands present and working? | | Architecture clarity | 20 pts | Can Claude understand the codebase structure? | | Non-obvious patterns | 15 pts | Are gotchas and quirks documented? | | Conciseness | 15 pts | Is content dense without filler? | | Currency | 15 pts | Does it reflect current codebase state? | | Actionability | 15 pts | Are instructions executable and copy-paste ready? |
Quality Scores: A (90-100), B (70-89), C (50-69), D (30-49), F (0-29)
CRITICAL: 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]
After report output, ask user for confirmation before updating.
Read references/update-guidelines.md for detailed update principles.
Key principles:
Diff format:
### Update: ./CLAUDE.md
**Why:** [Brief explanation of why this helps]
```diff
+ ## Quick Start
+
+ ```bash
+ npm install
+ npm run dev
+ ```
### Phase 5: Apply Updates
After user approval, use Edit tool to apply changes. Preserve existing content structure.
## Examples
### Example 1: Quality Assessment
**User request:** "Check if my CLAUDE.md is good"
**Response:**
~~~markdown
## CLAUDE.md Quality Report
### Summary
- Files found: 1
- Average score: 65/100
- Files needing update: 1
### File-by-File Assessment
#### 1. ./CLAUDE.md
**Score: 65/100 (Grade: C)**
| Criterion | Score | Notes |
|-----------|-------|-------|
| Commands/workflows | 10/20 | Only npm install documented |
| Architecture clarity | 15/20 | Basic tree, missing module relationships |
| Non-obvious patterns | 5/15 | No gotchas documented |
| Conciseness | 15/15 | Concise and dense |
| Currency | 10/15 | Some outdated paths |
| Actionability | 10/15 | Some vague instructions |
**Issues:**
- Missing test command
- Missing build command
- No documentation of auth flow complexity
- References to old src/structure
**Recommended additions:**
- Add Commands section with test/build
- Document auth module gotcha
- Update architecture paths
User request: "Create a CLAUDE.md for this React project"
Response:
I'll create a CLAUDE.md for your React project. Let me first analyze the codebase structure.
[Scans package.json, src/, and key config files]
## CLAUDE.md Quality Report
### Summary
- Files found: 0
- Creating new CLAUDE.md at project root
### Proposed CLAUDE.md Content:
# Project Name
## Commands
| Command | Description |
|---------|-------------|
| `npm install` | Install dependencies |
| `npm run dev` | Start dev server (Vite on port 5173) |
| `npm run build` | Production build |
| `npm run test` | Run Vitest tests |
| `npm run lint` | ESLint check |
## Architecture
src/ ├── components/ # Reusable UI components ├── pages/ # Route pages ├── hooks/ # Custom React hooks ├── lib/ # Utilities and API clients └── main.tsx # Entry point
## Gotchas
- Vite requires files in `public/` for static assets
- State updates in `useEffect` need proper dependency arrays
Shall I create this file?
### Example 3: Update Proposal
**User request:** "Update my CLAUDE.md with what you learned"
**Response:**
```markdown
### Update: ./CLAUDE.md
**Why:** Discovered that tests require database setup which wasn't documented.
```diff
## Testing
+ **Prerequisites:** Start test database first with `docker-compose up -d test-db`
+ `npm run test` - Run all tests
+ `npm run test:unit` - Unit tests only (no DB required)
Also found issue with API_BASE_URL:
## Environment
- `API_BASE_URL` - API endpoint (default: localhost:3000)
+ `API_BASE_URL` - API endpoint (required for production, defaults to http://localhost:3000 in dev)
Apply these changes?
## Best Practices
1. **Always read references before acting**: Quality criteria, templates, and update guidelines contain essential details
2. **Report before editing**: Never modify CLAUDE.md without first presenting a quality report
3. **Preserve existing structure**: When updating, maintain the existing organization and style
4. **Be project-specific**: Only add information specific to this codebase, not generic advice
5. **Verify commands work**: Before suggesting commands, mentally or actually verify they execute correctly
6. **Use progressive disclosure**: Keep SKILL.md lean, reference detailed rubrics in separate files
7. **Score consistently**: Apply the same scoring standards across all files for fair comparison
## Constraints and Warnings
1. **Never modify without approval**: Always get user confirmation before editing CLAUDE.md files
2. **Don't remove content without asking**: If suggesting deletions, explicitly mark them and get approval
3. **Respect `.claude.local.md`**: These are personal settings; never suggest modifying them in shared docs
4. **Avoid generic advice**: Do not add "write good code" type content - focus on project-specific patterns
5. **Keep diffs concise**: Show only the actual changes, not entire file contents
6. **Verify file paths**: Ensure all referenced files exist before documenting them
7. **Score objectively**: Use the rubric consistently; don't inflate scores for incomplete documentation
development
Provides security review capability for TypeScript/Node.js applications, validates code against XSS, injection, CSRF, JWT/OAuth2 flaws, dependency CVEs, and secrets exposure. Use when performing security audits, before deployment, reviewing authentication/authorization implementations, or ensuring OWASP compliance for Express, NestJS, and Next.js. Triggers on "security review", "check for security issues", "TypeScript security audit".
development
Provides final code cleanup after task review approval. Removes debug logs, temporary comments, dead code, optimizes imports, and improves readability. Use when asked to clean up code, polish, finalize, tidy up, remove technical debt, or prepare code for completion after review. Not for refactoring logic or fixing bugs—focused solely on cosmetic and hygiene cleanup.
tools
Ralph Wiggum-inspired automation loop for specification-driven development. Orchestrates task implementation, review, cleanup, and synchronization using a Python script. Use when: user runs /loop command, user asks to automate task implementation, user wants to iterate through spec tasks step-by-step, or user wants to run development workflow automation with context window management. One step per invocation. State machine: init → choose_task → implementation → review → fix → cleanup → sync → update_done. Supports --from-task and --to-task for task range filtering. State persisted in fix_plan.json.
testing
Creates, updates, validates, and displays the architectural DNA of a project through two shared documents: docs/specs/architecture.md (technology stack, architectural rules, security constraints, AI guardrails) and docs/specs/ontology.md (domain glossary / Ubiquitous Language). Use BEFORE brainstorm as a project setup step, or at any point in the SDD lifecycle to validate specs/tasks against architecture principles. Triggers on 'create constitution', 'update constitution', 'constitution check', 'validate against constitution', 'project principles', 'architectural guardrails', 'setup project architecture', 'define ontology'.