mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Spec → Context → Build → Test → Evaluate → Deploy workflow for agentic coding, for new and existing repos
Plugin ship-standards from marketplace jawad-plugins in Jawad606/standard-ship-plugins. Commands read from the repo's manifest — 19 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
engineering-standardsDefault engineering standards for building features — structure, TypeScript/NestJS/Next.js/Python practices, testing strategy, security and AI-feature practices. Use whenever writing or changing code in a repo that uses ship-standards, when scaffolding a new project, or when the user asks "what's th
init-standardsSet up the ship-standards workflow (specs, decision logs, tests, verification, CI) in a repository. Works in two modes — adopting an EXISTING codebase without overwriting its conventions, or bootstrapping a NEW project. Use when the user runs /init-standards, says "set up standards", "add the workfl
merge-critiqueExplain and critique a finished code change for the person who will review or merge it. Answers "why this approach?", "why does this file exist?", "why not X?", and flags weak spots honestly, with every claim backed by evidence from the repo, ticket, tests, or decision log. Use this whenever a codin
specWrite a structured feature spec (goal, user stories, acceptance criteria, scope, data and API changes) in the repo's specs folder before any code is written. Use when the user runs /spec, asks to "plan a feature", "write requirements", "spec this out", or asks to build a new feature in a repo using
verifyRun the project's quality gates (lint, typecheck, unit/integration tests, e2e, build) using the commands recorded in .ship-standards.json, and map results back to the spec's acceptance criteria. Use when the user runs /verify, before claiming any coding task is done, before running merge-critique, o
critique-reviewerFresh-context skeptical reviewer that challenges a finished change before merge. It reads the diff, spec, and decision log, and flags any claimed reason that has no evidence. Used by the merge-critique skill; can also be invoked directly. <example> Context: The coding agent just finished a feature a
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session-start.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/stop-check.sh"
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
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Use Alibaba Open Code Review from local Codex.
2 skills
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.