mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core plugins for working with Claude Code
Plugin core from marketplace tricky-cc-plugins in trickycdm/tricky-cc-plugins. Commands read from the repo's manifest — 1 month 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.
a11y-auditAudit TSX files for WCAG 2.1 AA accessibility compliance. Reports findings by severity with WCAG references and code fixes. Use when the user says 'a11y audit', 'accessibility check', 'check accessibility', 'WCAG audit', 'is this accessible', 'audit for screen readers', or asks about accessibility o
gen-changelogGenerate a changelog from git history. Compares tags, branches, or commits to produce a categorized, human-readable changelog. Handles multiple scenarios: what's unreleased on HEAD vs latest tag, tag-to-tag comparisons, staging/RC vs production, or any custom git range. Invoke with /gen-changelog or
github-project-ticketsCreate and manage GitHub Project issues retrospectively using the GitHub CLI (gh). Use this skill whenever the user wants to push completed work to a GitHub Project board, create issues from git commit history, generate tickets from documentation or specs, add done work to a GitHub project after the
learnSelf-improving loop for the project's institutional knowledge. This project maintains a structured knowledge system — a root CLAUDE.md that indexes standards docs (error handling, database, security, accessibility, etc.), directory-level CLAUDE.md files for each module, and dedicated docs for cross-
optimize-docOptimize documentation for conciseness and clarity. Strengthens vague instructions with explicit criteria, removes redundancy while preserving meaning, and tightens prose. Use when the user says 'optimize this doc', 'tighten this', 'make this more concise', 'clean up this documentation', 'this doc i
playwright-cliAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
product-lensProduct thinking before building. Use when the user says 'product lens', 'is this worth building', 'write a spec', 'scope this', 'prioritize features', 'review the UX', 'what should we build', 'cut scope', 'too much scope', 'feature creep', 'convert this idea into a spec', 'what's the MVP', or asks
wrap-upClose out plan execution. Finalizes the plan, captures lessons, and produces a clean artifact. Use when the user says 'wrap up', 'we're done', 'finish up', 'close this out', 'wrap-up', or after completing all plan steps.
wt-mergeSquash-merge a worktree branch's PR, clean up the worktree, update main, and report status. Use when done with a worktree — after a subagent finishes, when the user says 'merge worktree', 'merge this branch', 'clean up worktree', 'wt merge', 'done with this worktree', or 'merge and clean up'. Also t
/core:a11y-auditAudit TSX files for WCAG 2.1 AA accessibility compliance.
/core:commitGit commit all changes and update docs
/core:gen-changelogCreate a changelog by comparing git refs.
/core:optimize-docOptimize documentation for conciseness and clarity.
/core:plan-statusShow status of all active plans
/core:product-lensProduct thinking before building.
/core:pw-testExploratory testing with Playwright, then write E2E tests
/core:reviewreview the changes just made
/core:warpCreate a copy pasteable summary of the current session designed to allow you to /clear and bootstrap a new session with all the relevant context.
/core:wrap-upClose out plan execution and capture lessons.
/core:wt-mergeSquash-merge a worktree branch's PR and clean up.
claude-md-generatorUse this agent when you need to create or update CLAUDE.md files for projects or specific subfolders. This agent should be used when: 1) Starting a new project that needs development guidelines, 2) Adding Claude-specific instructions to an existing codebase, 3) Creating subfolder-specific CLAUDE.md
code-explorerDeeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development
code-reviewerReviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter
documentation-generatorUse this agent to produce or refine concise architectural documentation (300-500 lines) for a project or module. Detects the host's doc convention (CLAUDE.md / AGENTS.md / OVERVIEW.md / ARCHITECTURE.md / `docs/`) and updates existing files in place when present. Does **not** write into a `steering/`
feature-creatorUse this agent when you need to document a feature implementation from the current session into a reusable playbook. This agent should be called after significant progress has been made on a feature and you want to capture the implementation details, context, and references for future sessions.
security-reviewerSecurity vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
tech-debt-reviewerUse this agent when you need to analyze code quality and identify technical debt across systems, services, or specific files. This agent systematically reviews code for maintainability issues, outdated patterns, performance bottlenecks, security concerns, and architectural problems, then documents f
test-generatorUse this agent to generate high-quality TypeScript unit tests for a target file or directory. Detects the host project's test runner (Jest, Vitest, node:test) and follows the project's documented testing standards.
${CLAUDE_PLUGIN_ROOT}/scripts/rename-plan.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
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
8 skills · 1 MCP server
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.
2 commands
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.