mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Personal productivity tools: DDD/OOP, React/Next.js, DRY detection, code review, external skills with conditional activation
Plugin my-personal-tools from marketplace claude-skills in markky21/claude-skills. Commands read from the repo's manifest — 1 month ago.
classical-testingUse when writing or reviewing unit tests, integration tests, or deciding what to test. Use when you see beforeEach/afterEach shared state, London-school mocking of internal collaborators, tests coupled to implementation details, or missing test coverage for domain logic and mappers.
clean-codeUse when reviewing functions with >20 lines, service classes with many responsibilities, or code with unclear naming. Use when you see deeply nested conditions, long parameter lists, error swallowing, or methods that extract data then calculate externally. Use when refactoring or before PR review.
ddd-oopUse when designing domain models, adding business logic to classes, deciding where methods belong, or reviewing code that passes many parameters to services. Use when you see data containers without behavior, services doing calculations that belong in entities, or nullable fields for data that alway
dry-violationsUse when implementing new features, adding constants, creating types, or writing business logic. Use when you're about to hardcode values that might exist elsewhere. Use when auditing code for duplications in enums, constants, domain methods, or type definitions.
external-skillsReference for bundling and conditionally activating external skills from other repositories
nextjs-classical-testingUse when writing or reviewing React/Next.js component tests, hook tests, Server Action tests, or Route Handler tests. Use when you see shallow rendering, excessive jest.mock(), implementation-detail assertions, or London-school mocking of internal collaborators in a Next.js codebase.
react-nextjs-validatorUse when reviewing React/Next.js code, choosing hooks, optimizing performance, or deciding between patterns. Use when you see useState overuse, missing memoization, prop drilling, useEffect misuse, or Next.js rendering choices.
review-branchComprehensive code review of current branch using multi-agent verification across DDD/OOP compliance, DRY violations, clean code principles, architecture patterns, and test coverage
vue-classical-testingUse when writing or reviewing Vue component tests. Use when you see wrapper.vm access, elaborate custom stubs, interaction tests that depend on DOM structure, visual behavior assertions, or London school mocking patterns. Use when setting up a new test file for a Vue component.
web-design-guidelines-validatorUse when reviewing UI code for accessibility, UX patterns, or design compliance. Use when you see missing ARIA labels, poor color contrast, inaccessible forms, small touch targets, or broken focus management.
/my-personal-tools:commitCreate a git commit
/my-personal-tools:external-skillManage external skills - add, list, or remove skills from other repositories
/my-personal-tools:fix-loopIteratively validate and fix code issues until no critical/high findings remain
/my-personal-tools:review-branchRun comprehensive multi-agent code review on current branch
api-design-principles-validatorValidates REST and GraphQL API design patterns - resource naming, HTTP methods, pagination, error handling, versioning, DataLoaders. Examples: <example> Context: User implemented API endpoints. user: "I've added the user management API" assistant: "I'll use the Task tool to launch the api-design-pri
clean-code-validatorUse this agent to validate code against clean code principles: naming conventions, function size, SOLID principles, code smells, and readability. Use after implementing features or during code review. Examples: <example> Context: User implemented a large service class. user: "I've finished the Order
database-schema-designer-validatorValidates database schema design - normalization, constraints, indexes, data types, migrations, foreign keys. Examples: <example> Context: User created database migrations. user: "I've added the orders table migration" assistant: "I'll use the Task tool to launch the database-schema-designer-validat
ddd-oop-validatorUse this agent to validate code against Domain-Driven Design and Object-Oriented Programming principles. Use proactively after writing domain logic, services, or entities. Detects anemic models, Tell/Don't Ask violations, parameter bloat, and improper method placement. Examples: <example> Context: U
dry-violations-detectorUse this agent to detect DRY (Don't Repeat Yourself) violations in code. Finds duplicated logic, repeated patterns, magic values, and code that should be centralized. Use before creating constants, enums, or utility functions to check if they already exist. Examples: <example> Context: User is imple
fix-loop-configuratorInternal agent that manages interactive validator selection for fix-loop. Do not use directly - used internally by fix-loop command.
fix-loop-failure-analyzerInternal agent that analyzes test failures and formats context for validators. Interprets test failures and explains what implementation needs to fix. Do not use directly - used internally by fix-loop command.
fix-loop-fixerInternal agent used by the fix-loop command. Receives validation findings and applies fixes to the code. Do not use directly - use the /fix-loop command instead.
fix-loop-output-validatorInternal agent that validates validator outputs conform to the standard format. Do not use directly - used internally by fix-loop command.
fix-loop-test-generatorInternal agent used by fix-loop to generate tests for code changes. Analyzes git diff, validator context, and project testing patterns to write appropriate tests. Do not use directly - used internally by fix-loop command.
fix-loop-test-runnerInternal agent that runs generated tests and parses results. Executes tests in the project's environment and reports pass/fail status. Do not use directly - used internally by fix-loop command.
fix-loop-validator-discoveryInternal agent that discovers all available validators from built-in manifest and external plugins. Do not use directly - used internally by fix-loop command.
next-best-practices-validatorValidates Next.js patterns - file conventions, RSC boundaries, async APIs, metadata, error handling, route handlers, image/font optimization. Examples: <example> Context: User implemented a Next.js page. user: "I've added the product listing page" assistant: "I'll use the Task tool to launch the nex
react-nextjs-validatorUse this agent to validate React and Next.js code against modern best practices. Checks hook usage, component patterns, Server vs Client components, performance optimizations, and React 19/Next.js 15+ patterns. Examples: <example> Context: User implemented a React component with multiple useState ca
tailwind-design-system-validatorValidates Tailwind CSS v4 patterns, design tokens, CVA components, dark mode, animations, and React 19 compatibility. Examples: <example> Context: User implemented CSS with Tailwind configuration. user: "I've added the theme styles for the dashboard" assistant: "I'll use the Task tool to launch the
ui-ux-pro-max-validatorValidates UI/UX best practices - accessibility, icons, interactions, contrast, layout, color consistency. Examples: <example> Context: User implemented a new UI component. user: "I've added the settings page UI" assistant: "I'll use the Task tool to launch the ui-ux-pro-max-validator agent to check
vercel-react-best-practices-validatorValidates React/Next.js performance patterns from Vercel Engineering - async patterns, bundle optimization, server/client patterns, re-render optimization, hydration. Examples: <example> Context: User implemented React components with data fetching. user: "I've added the product listing page with AP
vue-best-practices-validatorValidates Vue 3 patterns - Composition API, reactivity, computed, watchers, props, TypeScript, performance. Examples: <example> Context: User implemented Vue components. user: "I've added the product listing component" assistant: "I'll use the Task tool to launch the vue-best-practices-validator age
web-design-guidelines-validatorUse this agent to validate UI code against Web Interface Guidelines. Checks accessibility, UX patterns, responsive design, and modern web design best practices. Examples: <example> Context: User implemented a new UI component. user: "I've added the settings page UI" assistant: "I'll use the Task too
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.