| name | ask-matt |
| description | Ask which skill or flow fits your situation. A router over the skills in this repo. |
| disable-model-invocation | true |
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 โ ship
The route most work travels. You have an idea and want it built.
-
/grill-with-docs โ sharpen the idea by interview. Start here when you have a codebase: it's stateful, retaining what it learns in CONTEXT.md and ADRs. (No codebase? Use /grill-me โ see Standalone. Both run the same /grilling primitive; grill-with-docs is the one that leaves a paper trail.)
-
Branch โ 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 /handoff in both directions (see Crossing sessions):
/handoff out, then open a fresh session against that file,
/prototype to answer the question with throwaway code,
/handoff back what you learned, and reference it from the original idea thread.
-
Branch โ is this a multi-session build?
- Yes โ
/to-spec (turn the thread into a spec), then /to-tickets to 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. Run /to-goal for the current frontier ticket, then open a fresh session and kick off /implement (or paste the goal into a goal loop). Clear context between tickets and regenerate the goal from the new frontier each time. Use /to-goal --all only for a persistent harness that can renew context across tickets.
- No โ
/implement right here, in the same context window.
Either way, /implement builds each issue by driving /tdd internally โ one red-green slice at a time โ then closes out by running /code-review, a two-axis review (Standards + Spec) of the diff, before committing. Reach for /tdd on its own when you just want to build a concrete behaviour test-first without a full spec, and /code-review on its own whenever you want to review a branch or PR against a fixed point.
Context hygiene
Keep steps 1โ3 in one unbroken context window โ don't compact or clear until after /to-tickets and /to-goal โ so the grilling, spec, tickets, and execution goal build on the same thinking. Each /implement then starts fresh, working from the ticket-scoped goal.
The limit on this is the smart zone: the window (~120k 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 โ /handoff and continue in a fresh thread.
On-ramps
A starting situation that generates work, then merges onto the main flow.
-
Bugs and requests piling up โ /triage. It moves issues through triage roles and produces agent-ready issues. Run /to-goal on the selected ready issue, then start /implement in a fresh session.
Triage is only for issues you didn't create โ bug reports, incoming feature requests, anything that arrives raw. Tickets that /to-tickets produced are already agent-ready, so don't triage them. /to-goal consumes either kind of ready ticket without repeating triage or interviewing the user.
-
Something's broken โ /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 โ one command that already goes red on this bug โ then fixes with a regression test. Its post-mortem hands off to /improve-codebase-architecture when the real finding is that there's no good seam to lock the bug down.
-
A huge, foggy effort โ a greenfield project or a huge feature build, too big for one session โ /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 โ producing decisions, not deliverables โ until the fog is pushed back and the way is clear. Where /grill-with-docs sharpens an idea you can hold in one session, wayfinder is for the idea you can't โ 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-tickets, /to-goal, and a fresh /implement as usual. Looping the map straight into /implement skips that collapse and throws the linked detail away โ go straight to /implement only when the effort turned out genuinely small.
Codebase health
Not feature work โ upkeep.
/improve-codebase-architecture โ run 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 โ 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 โ 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-docs drives to keep CONTEXT.md a clean glossary.
/codebase-design โ 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. /tdd and /improve-codebase-architecture both speak it.
Crossing sessions
/handoff โ when a thread is full or you need to branch off (e.g. into a /prototype session), this compacts the conversation into a markdown file. You don't continue in place โ you open a new session and reference that file to carry the context across. It's the bridge between context windows, in either direction. Use it when you want a fresh session but need the current conversation preserved.
/compact (built-in) โ stay in the same conversation, letting the earlier turns be summarized. Use it at intentional breaks between phases, when you don't mind losing the verbatim history. Don't compact mid-phase โ the agent can lose its way. /handoff forks; /compact continues.
Standalone
Off the main flow entirely.
/grill-me โ the same relentless interview as /grill-with-docs, but for when you have no codebase. Stateless: it saves nothing locally, builds no CONTEXT.md. Reach for it to sharpen any plan or design that doesn't live in a repo.
/prototype โ a small, throwaway program that answers one design question: does this state model feel right, or what should this UI look like. Throwaway from day one โ keep the answer, delete the code. 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 โ 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 โ research feeds the thinking, it doesn't replace it.
/to-goal โ compile an agent-ready ticket or frontier into a verifiable execution goal for a fresh implementation session. Use after /to-tickets or /triage, not as a planning interview.
/teach โ learn a concept over multiple sessions, using the current directory as a stateful workspace.
/writing-great-skills โ reference for writing and editing skills well.
Precondition
/setup-matt-pocock-skills โ 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.