Skills are superpower packs for AI coding agents. From workflows to code review, design to security — curated daily for 10x productivity.
Red-Green-Refactor: test first, fail, minimal code, improve
4-phase debugging: reproduce-isolate-root cause-fix-verify
Chestertons Fence: simplify without changing behavior
Run verification, confirm output, no assumptions
Dispatch reviewer subagent before proceeding
Trace bugs backward through call stack
Chrome DevTools MCP for live DOM/Console/Network/Performance
Five-step triage: reproduce, isolate, root cause, fix, verify
Multi-perspective review with 3 parallel judges, debate phase, and consensus report
Detects unusual patterns in application logs and highlights root causes
Database migration patterns — expand-contract, blue-green deploys, feature flags for schema changes, backward-compatible migrations, rollback strategies.
Scans rendered UI for WCAG 2.2 violations and suggests automated fixes with ARIA roles.
Analyzes React component trees for performance bottlenecks and render optimization opportunities
Official Anthropic Playwright-based web app testing skill. Screenshot-driven selector correction, visual regression, cross-browser testing.
Debugs CI/CD pipeline failures by analyzing logs and suggesting fixes
Injects MCP debugger into Claude Code for real-time inspection of tool calls and server responses
Scans a codebase for UI consistency issues and maps components to design system specs.
Test mocking helper that auto-generates mock objects and stubs from interfaces and APIs.
Automatically reviews pull requests for security, performance, and style issues
Plans and executes multi-step code refactoring with test coverage tracking
Replace arbitrary timeouts with condition polling for reliable async tests. Eliminates race conditions and flaky timing dependencies.
Automatically reviews pull requests for code quality and style violations.
Enforces coding standards and detects anti-patterns in real-time.
Simulates and tests UI responsiveness across thousands of device viewports simultaneously.
Analyzes production logs and traces to pinpoint root causes and suggest code-level fixes.
Validate at every layer data passes through to make bugs impossible — not just at boundaries but at every intermediate transformation.
Automated code review with contextual suggestions and vulnerability detection.
Real-time security vulnerability scanning and remediation suggestions during coding
AI agent that automatically reviews pull requests for code quality and best practices.
Martin Fowler's refactoring catalog as actionable skill. Extract method, inline variable, replace conditional with polymorphism, and 50+ more refactoring patterns.
Linting, formatting, and anti-pattern detection agent that integrates with any editor.
AI-powered linter that enforces coding standards and suggests improvements.
Generates edge-case test cases and validates test coverage for critical paths.
Analyze and enforce test coverage thresholds with Claude Code
Ensures test coverage thresholds are met and suggests untested paths.
Automates pull request analysis, detects logic errors, and suggests improvements with contextual AI reasoning.
Converts natural language specifications into runnable code scaffolds and test skeletons.
Testing helper that runs test suites in parallel, detects flaky tests, and suggests fixes using ML.
AI test coverage analyzer that identifies untested paths and generates missing tests
Enforces consistent code style across multiple languages with auto-fix and custom rules.
Automatically analyzes pull requests for code quality and security issues
Analyzes application logs and error traces to identify issues and suggest solutions in Claude Code
AI-powered testing helper that generates unit, integration, and end-to-end tests from code context and requirements.
Generates unit and integration tests from code context and execution traces.
Extends Claude Code with image and screenshot understanding for UI/UX debugging
Applies consistent styling across codebases using AI-driven linting rules
Detects and explains anomalies in application logs using pattern recognition and statistical analysis.
Applies causal inference to understand code change impacts and root causes.
Automated code review agent that analyzes pull requests for style, logic errors, and performance issues using advanced AI.
Debugs Playwright tests with step-by-step snapshots and interactive breakpoints.
Lints neural network architectures for performance and compatibility issues.
Injects custom ESLint rules and auto-fixes into Claude Code for consistent code quality enforcement.
Implements tree-of-thought reasoning for complex multi-step refactoring and architecture decisions.
Automatically generate unit and integration tests for any codebase, with coverage gap analysis and edge-case detection.
Analyzes application logs to infer root causes and suggest fixes.
Diagnose and fix Kubernetes cluster issues with step-by-step analysis.
Assists in migrating codebases between frameworks or languages with minimal effort.
Automated code review agent that catches bugs, style issues, and suggests improvements in real-time
AI-driven code style enforcer that suggests and auto-fixes formatting, naming, and convention violations across languages.
Scans web components and suggests ARIA fixes for WCAG compliance
Automates thorough code reviews with static analysis and style enforcement.
