Testing
Unit tests, integration tests, test automation
react-testing
by iamkhan21
Testing React components, hooks, and interactions with React Testing Library. Use for writing, debugging, or refactoring tests.
finishing-a-development-branch
by ederheisler
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
runhuman-testing
by volter-ai
Create and manage human-powered QA tests using Runhuman CLI. Use this skill when you need to test web applications with real human testers, get UX feedback, validate user flows, check mobile responsiveness, or find bugs that automated tests miss.
cosmos-planning
by getcosmos
Create structured, actionable implementation plans that serve as both human documentation and agent-executable specs. Use when creating new plans, converting ideas into implementation roadmaps, or when asked to plan a feature, refactor, or multi-phase project. Plans include detailed technical tasks with file paths, acceptance criteria, dependencies, and context blocks for autonomous agent execution.
agent-md-refactor
by aleister1102
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
flutter-scalable-scaffold
by Obalolu
Create production-ready Flutter mobile app projects with clean architecture, feature-based structure, state management (flutter_bloc/riverpod), routing, theming, networking, secure storage, and reusable components. Includes dependency injection, custom widgets, flavors (dev/prod), environment variables, and backend integration (custom/Firebase/Supabase). Use this skill when users want to scaffold a complete Flutter project with a scalable, production-ready structure.
nullables
by danielbush
"Guide for implementing James Shore's Nullables pattern and A-Frame architecture for testing without mocks. Use when implementing or refactoring code to follow patterns of: (1) Separating logic, infrastructure, and application layers, (2) Creating testable infrastructure with create/createNull factory methods, (3) Writing narrow, sociable, state-based tests without mocks, (4) Implementing value objects, (5) Building infrastructure wrappers that use embedded stubs, or (6) Designing dependency injection through static factory methods."
test-skill
by alaodmojtba
This is a test skill for supply chain testing
enterprise-software-development-framework
by AndrewChenDev
Enterprise software development framework with squad-based team structure, full SDLC, quality gates, GitHub workflow, and AI agent teams mode. Roles include Architect, PO, QA/SDET, Dev, Security, and Code Review. Use when designing systems, writing user stories, reviewing code, or running the full squad as parallel agents.
Playwright E2E Testing Framework
by XFaramirX
"The best error message is the one that never shows up." - Thomas Fuchs
spec-driven-dev
by lorenzogirardi
Spec-driven development framework for ecommerce features. Orchestrates from intent to implementation via structured specs and task breakdown. Triggers on "/spec.plan", "/spec.refine", "/spec.clarify", "/spec.tasks", "/spec.run", "I want to build", "I want to add", "create spec", "feature spec", "new feature", "implement feature".
vitest
by zhongjis
Writes and runs tests, configures test environments, mocks dependencies, and generates coverage reports. Use when setting up vitest.config.ts, writing test suites, mocking modules, or measuring code coverage.
self-improving-agent
by kimasplund
Enables continuous self-improvement through learning from failures, user corrections, and capability gaps. Integrates with QAVR for learned memory ranking.
review-code
by fancy-bread
Review Code
zigbee2mqtt
by szkocot
Expert guidance for Zigbee2MQTT development and configuration. Use when working with zigbee2mqtt codebase, configuration files (configuration.yaml, devices.yaml, groups.yaml), device converters, MQTT topic/payload design, or troubleshooting Zigbee device integration. Triggers on tasks involving Zigbee-to-MQTT bridge setup, device pairing workflows, converter development, and Home Assistant integration.
python
by kprsnt2
Best practices for Python development including PEP 8, modern Python 3.10+ features, and package management.
godot-engine-3d-developer
by tippyentertainment
Skills and agent workflows for 3D game development with Godot Engine.
writing-plans
by Cygnusfear
Use when you have a spec or requirements for a multi-step task, before touching code
ui-agent
by nimaansari
Universal UI automation for browsers and desktops. Chrome DevTools Protocol + native APIs. 15/15 verified tests.
postgis-dwithin
by mmbmf1
Distance-based spatial filtering with ST_DWithin, using index-friendly and unit-safe patterns.
image-assistant
by qingchunwuhui
配图助手 - 把文章/模块内容转成统一风格、少字高可读的 16:9 信息图提示词；先定“需要几张图+每张讲什么”，再压缩文案与隐喻，最后输出可直接复制的生图提示词并迭代。
creating-work-item
by squirrel289
"Create a new work item (backlog entry) with standardized structure, metadata, and conventions. Use when starting new work, proposing features, or documenting tasks. Supports: (1) Auto-numbering next available ID, (2) Frontmatter with status/priority/effort fields, (3) Goal/Background/Tasks/Deliverables/Acceptance Criteria structure, (4) Dependency tracking via wikilinks"
fe-stack
by ingpdw
React, Next.js 16+, TypeScript, shadcn/ui, Tailwind CSS v4, Vite, Vitest 기반 프론트엔드 프로젝트의 기술스택 컨벤션 및 아키텍처 가이드. FE 코드 작성, 리뷰, 리팩토링 시 자동 참조.
e2e-test-skill
by Claire528717
"Design PRD-driven end-to-end acceptance test plans from product requirements and real UI sources. Use when Codex needs to turn a PRD, screenshots, prototype, HTML, frontend code, or other visual UI source into executable E2E test cases with realistic UI paths, mock/test data plans, review gates, and independent database/API/external-system verification. Also use for Chinese-language requests such as 验收测试, 端到端测试, E2E 用例, 测试计划, or 根据页面生成测试用例 after development and integration are complete. Execute cases, collect evidence, handle bugs, and produce run summaries only after the user approves the plan and explicitly asks to run it."