cursor-doctor
Cursor rules linter and auto-fixer. Find out why Cursor ignores your rules. 100+ checks, zero dependencies.
Install / Use
npx skills add nedcodes-ok/cursor-doctorInstalls into whichever agent you are using.
.cursorrules
Cursor IDE rules (legacy)
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of cursor-doctor
cursor-doctor scores 75/100 on our quality scale, 3712th of 4,617 Development & Engineering skills we index.
Its .cursorrules is 7.4 KB long, well organised into 19 sections with 10 code examples: a thorough specification that gives an agent plenty to work with.
It has 10 GitHub stars, so there is little community track record yet; judge it on its content.
Maintenance, license and trust
- The repository was last updated about 8 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
- Our last check on 2026-09-27 found the source still online.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 91/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
cursor-doctor compared with similar skills
All 4 of these similar skills score higher than cursor-doctor; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| cursor-doctor (this skill)by nedcodes-ok | 75 | 10 | 8mo ago | .cursorrules |
| taste-skillby Leonxlnx | 100 | 110.6k | today | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 69.8k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 46.6k | 2d ago | CLAUDE.md |
| algorithmic-artby anthropics | 100 | 177.9k | 44d ago | SKILL.md |
Frequently asked questions
- How do I install cursor-doctor?
- Run
npx skills add nedcodes-ok/cursor-doctor. The install tabs above show the steps for each supported agent. - Which AI agents does cursor-doctor work with?
- It is written for Cursor, as a .cursorrules file. Other agents that read the same format can often use it too.
- Is cursor-doctor safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 91/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is cursor-doctor still maintained?
- The repository was last updated about 8 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
Skill content
View source on GitHubcursor-doctor
Your Cursor rules have bugs. This finds them.
You wrote rules. Cursor still ignores them. cursor-doctor tells you exactly what's wrong: conflicting directives, broken globs, vague instructions the AI can't act on, token budget waste, and 100+ other issues. One command. Zero dependencies.
npx cursor-doctor scan

🔧 Auto-fix everything:
npx cursor-doctor fix— first 3 fixes free, Pro for all
What you get
▒▒ Cursor Health: B ▒▒
██████████████████████████░░░░ 84%
✗ Conflict: "always use semicolons" vs "omit semicolons" in 2 files
✗ Glob *.tsx doesn't match any files in your project
⚠ 3 rules use alwaysApply — burning 2,400 tokens on every request
⚠ "write clean code" is too vague for the AI to act on
✓ Frontmatter valid across 12 rules
✓ No legacy .cursorrules detected
8 passed 4 issues (2 auto-fixable)
Not generic warnings. Issues specific to your rules, with the exact file and line.
Why this exists
We scanned 50 real open-source projects and found that 82% had at least one broken or misconfigured rule. The most common issues: contradictory instructions across files, glob patterns that match nothing, and vague rules the AI silently ignores.
Commands
| Command | What it does | Free? |
|---------|-------------|-------|
| npx cursor-doctor scan | Health check with letter grade | ✅ |
| npx cursor-doctor lint | Rule-by-rule detailed diagnostics | ✅ |
| npx cursor-doctor check | CI pass/fail (exit code 0 or 1) | ✅ |
| npx cursor-doctor badge | Generate README badge snippets | ✅ |
| npx cursor-doctor init | Generate starter rules for your stack | ✅ |
| npx cursor-doctor install react | Install community rule packs | ✅ |
| npx cursor-doctor fix --preview | Preview auto-fixes before applying | ✅ |
| npx cursor-doctor fix | Apply all auto-fixes | 3 free / Pro for unlimited |
| npx cursor-doctor audit | Full diagnostic report | Pro |
| npx cursor-doctor conflicts | Cross-format conflict detection | Pro |
| npx cursor-doctor test <file> | AI rule adherence testing | Pro |
| npx cursor-doctor team drift | Detect config drift across team | Pro |
What it checks
100+ lint rules:
- Conflicts — contradictory instructions across files (48 semantic patterns)
- Syntax — broken YAML frontmatter, boolean strings, unclosed code blocks
- Token budget — rules burning context window, dead rules, excessive alwaysApply
- Globs — patterns that don't match files, regex in globs, overlapping coverage
- Prompt quality — vague instructions, first person, politeness tokens, negation-only rules
- Structure — file naming, duplicate content, missing descriptions, legacy .cursorrules
Auto-fix (Pro)
34 auto-fixers: frontmatter repair, glob syntax, boolean strings, whitespace, TODO removal, duplicate descriptions, heading normalization, and more.
npx cursor-doctor fix --preview # See what would change (free)
npx cursor-doctor fix # Apply all fixes (Pro)
$9 one-time at nedcodes.gumroad.com/l/cursor-doctor-pro. If it doesn't find real, fixable issues in your project, email hello@nedcodes.dev for a full refund.
VS Code / Cursor extension
Search "Cursor Doctor" in the extensions panel. Health grade in your status bar. Inline diagnostics on save. Quick-fix code actions with Pro.
CI / GitHub Action
Catch broken rules before merge:
- uses: nedcodes-ok/cursor-doctor@v1
Pre-commit hook
Validate rules locally before every commit:
cp scripts/pre-commit-hook.sh .git/hooks/pre-commit && chmod +x .git/hooks/pre-commit
The hook runs cursor-doctor check only when .mdc, .cursorrules, CLAUDE.md, or AGENTS.md files are staged.
README Badge
Show your project's Cursor rules health in your README:
npx cursor-doctor badge
Output:
Markdown:
-brightgreen)
HTML:
<img src="https://img.shields.io/badge/Cursor%20Rules-A%20(96%25)-brightgreen" alt="Cursor Rules: A (96%)">
Example:
Dynamic badge (updates automatically via shields.io endpoint):
# Generate endpoint JSON
npx cursor-doctor badge --json > cursor-rules-badge.json
# Commit to your repo
git add cursor-rules-badge.json && git commit -m "chore: add cursor rules health badge"
# Use in README.md (replace YOUR_REPO_URL)

Badge colors: A=brightgreen, B=green, C=yellow, D=orange, F=red.
MCP Server
Use cursor-doctor as an MCP tool inside your AI coding assistant:
{
"mcpServers": {
"cursor-doctor": {
"command": "npx",
"args": ["-y", "cursor-doctor-mcp"]
}
}
}
LSP Server
Real-time diagnostics in Neovim, Zed, or any LSP-compatible editor:
npm install -g cursor-doctor
# Configure your editor to use cursor-doctor-lsp
Related tools
| Tool | What | Install |
|------|------|---------|
| rule-gen | Generate rules from your codebase with AI | npx rulegen-ai |
| rule-porter | Convert rules between Cursor, Claude, Copilot, Windsurf | npx rule-porter |
| nedcodes.dev | Guides, playground, and tools for Cursor AI developers | |
Like cursor-doctor?
If cursor-doctor helps your team ship better AI-assisted code, here's how to support it:
- ⭐ Star the repo — helps other developers find it
- 🐛 Report bugs — we fix issues fast
- 💬 Join the discussion — share patterns, request features, help others
- 📢 Share it — if it saved you debugging time, tell your team
- 🔧 Explore the ecosystem — rule-gen generates rules from your codebase, rule-porter converts between AI assistants, cursor-lint catches rule issues in real-time
License
MIT
Related Skills
taste-skill
110.6kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
69.8kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
46.6kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
