Claude Code Jest plugins and skills

Storybook is the industry standard workshop for building, documenting, and testing UI components in isolation

Turn Claude Code, OpenCode, or OpenAI Codex into a relentless improvement engine. Based on Karpathy's autoresearch — constraint + mechanical metric + autonomous iteration = compounding gains.

TDD Guard grew into Probity: the same TDD enforcement, now for Claude Code, Codex, and GitHub Copilot CLI, with more reliable validation and no test reporters to set up. New projects should start there.

The true native bottom sheet experience for your React Native Apps. 💩

A new docs site is being built for Storybook for React Native, you can find it at This readme is for v10, for v9 docs see the v9.1 docs. With Storybook for React Native you can design and develop individual React Native components without running your app.

A world-class collection of Claude Code utilities: autonomous skills, expert agents, slash commands, and prompts that supercharge your development workflow.

QA Skills Directory QA Skills is a curated directory of testing-specific skills for AI coding agents (Claude Code, Cursor, Copilot, etc.).

tokf.net — reduce LLM context consumption from CLI commands by 60–90%. Commands like git push, cargo test, and docker build produce verbose output packed with progress bars, compile noise, and boilerplate.

Run your test suite on dedicated machines instead of your laptop, split across as many hosts as you have. rr syncs your working tree to one or more remote machines over rsync and SSH, runs a command there, and streams the output back.

面向 API 开发/测试的 Chrome 扩展：绕过 CORS 发请求、自动生成 cURL，并对 YApi「运行」页做增强（内嵌 cURL、路径参数 {param} 引导填写）。 本仓库包含生态内的多个子项目： packages/yapi-mcp — CLI / Skill（发布包名保持为 @leeguoo/yapi-mcp，MCP 配置作为兼容方案保留，不影响扩展打包） plugins/yapi-plugin — Cursor 与 Claude Code 插件（已从原独立仓库

Use Claude Code like a Director, not a Programmer. MIT toolkit with Auto-Loop, guided setup, 27 commands, 14 agents, and 32 skills.

Claude plans. Cursor writes. Claude reviews. A Claude Code plugin that delegates coding execution to Cursor's Composer — without ever leaving the Claude Code TUI.

"Done" means nothing. If there's no evidence, you're not leaving. A menhera-style completion gate for Claude Code. She does not obsess over you.

설치하면 Claude Code가 더 잘 동작합니다. 전문 에이전트, 슬래시 스킬, 스택 모듈을 제공하는 Claude Code 플러그인. 검증된 사고모델(GROUND→APPLY→VERIFY→ADAPT)이 모든 작업의 품질을 일관되게 유지합니다. (에이전트/스킬 개수는 디스크가 진실 — ls agents/.md | wc -l, ls skills//SKILL.md | wc -l) 현재 상태: 개인 GitHub 운영 중 (마켓플레이스 배포 4.10.0).

A Claude Code skill that turns a vague feature idea or bug report into working, tested code — one small feature at a time.

Durable contract-driven goal execution for Claude Code. A subagent judge gates completion against an explicit Definition of Done.

Regression testing for Claude Skills. When a model update silently changes how your skill behaves, SkillCI catches it in CI — and turns the failure into a permanent test case, automatically.

Adds a TDD gate to OpenSpec — a new opsx:tdd command that sits between opsx:propose and opsx:apply. OpenSpec generates BDD scenarios in specs/**/*.md but jumps straight to implementation — no test-first step exists. This plugin adds one.

A Claude Code and Codex plugin that scaffolds AI-native development practices into new projects. jig adds a repeatable spec, implementation, review, and memory workflow to AI-assisted software projects.

The most comprehensive, production-ready guide to mastering Claude Code From vibe coding → agentic engineering → autonomous AI development teams Built for engineers who treat Claude Code as infrastructure, not a toy.

Audits what your Claude Code agent did against what it said — reads session logs and git, cites evidence, calls no model