mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Production-grade skills, agents, and commands for AI-assisted software development
Plugin claude-skills from marketplace claude-skills in zeon-kun/claude-skills. Commands read from the repo's manifest — 1 month ago.
adrWrite an Architecture Decision Record (ADR) documenting a technical decision with context, options considered, and rationale. Use when a significant technical decision needs to be documented.
animation-designDesign animations for React/Next.js components using Framer Motion (Motion) or GSAP. Covers entrances, scroll-triggered reveals, page transitions, stagger effects, and interactive micro-animations. Respects user motion preferences.
api-designDesign a RESTful or GraphQL API with endpoints, schemas, error handling, and versioning strategy. Use when starting a new API or extending an existing one.
brand-intakeInterview the user about their brand guidelines, aesthetics, and design preferences before building any UI. Produces a structured Brand Profile used by all other frontend skills. Always invoke first before design-system-init or component-design.
breakdownDecompose an epic or large feature into stories and tasks ready for sprint planning. Produces a structured backlog. Use when given a feature, epic, or milestone to break down.
changelogGenerate a structured changelog from git commits, PR titles, or a list of changes. Follows Keep a Changelog format. Use when preparing a release or documenting what changed.
ci-pipelineDesign and generate a CI/CD pipeline (GitHub Actions, GitLab CI, or generic) with test, build, security scan, and deploy stages. Use when setting up or improving CI/CD for a project.
code-reviewReview code for correctness, security, performance, and maintainability. Produces a structured review with severity-tagged findings. Use when asked to review a PR, file, or code snippet.
codebase-ingestSystematic codebase analysis — architecture, tech stack, code patterns, brand guidelines, and provider doc health. Produces a structured Codebase Digest consumed by other agents.
component-designDesign a React component from scratch using shadcn/ui primitives + Tailwind CSS + CVA variants. Respects the project's Brand Profile and design tokens. Produces a complete, typed, accessible component.
db-schemaDesign a relational or document database schema with tables, relationships, indexes, and migration plan. Use when designing data models for a new feature or service.
debugSystematically debug an error, bug, or unexpected behavior. Produces a root cause analysis and fix. Use when given an error message, stack trace, or bug description.
design-system-auditScan an existing React/Next.js codebase and extract its implicit design system — colors, typography, spacing, component patterns, and inconsistencies. Use when onboarding to an existing project or before formalizing a design system.
design-system-initBootstrap a complete design system for a React/Next.js project using shadcn/ui + Tailwind CSS v4. Generates globals.css tokens, tailwind.config, font setup, and a base component theme. Requires a Brand Profile from brand-intake first.
doc-syncValidates and updates provider docs (CLAUDE.md, GEMINI.md, AGENTS.md, WARP.md) for staleness after task execution. Also updates CHANGELOG.md and TASKS.md checklist.
dockerfileGenerate an optimized, secure, production-ready Dockerfile and docker-compose for a given application. Use when containerizing an app or improving an existing Dockerfile.
estimateEstimate task complexity and effort using T-shirt sizes and story points. Produces estimates with confidence levels and risk factors. Use when asked to estimate a task, story, or epic.
explain-codeExplains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?
frontend-reviewReview React/Next.js frontend code for correctness, accessibility, performance, design system adherence, and best practices. Produces a severity-tagged report. Use when reviewing frontend PRs or auditing existing components.
generate-rulesConverts a structured decisions document into .claude/rules/ files (frontend.md, backend.md, security.md, infra.md). Called by the rules-writer agent after architect or rules-lock interview completes.
git-history-restructureUse when auditing a repository's uncommitted or messy changes and restructuring them into clean, logical commits. Enforces zero AI co-author footers and groups related files by domain.
inspect-secretsSafely inspects sensitive config files (.env, docker-compose, Dockerfile, YAML, vault configs) and reports their structure without ever exposing secret values. Use when you need to understand what secrets/config a project uses without reading the actual values.
layout-designDesign a page layout or section layout using modern patterns (bento grid, dashboard, hero, magazine, masonry, etc.) for React/Next.js with Tailwind CSS. Produces complete, copy-paste JSX with layout rationale.
perf-auditAudit code or system design for performance issues. Identifies bottlenecks, N+1 queries, unnecessary re-renders, and algorithmic inefficiencies. Use when investigating slow code or reviewing for performance.
plan-featurePlan and scope a new feature with phases, acceptance criteria, and risk assessment. Use when a user describes a feature idea and wants a structured implementation plan.
refactorRefactor code for clarity, maintainability, and reduced complexity without changing behavior. Use when asked to clean up, restructure, or improve existing code.
save-outputPrompt the user to save the current agent output as a markdown spec file. Handles y/n prompt, target directory selection, filename generation, and file writing. Use at the end of any agent workflow.
security-auditAudit code for security vulnerabilities (OWASP Top 10, injection, auth issues, secrets exposure). Produces a severity-ranked findings report. Use when asked to security-review code, a PR, or a module.
session-planToken-aware session planning. Takes a list of goals/tasks and produces a prioritized TASKS.md checklist split across sessions based on estimated token usage and complexity.
write-docsWrite technical documentation — README, guides, runbooks, or onboarding docs. Produces clear, maintainable docs. Use when asked to document a feature, service, or process.
write-testsGenerate comprehensive test suites for a function, module, or API endpoint. Covers unit, integration, and edge cases. Use when asked to add tests to existing code.
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
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
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
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.