ask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
- License 许可
- MIT
- 最近更新
- 2026-11-04
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- ask-matt
- description
- Ask which skill or flow fits your situation. A router over the skills in this repo.
- disable-model-invocation
- true
02 资源文件 4
- 参考文档agents/openai.yaml137 B
- 参考文档CREDITS.md335 B
- 许可证LICENSE1.0 KB
- 参考文档PHASE-BOUNDARIES.md4.1 KB
03 SKILL.md 正文
Ask Matt
You don't remember every skill, so ask.
A flow is a path through the skills. Most paths run along one main flow, and two on-ramps merge onto it. Everything else is standalone, or a vocabulary layer that runs underneath.
The main flow: idea → ship
The route most work travels. You have an idea and want it built.
-
/grill-with-docssharpens the idea by interview. Start here whenever you are working in a working directory: it's stateful, retaining what it learns inGLOSSARY.mdand ADRs. (No working directory? Use/grilling, covered under Standalone.) -
Branch: can you settle every question in conversation? If a question needs a runnable answer (state, business logic, a UI you have to see), detour through a prototype, bridged by
/handoffin both directions (a prototype lives in its own directory, which is exactly what/handoffis for; see Phase boundaries):/handoffout, then open a fresh session against that file,/prototypeto answer the question with throwaway code,/handoffback what you learned, and reference it from the original idea thread.
-
Branch: is this a multi-session build?
- Yes →
/to-spec(turn the thread into a spec), then/to-ticketsto split it into tracer-bullet tickets, each declaring its blocking edges. On a local tracker that's one file per ticket under.scratch/<feature>/issues/, worked blockers-first by hand; on a real tracker the edges become native blocking links, so any ticket whose blockers are done can be grabbed. Each ticket then runs as three fresh sessions:/implement-ticket,/clear,/review-ticket,/clear,/deepen-ticket. Once the PRs have reviews,/address-reviewanswers one PR's threads and/merge-trainaddresses and merges a whole set. - No →
/implementright here, in the same context window: no tickets, one in-session build.
Every build drives
/tdd(one red-green slice at a time) and is reviewed by/adversarial-review, a two-axis review (Standards + Spec) run by the other model. Reach for/tddon its own when you just want to build a concrete behaviour test-first without a full spec, and/adversarial-reviewon its own whenever you want to review a branch or PR against a fixed point.When the work goes up as a pull request,
/prshapes the body: the smallest visual that shows the change, before/after evidence that it works, and a one-way or two-way door call. It's model-invoked, so the agent reaches for it whenever it writes a PR. - Yes →
-
/retrocloses the loop. After a build, and especially one that went sideways, it looks back over the session and suggests changes to the agent's environment, not the code: navigation pointers, automated checks, the coding standards/adversarial-reviewenforces, steering files, tooling. Mechanical mistakes become deterministic checks; judgement calls become coding standards. The next build then starts from a better environment.
Context hygiene
Keep steps 1–3 in one unbroken context window (don't compact or clear until after /to-tickets) so the grilling, spec, and tickets all build on the same thinking. Each /implement-ticket then starts fresh, working from the ticket. Run /retro in the session it's looking back on, before you clear; after clearing, point it at that session's log instead.
The limit on this is the smart zone: the window (~150k tokens on state-of-the-art models) within which the model still reasons sharply. If a session approaches it before /to-tickets, don't push on degraded; /compact at the nearest phase boundary and carry on (see Phase boundaries).
On-ramps
A starting situation that generates work, then merges onto the main flow.
-
Bugs and requests piling up →
/triage. It moves issues through triage roles and produces agent-ready issues, which/implement-ticketlater picks up.Triage is only for issues you didn't create: bug reports, incoming feature requests, anything that arrives raw. Tickets that
/to-ticketsproduced are already agent-ready, so don't triage them. -
Something's broken →
/diagnosing-bugs. For the hard ones: the bug that resists a first glance, the intermittent flake, the regression that crept in between two known-good states. It refuses to theorise until it has a tight feedback loop (one command that already goes red on this bug), then fixes with a regression test. Once the fix is in, run/retroin the same session to ask what would have prevented the bug; where the real finding is that there's no good seam to lock it down, take that to/improve-codebase. -
A huge, foggy effort: a greenfield project or a huge feature build, too big for one session →
/wayfinder, the most cognitively demanding flow here. When the way from here to the destination isn't visible yet, it charts a shared map of decision tickets on the issue tracker and resolves them one at a time, producing decisions, not deliverables, until the fog is pushed back and the way is clear. Where/grill-with-docssharpens an idea you can hold in one session, wayfinder is for the idea you can't, and it's slower and denser, so save it for exactly that, never a well-scoped feature.When the map clears, it hands off, it doesn't build: merge onto the main flow at
/to-spec, which collapses the map's linked decisions into a buildable plan, then/to-ticketsand the per-ticket sessions as usual. Looping the map straight into/implementskips that collapse and throws the linked detail away, so go straight to/implementonly when the effort turned out genuinely small.
Codebase health
Not feature work, just upkeep.
/improve-codebaseruns whenever you have a spare moment to keep the codebase good for agents to operate in. It surfaces deepening opportunities; picking one generates an idea you can take into the main flow at/grill-with-docs. It's the survey that finds the candidates;/codebase-design(below) is the bench you design the chosen one on.
