curl -fsSL https://api.cheatcodehq.com/install.sh | sh -s -- mattpocock-skills --to allCopies 35 skills into each app's skills folder (Claude Code: ~/.claude/skills), after checking every file against mattpocock/skills at commit c55ee46. Nothing else on your computer changes. To undo it, run the terminal command with --uninstall at the end; that also removes what the app added.
Then start a new session in your AI app and ask for the work in plain words; it picks the skill from its description. In Claude Code you can also type /mattpocock-skills:ask-matt.
See it in use
After installing, start a new session and say: Our AI assistant reads instructions.md but keeps behaving differently. Rewrite it so it works better, save it as instructions.new.md, and tell me what I need to decide.
What else it can do, and its limits
- 35 skills from one engineer's own setup, most for software teams: test first coding, bug diagnosis, code review, architecture and prototypes
- Planning: an interview that grills a plan or idea, specs, tickets on an issue tracker, questionnaires for others and handoff notes
- Writing: instructions for AI agents and skills, pull request text, and an article from raw notes in three passes
- 21 skills start only when you type their name; several set up git hooks or tools and need a terminal
- Research and tracker skills need the web or a connected issue tracker
Sample input Recorded Oct 24, 2026 in Claude Code 2.1.308 with Sonnet 5.5. The video replays that session; nothing in it was acted or edited.
What's inside 35 skills
ask-mattAsk which skill or flow fits your situation. A router over the skills in this repo.
Ask which skill or flow fits your situation. A router over the skills in this repo.
claude-handoffHand the current conversation off to a fresh background agent that picks up the work immediately.
Hand the current conversation off to a fresh background agent that picks up the work immediately.
code-reviewReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".
codebase-designShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugsDiagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
domain-modelingBuild and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.
git-guardrails-claude-codeSet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
grill-meA relentless interview to sharpen a plan or design.
A relentless interview to sharpen a plan or design.
Show all 35 skills
grill-with-docsA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
grillingGrill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
handoffCompact the current conversation into a handoff document for another agent to pick up.
Compact the current conversation into a handoff document for another agent to pick up.
implementImplement a piece of work based on a spec or set of tickets.
Implement a piece of work based on a spec or set of tickets.
implement-specImplement a specification in code.
Implement a specification in code.
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
loop-meGrill me about specs for the workflows I want to build, within this workspace.
Grill me about specs for the workflows I want to build, within this workspace.
prUse when writing a PR body.
Use when writing a PR body.
prototypeBuild a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
researchInvestigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
resolving-merge-conflictsUse when you need to resolve an in-progress git merge/rebase conflict.
Use when you need to resolve an in-progress git merge/rebase conflict.
setup-matt-pocock-skillsConfigure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
setup-pre-commitSet up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
setup-ts-deep-modulesWire dependency-cruiser into a TypeScript repo so each package is a deep module, with implementation hidden in subfolders and reachable only through its entry-point files. User-invoked.
Wire dependency-cruiser into a TypeScript repo so each package is a deep module, with implementation hidden in subfolders and reachable only through its entry-point files. User-invoked.
tddTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
teachTeach the user a new skill or concept, within this workspace.
Teach the user a new skill or concept, within this workspace.
to-questionnaireTurn a decision you can't fully answer into a questionnaire for someone else to fill in.
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
to-specTurn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.
Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.
to-ticketsBreak a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).
triageMove issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.
wait-whatStop. That last message did not land: re-pitch it.
Stop. That last message did not land: re-pitch it.
wayfinderPlan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
wizardGenerate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
writing-beatsWriting, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.
Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.
writing-for-agentsWriting documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
writing-fragmentsWriting, explore: mine raw fragments, no structure yet.
Writing, explore: mine raw fragments, no structure yet.
writing-shapeWriting, exploit: shape raw material into an article, paragraph by paragraph.
Writing, exploit: shape raw material into an article, paragraph by paragraph.
About
Skills for Real Engineers. Straight from my .agents directory. Nine skills come from the author's in-progress folder, which the author calls beta and may change or remove.
Something wrong with this listing, or it did not install? Tell us