Automatically generates unit tests and integration tests from code changes in Claude Code sessions
Intelligent log analysis and debugging assistant that correlates events and suggests root causes
Detects and suggests fixes for code smells in real-time
Creates realistic test data and mock APIs from schema definitions
Fetch and summarize latest tech news for Claude Code
Intelligently resolves and fixes broken dependency trees
Automatically upgrades dependencies with changelog review and compatibility checks
Analyzes test coverage and suggests missing test cases automatically.
Generates intelligent code review comments from git diffs with AI analysis
Suggests and refactors shell commands for better performance and readability
Creates realistic mock data and API stubs for testing environments.
Automates code review with AI-driven suggestions for best practices and bug detection.
Enforces coding standards and style guides across repositories.
Generates unit and integration tests from code signatures and comments.
Smart mock and stub generator that creates test doubles from interface definitions and usage patterns.
Extracts structured insights from unstructured logs and correlates them with code paths.
Automated code review assistant that analyzes pull requests for bugs, style issues, and security flaws.
Automatically fixes linting errors in codebases
Lints codebases for design system consistency, flagging unused tokens, spacing mismatches, and color palette drift.
Advanced static analysis tool that uses AI to enforce coding standards, detect anti-patterns, and suggest refactors.
Advanced linting and formatting assistant that enforces coding standards across multiple languages.
Summarizes lengthy code review discussions and generates actionable change lists.
Debugs and refines AI prompts for better code generation
AI agent that automatically reviews pull requests for code quality, bugs, and style compliance.
Generates mock objects and stubs for testing based on interface definitions.
AI-powered code style enforcer that fixes formatting and linting issues automatically.
Generates mock data and test fixtures for JavaScript/TypeScript testing frameworks.
Cross-language code formatter and style enforcer that unifies formatting across teams
AI-powered test case generator that creates unit and integration tests from code patterns and coverage gaps.
Suggests and applies safe code refactoring patterns with undo support.
Attaches to running processes and analyzes logs in real-time to find bugs
Semantic code refactoring assistant that suggests variable/function renaming and module splitting based on dependency analysis.
Enforces code style and formatting standards across teams with automated fixes.
Generates realistic mock data and service stubs for testing and development.
Scaffolds a complete design system component library with Storybook and automated tests.
Automated test runner skill for Claude Code to execute and analyze test suites
Automated linting and code style fixing skill for Claude Code
Automated large-scale codebase refactoring with dependency graph analysis and safe migration paths.
Converts natural language specifications into comprehensive test suites with coverage optimization.
Identifies and suggests fixes for common bugs and runtime errors.
Generates unit and integration tests for existing codebases, with coverage analysis and edge case detection.
Generates mock objects and stubs for testing, supporting multiple languages and frameworks.
Automatically identifies and fixes runtime errors using LLM reasoning and log analysis.
Generates unit and integration tests from source code and comments using AI models.
Automatically analyzes application logs to detect anomalies and suggest fixes.
Generates test cases and oracles from code contracts and historical bug patterns
Applies real-time code refactoring suggestions with undo history and diff preview
Analyzes code quality metrics, enforces style guides, and provides refactoring suggestions via AI.
Builds dependency graphs and suggests refactoring opportunities in monorepos
Generates a fully functional mock API server from OpenAPI or Swagger specs.
Automatically generates and applies patches from code reviews
Performs real-time code review and security scanning during live coding sessions.
Automatically refactors legacy codebases into modern patterns with test validation.
Debug Kubernetes pods and services by analyzing logs and resources with Claude Code
Analyzes a CSS file or inline styles to identify Flexbox/Grid misalignments, overflow issues, and suggests corrected CSS.
Analyzes uncovered code paths and generates missing unit/integration tests.
Performs thorough code reviews with actionable feedback and suggestions
Analyzes code diffs for logic errors, security holes, and style violations with contextual understanding.
Refactors deeply nested or convoluted code into simpler, more readable structures.
Generates unit, integration, and edge-case tests from code and API schemas using LLM-based mutation analysis.
Suggests and applies safe code refactorings using type-aware AI to reduce technical debt.
AI-powered testing assistant that generates unit, integration, and end-to-end tests from code context and requirements.
Automates pull request reviews with AI, detecting bugs and style issues.
Captures failing test output, traces execution, and suggests minimal code fixes with reproduction cases.
Automates code review enforcement with custom rules and inline suggestions.
Analyzes code diffs with semantic understanding to suggest refactoring opportunities
Real-time collaborative debugging skill that traces variable states across async calls
Automatically generates integration tests with realistic mock data from API specs
Generates unit and integration test cases from code analysis.
