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
- 2026-11-13
- Stars
- ★ 21
- Forks
- 4
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 2
- 参考文档agents/openai.yaml137 B
- 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 inCONTEXT.mdand ADRs. (No working directory? Use/grill-meinstead, covered under 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: 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: kick off/implementper ticket,/clearing context between each one. Each ticket is self-contained, so the last one's context is disposable. - No →
/implementright here, in the same context window.
Either way,
/implementbuilds each issue by driving/tddinternally (one red-green slice at a time), then closes out by running/code-review, a two-axis review (Standards + Spec) of the diff, before committing. 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. - Yes →
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 then starts fresh, working from the ticket.
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/implementlater 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. 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 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/implementas 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-codebase-architectureruns 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 keepCONTEXT.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-codebase-architectureboth speak it.
Phase boundaries
A phase is a chunk of work inside a session: the grilling, the implementation, the QA. At the boundary between two of them you have five options, and picking between them is the fuzziest decision in this whole map:
- Continue: stay put. Costs nothing, loses nothing.
/clear: empty the window, when nothing here matters to what's next./handoffwrites a portable markdown file. Narrow: only for a new harness, a new directory, a colleague, or forking a side task mid-phase. What it buys is portability.- Subagent: send a tightly-scoped task to its own window and get a report back.
/compactcompresses this context and seeds a fresh session with it. The default, at the bottom of the tree rather than the first reach.
Read PHASE-BOUNDARIES.md for the ordered tree: the five questions, the reasoning behind each branch, and why the primary-source cost makes Continue the one to rule out first. Make the decision at a boundary; mid-phase, continue or split the rest into subagents.
Standalone
Off the main flow entirely.
/grill-me: the same relentless interview as/grill-with-docs, but stateless: it saves nothing locally and builds noCONTEXT.md. Reach for it when you are not working in a working directory (sharpening a plan, a design, a piece of writing, anything with no repo under it). If you are in a working directory, use/grill-with-docsinstead: it runs the same interview and leaves a paper trail, so it is strictly the better one./grillingis the interview primitive itself: rounds, the frontier, facts are the agent's job and decisions are yours./grill-meand/grill-with-docsare the two named ways in, and/triage,/wayfinderand/improve-codebase-architectureall run it internally. Reach for it directly only when you want the interview with no wrapper around it./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/grill-me: 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 theCONTEXT.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.
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
write-doc-file-content-file-sidechannel
write_doc_file 建档报目标路径已被手写文件占用/路由冲突时——走 content_file 临时文件侧通道:正文写临时文件→删占位文件→write_doc_file(content_file=...) 正式建档→删临时文件
windows-python-release
当要手动发布 Python 包(codewiki-plus)到 PyPI 并建 GitHub Release 时——CI 不发布、Windows 控制台为 GBK、可能无 gh CLI、本机网络对 upload.pypi.org 的 Python TLS 握手有干扰——先核对 tag 区间与工作区未提交改动定 bump 级别,再按 8 步主干执行:同步四处版本→bump 提交(只 add 具体文件)→聚焦+ruff+全量闸门→清 dist 构建→PR 合并 main→tag merge commit 建 Release→uv publish(TLS 超时则 curl.exe 直传)→PyPI JSON API 核对
windows-dev-env
Windows/PowerShell 下做 git 写操作、跑子进程或批量文件/测试清理时:shell 漂移与中文路径致命令静默失败、无控制台宿主子进程闪窗、GCM 每次弹 OAuth 框、原生 DLL 被锁——须显式复核落盘、subprocess 加 CREATE_NO_WINDOW、gh auth setup-git 持久化凭据,并用 cmd /c 绕 safe-delete 钩子
repowiki-conclusion-update
已落库 repowiki 结论发生变化时,按「结论方向 vs 表述」分流:方向变则新写 decision 笔记+reject_note 旧+confirm 并回源 ADR,仅表述/证据变则 edit_doc_file 原地改
maintain-fork-pr-merge
当合入 fork 来源的 PR 且 mergeStateStatus=CONFLICTING/DIRTY 时——先 git merge-tree 探测冲突清单,查 maintainer_can_modify,再在 worktree 隔离目录解冲突后 push fork 分支,勿因 CI 绿直接 merge
git-commit-hygiene
在共享 worktree 多会话并行或暂存区有残留时提交代码——用显式 pathspec 只提交自己的文件并排除临时目录,禁止 git add -A 或裸 commit 扫入并行会话的改动