ask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
tt-a1i · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add tt-a1i/matt-skills-with-to-goal --skill ask-matt技能说明
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 → ship
The route most work travels. You have an idea and want it built.
-
/grill-with-docs— sharpen the idea by interview. Start here whenever you are working in a working directory: it's stateful, retaining what it learns inCONTEXT.mdand ADRs. (No working directory? Use/grill-me— see Standalone. Both run the same/grillingprimitive;grill-with-docsis the one that leaves a paper trail, which makes it the better of the two whenever a repo is there to leave it in.) -
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 — how should implementation cross the context boundary?
- Small, already clear, no durable spec needed →
/implementright here, in the same context window. - The approved spec fits one execution session and this thread is coherent →
/to-spec, then run/execute-spec-in-forkin Codex App. It creates a same-directory fork, launches/spec-executor, routes decisions back here, validates the returned receipt, and archives a clean completion. Without Codex App task tools or Codex Task Messenger, fork manually from the finalSPEC READY, run/spec-executor, and paste its receipt back. - Multi-session, parallel, cross-agent, delayed, or context already noisy →
/to-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. Run/to-goalon the current frontier ticket and execute that goal in a clean session, regenerating from the next frontier after each slice. Use/to-goal --allonly for a persistent harness that must renew context across tickets.
Both
/implementand/spec-executordrive/tddinternally — one red-green slice at a time — then close out with/code-review, a two-axis review (Standards + Spec) of the diff, before committing./spec-executorpreserves the fork contract and receipt;/execute-spec-in-forkowns the Codex task lifecycle around it. Reach for/tddon its own when you just want to build a concrete behaviour test-first without a full spec, and/code-reviewon its own whenever you want to review a branch or PR against a fixed point. - Small, already clear, no durable spec needed →
Context hygiene
Keep steps 1–3 in one unbroken context window — don't compact or clear until the final SPEC READY, /to-tickets, or /to-goal boundary — so the grilling, spec, and tickets all build on the same thinking. Fork only from the final marker, never from a half-settled draft. Each execution session then starts from the ticket or the goal.
A fork isolates future conversation, not the filesystem. Parallel implementation threads still need separate worktrees, branches, and ownership boundaries. The fork also inherits a snapshot: later product changes in the planning thread must be sent to the executor explicitly. When the inherited history is already noisy or contradictory, prefer /to-goal, which compresses the approved evidence into a clean contract instead of carrying the mess forward.
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 SPEC READY or /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. Run/to-goalon the selected ready issue, then execute it in a fresh session — or pick it up with/implementdirectly when the context is already clean.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./to-goalconsumes either kind of ready ticket without repeating triage or re-interviewing you. -
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. Its post-mortem hands off to/improve-codebase-architecturewhen the real finding is that there's no good seam to lock the bug down. -
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