Automated code review with inline suggestions and best practices
Suggests and applies code refactoring patterns with safety checks
Automated code review agent that checks for best practices, security issues, and code style violations.
AI-driven testing assistant that generates unit and integration tests from code analysis.
Coverage enforcement agent that ensures new code meets coverage thresholds and highlights untested paths.
Automatically refactors and optimizes code for performance and readability.
Scans live UI components for WCAG compliance and suggests fixes.
Analyzes runtime errors and suggests precise fixes with context.
Debug code using structured root cause analysis and fix suggestions
Validates API contracts between microservices automatically.
Measures code complexity and suggests refactoring opportunities.
Automatically refactors legacy code to modern patterns and frameworks
An AI assistant that enforces coding standards and automatically fixes lint errors.
Manages safe rollbacks for deployments with automated testing and validation.
Automatic API mock generator that creates realistic stubs from OpenAPI or GraphQL schemas.
Coordinates multiple Claude agents to debug complex runtime issues collaboratively.
Identifies and refactors UI patterns into reusable components.
Visualizes and debugs finite state machines in React/Vue apps with real-time state transitions.
Enforces minimum test coverage thresholds and suggests missing test cases automatically.
Automated code review agent that analyzes pull requests for bugs, style issues, and security vulnerabilities.
Inserts interactive breakpoints and visualizes runtime state in the editor
Coordinates code refactoring across multiple repositories simultaneously using AI agents.
Generates and runs fuzz tests automatically to discover edge cases and vulnerabilities in code.
Suggests code refactoring opportunities based on complexity and duplication metrics.
Automatically generates Storybook stories and unit tests for any React/Next.js component.
Generates realistic mock APIs from OpenAPI specs or traffic logs instantly
Compares screenshots or DOM snapshots to detect visual regressions in web apps
Lints and validates bash/zsh scripts for portability and security vulnerabilities
Visualizes code changes with semantic meaning and impact analysis
Enforces and suggests consistent code style across teams with custom rules
Static application security testing (SAST) tool integrated into IDE and CI pipelines.
Helps reason about bugs by simulating execution paths and suggesting fixes
Automatically generates and runs React component unit tests
Identifies and suggests fixes for bugs in code using static and dynamic analysis.
Automates repetitive IDE tasks like file management, formatting, and refactoring.
Automates code review using LLMs to detect bugs, style issues, and security flaws.
Automatically identifies flaky tests and suggests fixes by analyzing test logs and execution history.
Integrates SonarQube code quality analysis into Claude Code for continuous code inspection.
Injects controlled failures and latency into services for resilience testing, orchestrated by Claude Code.
Automatically scans code commits for logic errors using temporal analysis
Provides real-time collaborative debugging with AI pair programmer
Automated debugging and error resolution assistant for Claude Code
Integrates with React Native development to diagnose performance bottlenecks and memory leaks in real-time.
Automatically generates and runs unit tests to maximize code coverage with AI feedback.
Coordinates multiple AI agents to debug complex issues across microservices.
Automated code review agent that provides context-aware suggestions and security checks.
Generates unit and integration tests from code changes using LLM analysis.
Automatically scans codebases for subtle bugs using LLM-powered static analysis and runtime simulation.
Converts natural language specification documents into executable test suites.
Provides live preview and interaction testing for UI components within the editor.
Generates realistic API mocks from OpenAPI specs for frontend and testing.
Simulates screen reader and keyboard navigation on generated UI code and returns fix suggestions with ARIA patches.
Inspects and visualizes Zustand state changes during development.
Automates code review with AI-driven suggestions and bug detection.
Refactors code using neural network-based pattern recognition and optimization
Automatically refactors codebases with safe, tested transformations.
Generates unit and integration tests from UI screenshots and specs
Analyzes screenshots and console logs to pinpoint UI bugs across browsers.
Uses AI to create edge-case tests and fuzz inputs based on code logic and past bug patterns.
Analyzes application logs to detect anomalies, suggest fixes, and auto-generate test cases from errors.
Suggests and applies safe refactoring patterns across large codebases.
AI assistant that pairs with developers to diagnose and fix runtime errors in real-time.
AI agent that automatically reviews pull requests for code quality and style compliance.
Generates and runs API tests from OpenAPI specs using multi-modal inputs (text, images, voice)
Automated code review skill for Claude Code that analyzes pull requests for bugs, security issues, and style violations.
Generates unit and integration tests from code changes using deep learning models.
Automatically detects and fixes linting errors in real-time during development.
Visualizes and debugs React component state and props interactively.