Skill Claude CodeCodex
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
not rated 12 today A 31 tokens
Skill Claude CodeCodex
Review a range of recent work in the current repo and land the findings as an uncommitted markdown file at the repo root, ordered by severity. Use when the user asks for a code review of recent commits, a branch, a diff, or "the last couple of days", or wants a written review they can work through afterwards. Not for…
not rated 12 today A 87 tokens
Skill Claude CodeCodex
Use when the user asks for a rich explanation of a code change, diff, branch, or PR. Produces HTML output.
not rated 12 today A 32 tokens
handoff
04Skill Claude CodeCodex
Compact the current conversation into a handoff document for another agent to pick up.
not rated 12 today A 19 tokens
Skill Claude CodeCodex
Fork a repo, park it in the right place, and draft a pull request body (or issue report) in the user's house style, including the review handoff before it is opened. Use whenever forking a repo, drafting a PR description, opening a PR, or proposing a fix to an upstream/third-party repo.
not rated 12 today A 70 tokens
tailwind-4
06Skill Claude Code
Tailwind CSS 4 patterns and best practices. Trigger: When styling with Tailwind (className, variants, cn()), especially when dynamic styling or CSS variables are involved (no var() in className).
not rated 12 today A 47 tokens
Skill Claude CodeCodex
Powerful asynchronous state management, server-state utilities, and data fetching for TS/JS, React, Vue, Solid, Svelte & Angular.
not rated 12 today A 33 tokens
Skill Claude CodeCodex
Type-safe routing for React and Solid applications with first-class search params, data loading, and seamless integration with the React ecosystem.
not rated 12 today A 29 tokens
Skill Claude CodeCodex
Headless UI for virtualizing large element lists at 60FPS in TS/JS, React, Vue, Solid, Svelte, Lit & Angular.
not rated 12 today A 36 tokens
Skill Claude Code
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
not rated 12 today A 54 tokens
turborepo
11Skill Claude CodeCodex
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines…
not rated 12 today A 111 tokens
Skill Claude CodeCodex
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…
not rated 12 today A 67 tokens
vitest
13Skill Claude CodeCodex
Vitest API and config reference (Jest-compatible) — mocking with vi., spies, fake timers, coverage configuration, fixtures, snapshots, and test filtering. Use for Vitest API and configuration questions anywhere in the monorepo; for Studio-specific test strategy and component-test setup, start with studio-testing and…
not rated 12 today A 71 tokens
xstate-v5
14Skill Claude CodeCodex
Design, implement, review, and migrate XState v5 state machines and statecharts in TypeScript using modern v5 patterns. Use this whenever the user mentions XState, actors, state machines, statecharts, guards, transitions, workflows, or Stately, or is modeling non-trivial UI/app/process logic in a codebase that uses…
not rated 12 today A 110 tokens
Skill Claude CodeCodex
Use when the user says "visual answer" or asks for a question answered or work explained visually.
not rated 12
changed 23d ago A 23 tokens
SessionStart
16Hook Claude Code
One of 2 in settings.json
Runs when a session starts on ^(startup, resume, clear, compact and fork)$, executing herdr-agent-state.sh via bash. From mutewinter/.dot.
not rated 12
changed 13d ago A
tokens not measured
humanizer
17Skill Claude CodeCodex
Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler. Based on Wikipedia's…
not rated 12 today A 81 tokens
no-ai-slop
18Skill Claude CodeCodex
Edit drafts into sharper, more human writing while preserving the writer's personal voice, or detect AI-slop patterns without rewriting. Use when the user wants a draft clearer, more direct, more opinionated, or less AI-sounding, or asks whether writing reads as AI.
not rated 12 today A 60 tokens
Skill Claude CodeCodex
Build a one-page review of a range of commits the user did not read as they landed, grouped by concern, with every commit tied to the Claude Code session that made it. Use when the user asks to review recent work, a merge, a branch, a release, "what landed while I was away", "since my last review", one subject's…
not rated 12 today A 107 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: