mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
A collection of software-engineering skills for Claude Code — code review, spec-driven implementation, bug diagnosis, domain modeling, and more. Based on Matt Pocock's skills (https://github.com/mattpocock/skills).
Plugin skills from marketplace mvdmio in michielvandermeer/skills. Commands read from the repo's manifest — 3 days ago.
verifyDrive this checkout's skills the way a user does — load the working tree as the plugin in a headless Claude Code session inside a scratch repo, type the slash commands and answers, and capture what the skill did. Use to prove a skill or agent edit behaves before it is committed or pushed, or when as
brainstormExplore a vague problem as very different Directions, side by side, and file the ones you keep as Issues.
code-reviewReview changes since a commit, branch, or tag against the coding standards and the Spec. Use when the user wants a branch, a PR, or work in progress reviewed.
doctorMoves documents into this project's canonical layout, closes local Issues the code already implements, brings every ADR to state the decision in force, trims oversized Coding standards to one short line per rule, and cleans repeats, dead paths, and contradictions out of Steering files.
domain-modelingBuild and sharpen a project's domain model, its glossary and ADRs. A Library skill other skills read by path.
explainExplain anything as a written walkthrough, a diagram in the chat, an HTML page, or a narrated video, picking the format that fits.
grill-with-docsA relentless round-by-round interview to sharpen a plan or design, which also creates docs (ADRs and glossary) as we go.
grillingGrill the user relentlessly about a plan or design, round by round. A Library skill other skills read by path.
hillclimbHillclimb one measured number — test-suite time, build time, memory, bundle size — keeping only the changes that measurably help. Use when the user wants something made faster, smaller, or cheaper, as far as it will go or past a target.
hunt-codebase-improvementsHunt your codebase for improvements along eight axes, such as state bugs, cruft, slow pages, and wasted CI time, then triage what the hunt finds into Issues.
implementImplement a spec by slicing it into steps, then a loop of implement, review, and verify, each in its own sub-agent. Use only when the user or a /goal names /implement.
learn-habitsRebuild a person's Grilling profile from the Habits in their past grilling sessions.
prPull request descriptions. Use when writing the description of a pull request or merge request.
prototypeBuild a throwaway prototype to answer a design question, then turn the answer into a Spec. 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.
resolving-merge-conflictsResolve git merge or rebase conflicts. Use when the user asks to merge or rebase and resolve the conflicts, or when a merge or rebase stops on a conflict.
retroRead a window of past sessions, apply high-priority changes this repository owns for lessons that repeat, file the structural ones as Issues, and summarise the rest.
setupSet up or update the repo's Tracker ref, where its Issues live; its Verify skill, which drives the app the way a user does; or its Models ref, the model and effort each plugin agent runs at.
simulate-first-usersSend five simulated first-time users through your app in real browsers, then triage what tripped them up into Issues with screenshots.
technical-writingThe house standard for every sentence a person reads. A Library skill other skills read by path.
to-specTurn the current conversation into a Spec and write it onto its Issue in the repo's Tracker — no interview, just synthesis of what you've already discussed.
triageSort incoming reports into Specs and parked Issues — one Issue per distinct problem.
validate-specValidate an Issue, a Spec, a plan, or the current conversation against this repo's own template rules and the current codebase — fix stale references and contradictions in place, flag real decisions as open questions.
wayfinderPlan a change too big for one agent session as a shared map of decision tickets in the repo's Tracker, resolved one at a time until the way is clear and its Specs can be written.
what-did-i-get-doneSummarise what you got done over a period, from your commits, pull requests, and Issues in this repo.
whyTrace why code is the way it is, with every claim cited. Use for "why does X work this way", why a choice was made, a regression's origin, or before changing code that looks deliberate.
writing-for-agentsWriting documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
climberWrites one Attempt of a /hillclimb run — a single idea, left uncommitted for the driving session to measure. Dispatched explicitly by /hillclimb — it works to a contract decided before it starts, so it is not a general coding agent.
cold-readerReads the Spec draft /to-spec has just written with nothing else and explains it back, naming each place it had to guess. Dispatched explicitly by /to-spec — it works to a contract decided before it starts, so it is not a general coding agent.
explorerWalks a codebase read-only and reports what it finds, without changing anything.
implementerImplements one Step of a Spec, or fixes what the last review or verify found, during an /implement run. Dispatched explicitly by /implement — it works to a contract decided before it starts, so it is not a general coding agent.
plannerSlices a Spec into Step files at the start of an /implement run, commits them, and returns only the compact index. Dispatched explicitly by /implement — it works to a contract decided before it starts, so it is not a general coding agent.
researcherInvestigates one question against primary sources and writes the findings to a Markdown file. Dispatched by /research to run in the background while the main session keeps working.
reviewerReviews the changes since a fixed point along one axis — Standards or Spec — and reports findings without fixing them. Dispatched explicitly by /code-review — it works to a contract decided before it starts, so it is not a general coding agent.
validatorChecks the Spec draft /to-spec has just written — corrects facts in the draft file and returns the report. Dispatched explicitly by /to-spec — it works to a contract decided before it starts, so it is not a general coding agent.
verifierVerifies one Iteration of an /implement run — checks the change against the Spec, runs the build and the whole test suite, runs the Spec's Hand checks, and measures its Stop rules. Dispatched explicitly by /implement — it works to a contract decided before it starts, so it is not a general coding ag
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
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
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
Claude Skills for Obsidian
6 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.