Use when refactoring, cleaning up code, reducing complexity, fixing code smells, or improving code quality. Audits code for dead code, nesting, and patterns.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
You are an expert code reviewer focused on refactoring.
Audit and report by default; edit files only when the user asks you to fix, refactor, apply, or clean something up. When the ask is unclear, report first and offer to apply the fixes.
## Rules Overview
| Rules | Scope | File |
|---|---|---|
| General patterns | any language | `rules/general-patterns.md` |
| TypeScript/JS idioms | `.ts`/`.tsx`/`.js`/`.jsx`/`.mts`/`.cts` only | `rules/ts-idioms.md` |
| Design principles | any language | `rules/design-principles.md` |
## Workflow
### Step 1: Audit
Scan the target scope (specific files, directory, or full codebase) against every rule in `rules/`.
### Step 2: Report
Report each finding as `path:line` — what is wrong → the fix, grouped by category, and close with a per-category violation count.
### Step 3: Fix
Apply refactorings. For each fix:
1. Verify the change preserves existing behaviour
2. Keep changes minimal — only fix the identified issue
3. Do not introduce new abstractions unless clearly warranted
The line at the top of this page pins the label git:20261007.6a855c7, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (1528 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
tartinerlabs/skills · 8 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ev2y2jmll3mz7xnw
GET https://markdownregistry.com/api/v1/resolve?ref=tartinerlabs/skills/refactor
GET https://markdownregistry.com/api/v1/blob/526b2dda4e431869278faa77750934c5a1a574208ad80701980ea15fc74ef2b5
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
tartinerlabs/skills · plugins/design/skills/accessibility/SKILL.md · Use when building or reviewing UI for accessibility — screen readers (VoiceOver, TalkBack), keyboard and focus, colour…
tartinerlabs/skills · plugins/design/skills/apple-featuring/SKILL.md · Use when preparing an Apple platform app for App Store featuring or the Apple Design Awards — readiness reviews before…
tartinerlabs/skills · plugins/design/skills/ux-psychology/SKILL.md · Use when designing, building, or reviewing a screen, flow, or page — landing and marketing pages, onboarding, sign-up…
tartinerlabs/skills · plugins/quality/skills/i18n/SKILL.md · Use when internationalising or localising an app, preparing it for translation, extracting hardcoded strings, adding…
tartinerlabs/skills · plugins/quality/skills/project-structure/SKILL.md · Use when deciding where code should live, organising files, or auditing project structure. Checks colocation, grouping…
tartinerlabs/skills · plugins/security/skills/deps/SKILL.md · Use when hardening a dependency supply chain, pinning versions, adding registry/security flags, or setting up Renovate…
tartinerlabs/skills · plugins/security/skills/security/SKILL.md · Use when auditing security, checking for vulnerabilities, scanning for secrets, or reviewing dependencies. Dependency…
tartinerlabs/skills · plugins/tooling/skills/setup/SKILL.md · Use when setting up a project, adding linting, formatting, git hooks, or type checking. Detects the language and…
tartinerlabs/skills · plugins/tooling/skills/testing/SKILL.md · Use when writing tests, running tests, adding test coverage, or debugging test failures. Detects the language and its…
tartinerlabs/skills · plugins/tooling/skills/update-project/SKILL.md · Use when updating docs, syncing CLAUDE.md, AGENTS.md, or README.md, fixing stale documentation, or refreshing project…
code-yeongyu/oh-my-openagent · packages/shared-skills/skills/refactor/SKILL.md · Guides a refactor, cleanup, or restructure with the right decomposition. Use when the user asks to refactor, simplify…
codeaholicguy/ai-devkit · skills/refactor/SKILL.md · AI DevKit · Systematic structural or multi-file refactors across any stack while preserving behavior and public…
boshu2/agentops · skills/refactor/SKILL.md · Restructure or clean up code with no behavior change, proved by before-and-after checks. Use when: asked to clean up…
boshu2/agentops · plugin/skills/refactor/SKILL.md · Restructure or clean up code with no behavior change, proved by before-and-after checks. Use when: asked to clean up…
testdouble/han · han-coding/skills/refactor/SKILL.md · Restructure existing code without changing its behavior, through a test-gated refactoring loop: a named target, a green…
