fuxicodex/fuxi/claude-md-improver
- community
Checking that the SKILL.md file is still in the repository.
Audit and improve FUXI.md files in repositories. Use when user asks to check, audit, update, improve, or fix FUXI.md files. Scans for all FUXI.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "FUXI.md maintenance" or "project memory optimization".
Install
npx vskill@latest install fuxicodex/fuxi/claude-md-improverSKILL.md
FUXI.md Improver
Audit, evaluate, and improve FUXI.md files across a codebase to ensure FuXi has optimal project context.
This skill can write to FUXI.md files. After presenting a quality report and getting user approval, it updates FUXI.md files with targeted improvements.
Workflow
Phase 1: Discovery
Find all FUXI.md files in the repository:
File Types & Locations:
| Type | Location | Purpose | |
|---|---|---|---|
| Project root | ./FUXI.md | Primary project context (checked into git, shared with team) | |
| Local overrides | ./.fuxi.local.md | Personal/local settings (gitignored, not shared) | |
| Global defaults | ~/.fuxi/FUXI.md | User-wide defaults across all projects | |
| Package-specific | ./packages/*/FUXI.md | Module-level context in monorepos | |
| Subdirectory | Any nested location | Feature/domain-specific context |
Note: FuXi auto-discovers FUXI.md files in parent directories, making monorepo setups work automatically.
Phase 2: Quality Assessment
For each FUXI.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 FuXi 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:
- A (90-100): Comprehensive, current, actionable
- B (70-89): Good coverage, minor gaps
- C (50-69): Basic info, missing key sections
- D (30-49): Sparse or outdated
- F (0-29): Missing or severely outdated
Phase 3: Quality Report Output
ALWAYS output the quality report BEFORE making any updates.
Format:
Phase 4: Targeted Updates
After outputting the quality report, ask user for confirmation before updating.
Update Guidelines (Critical):
- Propose targeted additions only - Focus on genuinely useful info:
- Commands or workflows discovered during analysis
- Gotchas or non-obvious patterns found in code
- Package relationships that weren't clear
- Testing approaches that work
- Configuration quirks
- Keep it minimal - Avoid:
- Restating what's obvious from the code
- Generic best practices already covered
- One-off fixes unlikely to recur
- Verbose explanations when a one-liner suffices
- Show diffs - For each change, show:
- Which FUXI.md file to update
- The specific addition (as a diff or quoted block)
- Brief explanation of why this helps future sessions
Diff Format:
- ## Quick Start
+
- ```bash
- npm install
- npm run dev # Start development server on port 3000
- ```
Phase 5: Apply Updates
After user approval, apply changes using the Edit tool. Preserve existing content structure.
Templates
See references/templates.md for FUXI.md templates by project type.
Common Issues to Flag
- Stale commands: Build commands that no longer work
- Missing dependencies: Required tools not mentioned
- Outdated architecture: File structure that's changed
- Missing environment setup: Required env vars or config
- Broken test commands: Test scripts that have changed
- Undocumented gotchas: Non-obvious patterns not captured
User Tips to Share
When presenting recommendations, remind users:
- `#` key shortcut: During a FuXi session, press
#to have FuXi auto-incorporate learnings into FUXI.md - Keep it concise: FUXI.md should be human-readable; dense is better than verbose
- Actionable commands: All documented commands should be copy-paste ready
- Use `.fuxi.local.md`: For personal preferences not shared with team (add to
.gitignore) - Global defaults: Put user-wide preferences in
~/.fuxi/FUXI.md
What Makes a Great FUXI.md
Key principles:
- Concise and human-readable
- Actionable commands that can be copy-pasted
- Project-specific patterns, not generic advice
- Non-obvious gotchas and warnings
Recommended sections (use only what's relevant):
- Commands (build, test, dev, lint)
- Architecture (directory structure)
- Key Files (entry points, config)
- Code Style (project conventions)
- Environment (required vars, setup)
- Testing (commands, patterns)
- Gotchas (quirks, common mistakes)
- Workflow (when to do what)
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingfuxi-marketplace/plugins/fuxi-plugins/plugins/fuxi-md-management/skills/claude-md-improver/SKILL.md
Popularity
- Repository stars
- 3,206
- Repository forks
- 220
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/fuxicodex/fuxi/claude-md-improver)