ask-matt
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseAsk Matt
Ask Matt
你不需要记住每个 skill,所以直接问。
Flow 是穿过 skills 的一条路径。大多数路径沿着一条 main flow 前进,两个 on-ramps 会并入它。其他内容要么是 standalone,要么是在下层运行的 vocabulary layer。
You don't need to remember every skill, so just ask.
Flow is a path through skills. Most paths follow a main flow, with two on-ramps merging into it. Other content is either standalone or a vocabulary layer running underneath.
The main flow: idea -> ship
The main flow: idea -> ship
这是大多数工作的路线:你有一个想法,并希望把它构建出来。
-
- 通过访谈打磨想法。有 codebase 时从这里开始:它是 stateful 的,会把学到的内容保存在
/grill-with-docs和 ADRs 中。(没有 codebase?用CONTEXT.md,见 Standalone。两者都运行同一个/grill-meprimitive;/grilling是会留下文档痕迹的版本。)grill-with-docs -
分支 - 能否在对话中解决所有问题? 如果某个问题需要可运行的答案(state、business logic,或必须亲眼看到的 UI),就通过 prototype 绕行,并用在两个方向桥接(见 Crossing sessions):
/handoff- 导出,然后基于该文件打开 fresh session;
/handoff - 用 throwaway code 回答问题;
/prototype - 把学到的内容带回来,并在原始 idea thread 中引用它。
/handoff
-
分支 - 这是 multi-session build 吗?
- 是 -> (把 thread 变成 PRD)->
/to-prd(把 PRD 拆成可独立领取的 issues)。因为 issues 彼此独立,每个 issue 之间都要清空 context:每个 issue 启动一个 fresh session,把 PRD 和单个 issue 传给/to-issues。/implement - 否 -> 在当前 context window 里直接运行 。
/implement
无论哪种方式,都会在内部驱动/implement构建每个 issue:一次一个 red-green slice;然后用/tdd收尾,对 diff 做 Standards + Spec 双轴 review,再提交。只想 test-first 构建一个具体 behavior 时,单独用/code-review;想按固定点 review branch 或 PR 时,单独用/tdd。/code-review - 是 ->
This is the route for most work: you have an idea and want to build it out.
-
- Refine ideas through interviews. Start here when there's a codebase: it's stateful and saves what's learned in
/grill-with-docsand ADRs. (No codebase? UseCONTEXT.md, see Standalone. Both run the same/grill-meprimitive;/grillingis the version that leaves documentation traces.)/grill-with-docs -
Branch - Can all issues be resolved in the conversation? If a problem requires a runnable answer (state, business logic, or UI that must be seen firsthand), detour via prototype and bridge both directions with(see Crossing sessions):
/handoff- Export, then open a fresh session based on that file;
/handoff - Answer the question with throwaway code;
/prototype - Bring back what's learned and reference it in the original idea thread.
/handoff
-
Branch - Is this a multi-session build?
- Yes -> (turn the thread into a PRD) ->
/to-prd(break the PRD into independently assignable issues). Since issues are independent, clear context between each issue: start a fresh session for each issue, pass the PRD and single issue to/to-issues./implement - No -> Run directly in the current context window.
/implement
Either way,internally drives/implementto build each issue: one red-green slice at a time; then wrap up with/tdd, conducting a dual-axis review of Standards + Spec on the diff before submitting. Use/code-reviewalone when you want to build a specific behavior test-first; use/tddalone when you want to review a branch or PR at a fixed point./code-review - Yes ->
Context hygiene
Context Hygiene
步骤 1 到 要留在 同一个未中断的 context window 中;不要 compact 或 clear,这样 grilling、PRD 和 issues 才能建立在同一组思考之上。之后每个 都从 fresh session 开始,只基于对应 issue 工作。
/to-issues/implement限制来自 smart zone:在该窗口(最新模型大约 120k tokens)内,模型还能保持敏锐推理。如果 session 在 前接近这个区间,不要硬撑降级状态;用 ,然后在 fresh thread 中继续。
/to-issues/handoffSteps 1 through must stay in the same uninterrupted context window; do not compact or clear it, so that grilling, PRD, and issues can build on the same set of thinking. Each subsequent starts with a fresh session, working only based on the corresponding issue.
/to-issues/implementThe limitation comes from the smart zone: within this window (approximately 120k tokens for the latest models), the model can still maintain sharp reasoning. If the session approaches this limit before , don't push through with degraded performance; use and continue in a fresh thread.