Vocabulary underneath
Two model-invoked references that run beneath the other skills, each the single source of truth for its vocabulary. Reach for them directly when the words, not the process, are the problem; or let the skills above pull them in.
/domain-modeling: sharpen the project's domain language: challenge a fuzzy term, resolve an overloaded word ("account" doing three jobs), record a hard-to-reverse decision as an ADR. It's the active discipline/grill-with-docsdrives to keepGLOSSARY.mda clean glossary./codebase-designis the deep-module vocabulary (module, interface, depth, seam, adapter, leverage, locality) for designing a module's shape: a lot of behaviour behind a small interface at a clean seam./tddand/improve-codebaseboth speak it.
Phase boundaries
At the boundary between two phases (continue, /clear, /handoff, subagent or /compact?), read PHASE-BOUNDARIES.md for the ordered tree.
Standalone
Off the main flow entirely.
/grillingis the relentless interview itself: rounds, the frontier, facts are the agent's job and decisions are yours. It is stateless: reach for it when you are not working in a working directory (sharpening a plan, a design, a piece of writing). Inside a repo,/grill-with-docsruns the same interview and leaves a paper trail./triage,/wayfinderand/improve-codebaseall run it internally./resolving-merge-conflictsworks an in-progress merge or rebase conflict hunk by hunk, resolving by intent traced to each side's primary source rather than by picking lines, then finishes the operation. It never runs--abort. Standalone and off every flow: reach for it when you are already mid-conflict./prototypeis a small, throwaway program that answers one design question: does this state model feel right, or what should this UI look like. Throwaway is a constraint on how the code is written, not a promise to destroy it: the answer folds into the real code, and the prototype itself is kept as a primary source on aprototype/<name>branch out of main, pointed at from the implementation issue. It's the detour in step 2 of the main flow, but reach for it any time a design question is hard to settle on paper./research: delegate reading legwork to a background agent: it investigates a question against primary sources, then leaves a cited Markdown file in the repo. Keep working while it reads. The file it produces is something to take into the main flow at/grill-with-docs, since research feeds the thinking rather than replacing it./to-questionnairecomes in when the thing blocking you isn't in your head or the codebase but in someone else's, and it writes them a questionnaire to fill in. It's the inverse of/grilling: instead of interviewing you about the subject, it interviews you about the send (who it's going to, what you need back) and aims the questions at the gap. What comes back is material for/grill-with-docsor/to-spec./wizardis for the steps only a human can take: provisioning infrastructure, setting up credentials or CI secrets, clicking through an unfamiliar third-party dashboard, running a one-off migration or cutover. It generates an interactive bash script that opens each URL, captures each value, and writes it into.envand GitHub secrets, so the procedure stops being something you re-explain to an agent every time. Model-invoked, so the agent reaches for it the moment it hits a wall only you can pass. If the agent could just do it itself, it should; this is for where a human is genuinely in the loop./wait-whatis the corrective for a message that didn't land. Use it mid-conversation, inside any other skill, and the agent re-pitches what it just said with the context you were missing, in plain English, using theGLOSSARY.mdvocabulary. It works after the fact;/grill-with-docsis the upfront cure, because a shared language agreed early is what stops the jargon arriving at all./teach: learn a concept over multiple sessions, using the current directory as a stateful workspace./writing-for-agentsis the reference for writing documents agents consume: skills, AGENTS.md, pointed-at docs./to-blueprintturns a finished grilling session into a visual, forever design doc for one feature./pr-walkthroughwalks a PR or branch visually: what changed, how the code flows now, what it impacts./client-replydrafts a reply to a client, partner, or CS colleague from findings already in hand.
Precondition
/setup-matt-pocock-skills: run before your first engineering flow to configure the issue tracker, triage labels, and doc layout the other skills assume. Custom issue trackers also work.
04 同仓库更多 Skills
explainroo
Make an explainer video (MP4) with a voice-over using explainroo. The voice is made on this computer and no API key is needed. Use when the user asks for an explainer, how-to, walkthrough, launch or tutorial video, an animated diagram with a voice-over, or a short for YouTube, Reels or TikTok.
unslop
Cut AI tells from prose a human will read. Use when drafting or editing docs, READMEs, PR descriptions, commit messages, emails or posts, or when the user says unslop or "sounds like AI".
technical-writing
Layered technical-writing standard (Diátaxis, Google style, STE, Global English) for docs, RFCs, READMEs, PR descriptions and commit messages.
no-comments
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
ponytail
Lazy senior dev mode: the smallest change that fully solves the task, and a reply a busy human understands in one read. Use on any coding task (writing, fixing, refactoring, reviewing, choosing dependencies) and when the user says "ponytail", "be lazy", "simplest solution", "yagni", or complains about over-engineering or bloat. Levels: lite, full (default), ultra.
ponytail-review
Quality review of a change: is the logic right, is it safe, does it hold under real load, is risky code tested, is it fast enough, and is every line needed. Reads the connected code, not only the diff. Each finding is explained in plain English. Use for "review this", "code review", "review the last commit", "review my PR", "is this over-engineered", /ponytail-review.