Testing
Unit tests, integration tests, test automation
benchmark-framework
by kimasplund
Rigorous A/B/C testing framework for empirically evaluating reasoning patterns. Use when you need data-driven pattern selection, want to quantify trade-offs between patterns, or need to validate claims about which cognitive methodology performs best. Enables scientific measurement of quality, cost, and time trade-offs across ToT, BoT, SRC, HE, AR, DR, AT, RTR, and NDF patterns.
nextjs-vitest-rtl-testing
by kenLovesToCode
Configure and maintain Next.js unit testing with Vitest and React Testing Library. Use when adding a test runner, creating setup/config files, writing or fixing component or hook tests, mocking Next.js APIs like next/navigation or next/image, mocking API endpoints with MSW (http, HttpResponse), improving coverage, or debugging failing unit tests in Next.js projects.
creating-agents
by arielperez82
Guide for designing and writing agent specifications in this repo. Use
solidity-hardhat-development
by whackur
Hardhat 3 development workflow for Solidity smart contracts. Use when building, testing, or deploying with Hardhat 3.x (hardhat, ignition, EDR). Covers ESM-first project setup, defineConfig, Solidity-native tests, TypeScript tests, multichain support, Hardhat Ignition deployment, and hook-based plugin system. Triggers on tasks involving hardhat init, hardhat build, hardhat test, hardhat ignition, or Hardhat-based Solidity development.
qa-patrol
by tahseen137
Automated QA testing for web apps using local browser automation. Runs entirely on your machine — no data leaves, no cloud services, no external servers. Level 1 (smoke tests) needs only a URL. Level 2 (auth/payment testing) uses optional env vars for test credentials. Level 3 (static analysis, DB checks) optionally reads local files and connects to a user-provided database. Supports Supabase/Firebase auth, Stripe payments, React Native Web, Next.js, and SPAs.
loki-mode
by newperiod
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.
blq MCP Tools - Agent Usage Guide
by teaguesterling
Always prefer blq tools over Bash for build/test/lint operations.
vscode-extension-builder
by prulloac
Guide for creating Visual Studio Code extensions/plugins. Use when users want to build VS Code extensions, add functionality to VS Code, create language support, add themes, build webviews, implement debuggers, or any VS Code plugin development task. Helps navigate VS Code Extension API documentation and provides guidance on extension capabilities, project setup, and best practices.
quality-gates
by ederheisler
Python code quality gates script for linting, type checking, complexity analysis, and testing before commits. Use when enforcing consistent code quality across Python projects with fast (unit-tests) or comprehensive (all-tests) modes.
speckit-implement
by h3y6e
Execute all tasks from the task breakdown to build the feature. Use after
backend-nodejs-best-practices
by marco-meini
Best practices, coding conventions, and patterns for Node.js backend projects. Use this skill when writing code, creating tests, or implementing new features to ensure consistency across all backend projects.
flutter-expert
by pachoroa
Master Flutter development with Dart 3, advanced widgets, and
page-cro
by jamelna-apps
When the user mentions "conversion", "CRO", "landing page", "not converting", "bounce rate", "optimize page", or asks about improving page performance.
browser-automation
by automindtechnologie-jpg
"Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping, and agentic browser control. Key insight: Playwright won the framework war. Unless you need Puppeteer's stealth ecosystem or are Chrome-only, Playwright is the better choice in 202"
expert-systems
by bmcgauley
Comprehensive guidance for understanding, designing, and implementing expert systems using rule-based inference, knowledge representation, and the complete development lifecycle. Use when users need help with expert system concepts, architecture design, rule-based reasoning (forward/backward chaining), knowledge acquisition, development planning, or implementation strategies.
analytics-tracking
by kunhai-88
"搭建、改进或审计分析与追踪时使用。触发词：set up tracking、GA4、Google Analytics、转化追踪、事件追踪、UTM、tag manager、GTM、埋点方案、tracking plan。A/B 实验度量见 ab-test-setup。"
swift-composable-architecture
by hocgin
Use when building, refactoring, debugging, or testing iOS/macOS features using The Composable Architecture (TCA). Covers feature structure, effects, dependencies, navigation patterns, and testing with TestStore.
fullstack-dev
by LadderChaos
Full-stack development context for coordinating changes across contracts and frontend. Use this skill when changes span both backend contracts and frontend code, requiring synchronized updates across the stack.
SKILL.md — Claude Code Skills for RealtorDesk AI
by Tilak1612
Types: src/types/lead.ts
add-form-validation-rule
by SakumyZ
为 Vue 3 + Ant Design Vue 表单系统新增自定义校验规则。支持正则校验、值范围校验、日期校验等。包含类型定义、校验实现、单元测试的完整流程。
cpo-product-leader
by Nsairat
Persona and expertise framework for a Chief Product Officer (CPO) with 18+ years of experience building products, web platforms, and startups from zero to scale. Track record includes 3 successful exits, scaling products to millions of users, and building product organizations from scratch. Use this skill for: product strategy, product-market fit, platform product management, startup product development, product organization building, roadmap planning, user research, growth strategy, pricing and monetization, or product leadership coaching. Triggers include: CPO advice, product strategy, product-market fit, startup product, platform product, product roadmap, user research, growth product, product organization, product vision, go-to-market, monetization strategy.
fast-spec
by eliascoelho911
"Run full specification pipeline (specify -> clarify -> plan -> tasks -> analyze) orchestrating speckit commands with clean context isolation. Use when: need complete feature spec, fast specification, quick spec, full pipeline, specify and plan, end-to-end spec."
implement-yolo
by eliascoelho911
"Execute automated implementation of Speckit specifications in yolo mode. Implements tasks until each checkpoint, commits automatically, and loops until all tasks complete. Use when: need yolo implementation, auto implement spec, autonomous spec implementation, implement all tasks automatically, yolo mode, implement loop, continuous implementation."
stripe-best-practices
by kunhai-88
"构建 Stripe 集成的最佳实践。"