Contact salesTry Claude

Matt Pocock's Skills

Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and...

A collection of 21 composable agent skills that embed real software engineering discipline into your AI-assisted workflow. Rather than vibe coding, these skills enforce structured practices: grilling sessions that stress-test your thinking before writing code, test-driven development with red-green-refactor loops, dual-axis code review (standards + spec compliance), domain modeling that builds a shared vocabulary, and spec/ticket generation that converts conversations into actionable work items.

The skills address four core failure modes when working with AI agents: misalignment (use grilling to clarify intent before building), verbosity (build domain language via CONTEXT.md and ADRs), non-functional code (TDD and structured debugging loops), and architectural decay (specs, architecture review, and codebase design skills).

How to use: Run /setup-matt-pocock-skills once per repo to configure issue tracking and documentation paths. Then use skills like /grill-me to stress-test a decision, /tdd for test-driven development, /to-spec to turn a conversation into a formal spec, /to-tickets to break plans into trackable tickets, /implement to build from specs with TDD, /code-review for dual-axis review, /domain-modeling to refine project terminology, /improve-codebase-architecture for architecture optimization, and /wayfinder to plan large multi-session work.

Other plugins

Frontend Design

Frontend design skill for UI/UX implementation

Superpowers

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

Code Review

Automated code review for pull requests using multiple specialized agents with confidence-based scoring

Context7

Upstash Context7 MCP server for up-to-date documentation lookup. Connects to Context7's hosted remote MCP server (https://mcp.context7.com/mcp) — no local Node.js or npx required — to pull version-specific documentation and code examples directly from source repositories into your LLM context. Authenticate with Context7 when prompted.

Code Simplifier

Agent that simplifies and refines code for clarity, consistency, and maintainability while preserving functionality

Playwright

Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.