mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Subagents, slash commands, and workflow skills for Claude Code: a planner/engineer/debugger/reviewer team plus commands for commits, branches, worktrees, and PR shepherding.
Plugin team from marketplace claude-agent-team in andymai/claude-agent-team. Commands read from the repo's manifest — 4 days ago.
outward-writingWrite outward-facing prose another person will read: a design or shaping doc, a proposal, a wiki page, a Slack message, a PR title, body, or reply, a review reply, an issue or ticket, an email. You collect every fact with a source, write the draft in ASD-STE100 Simplified Technical English, fact-che
shepherd-prDrive the current branch's pull request to a fully clean state — every review comment resolved, every check-run green (including neutral-status reviewers that the CI rollup hides), and CI passing — running as an autonomous loop, then hand the PR back. Use when the user says "shepherd the PR", "drive
/team:audit-claudemdAudit or bootstrap the project's CLAUDE.md against observed conventions
/team:branchCreate a branch following <type>/<kebab-description> naming
/team:checkRun the project's local quality gate (fmt + lint + types + tests)
/team:commitCreate a conventional commit from working tree changes
/team:contribution-reportGitHub contribution summaries for performance reviews
/team:pr-descriptionGenerate a PR title and description from branch changes
/team:upgrade-depUpgrade a dependency and fix breaking changes
/team:worktreeSet up a git worktree under .worktrees/ for parallel branch work
architectAudits architectural integrity — layer boundaries, dependency directions, module coupling, and circular references. Use when a project has documented layering (CLAUDE.md tables, boundary scripts, ESLint no-restricted-imports) or when you suspect cross-layer leakage.
context-auditorAudits markdown documentation for token efficiency. Identifies bloated files, redundancy across docs, and verbosity that wastes context window. Use after creating or modifying documentation.
debuggerSystematically investigates bugs by reproducing, isolating, and root-causing issues, then writing verified fixes. Use when something is broken and you need to find out why.
documenterCreates and maintains documentation — API docs, architecture diagrams, READMEs, changelogs, and onboarding guides. Reads existing docs to match style and fills gaps rather than starting from scratch.
engineerImplements features by deeply understanding existing codebase patterns and conventions, then writing clean code that integrates seamlessly with the established architecture
gap-finderFinds missing pieces — either by comparing implementation against a spec, or by analyzing the diff for orphaned references, broken patterns, and incomplete state flows. Use after engineering work and before code review.
optimizerSimplifies and refines recently modified code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recent changes unless instructed otherwise. Makes confident, high-impact improvements without over-engineering.
plannerDesigns implementation plans by analyzing existing architecture, identifying risks, and breaking work into ordered tasks. Produces plans, not code. Use before complex feature work.
researcherConducts deep technical research by exploring codebases, tracing patterns, comparing technologies, and synthesizing findings from documentation and the web into actionable insights with cited sources
reviewerReviews code for bugs, logic errors, security vulnerabilities, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter
securityAudits code for security vulnerabilities including OWASP Top 10, auth/authz issues, secrets exposure, and dependency risks. Reports findings with severity ratings. Use before shipping to production.
testerWrites focused unit tests for new functionality by studying existing test patterns and targeting core business logic, edge cases, and error handling rather than trivial 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
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · 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
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 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.