/to-issues/handoffOn-ramps
On-ramps
起点会生成工作,然后并入 main flow。
-
Bugs 和 requests 堆积 ->。它通过 triage roles 推进 issues,并产出 agent-ready issues,之后由
/triage领取。/implementTriage 只用于 不是你创建的 issues:bug reports、incoming feature requests,以及任何原始进入的内容。产出的 issues 已经是 agent-ready,不要再 triage。/to-issues -
Something's broken ->。用于难处理的问题:第一眼看不出的 bug、间歇性 flake、夹在两个 known-good states 之间的 regression。它在拥有 tight feedback loop 前拒绝空想,也就是一个已经能在 这个 bug 上变红的命令;然后用 regression test 修复。如果复盘发现真正问题是没有好 seam 能锁住 bug,它会把后续交给
/diagnosing-bugs。/improve-codebase-architecture
Starting points generate work and then merge into the main flow.
-
Bugs and requests are piling up ->. It advances issues through triage roles and produces agent-ready issues, which are then picked up by
/triage./implementTriage is only used for issues not created by you: bug reports, incoming feature requests, and any content that comes in originally. Issues produced byare already agent-ready, so don't triage them again./to-issues -
Something's broken ->. For tough problems: bugs not obvious at first glance, intermittent flakes, regressions stuck between two known-good states. It rejects speculation until it has a tight feedback loop, i.e., a command that already turns red for this bug; then fixes it with a regression test. If a retrospective finds the real issue is the lack of a good seam to lock the bug, it hands off follow-up to
/diagnosing-bugs./improve-codebase-architecture
Codebase health
Codebase health
这不是 feature work,而是维护。
- - 有空时运行,保持 codebase 适合 agents 操作。它会暴露 deepening opportunities;选择其中一个会生成一个 idea,可以带入 main flow 的
/improve-codebase-architecture。它负责找候选项;/grill-with-docs(见下文)是你设计已选候选项时使用的工作台。/codebase-design
This is not feature work, but maintenance.
- - Run when you have time to keep the codebase suitable for agent operation. It exposes deepening opportunities; choosing one generates an idea that can be brought into
/improve-codebase-architecturein the main flow. It is responsible for finding candidates;/grill-with-docs(see below) is the workbench you use when designing the selected candidates./codebase-design
Vocabulary underneath
Vocabulary underneath
两个 model-invoked references 在其他 skills 下层运行,分别是自己词汇的 single source of truth。问题在于词语而不是流程时直接用它们;也可以让上面的 skills 自动拉起它们。
- - 打磨项目的 domain language:挑战模糊术语、解决 overloaded word(例如一个 "account" 承担三件事)、把难以逆转的决策记录为 ADR。它是
/domain-modeling用来保持/grill-with-docsglossary 干净的主动纪律。CONTEXT.md - - deep-module vocabulary(module、interface、depth、seam、adapter、leverage、locality),用于设计 module 的 shape:把大量 behavior 放在 clean seam 上的小 interface 后面。
/codebase-design和/tdd都使用这套语言。/improve-codebase-architecture
Two model-invoked references run underneath other skills, each being the single source of truth for their own vocabulary. Use them directly when the problem is about words rather than processes; you can also let the above skills pull them up automatically.
- - Refine the project's domain language: challenge vague terms, resolve overloaded words (e.g., an "account" taking on three roles), and record irreversible decisions as ADRs. It is the active discipline used by
/domain-modelingto keep the/grill-with-docsglossary clean.CONTEXT.md - - Deep-module vocabulary (module, interface, depth, seam, adapter, leverage, locality) for designing the shape of modules: placing large amounts of behavior behind small interfaces on clean seams. Both
/codebase-designand/tdduse this set of language./improve-codebase-architecture
Crossing sessions
Crossing sessions
- - 当 thread 快满,或需要分支到另一个 session(例如
/handoffsession)时,把对话压缩成 markdown 文件。你不会在原地继续,而是 打开新 session 并引用该文件 来带过 context。它是 context windows 之间的桥,两个方向都能用。想要 fresh session 但又要 保留当前对话 时使用。/prototype - (内置)- 留在 同一个对话 中,让早先 turns 被总结。只在阶段之间的明确断点使用;不要在阶段中途 compact,否则 agent 可能迷路。
/compact是分叉;/handoff是继续。/compact
- - When a thread is nearly full, or you need to branch into another session (e.g., a
/handoffsession), compress the conversation into a markdown file. You won't continue in place; instead, open a new session and reference the file to carry over context. It is a bridge between context windows, usable in both directions. Use it when you want a fresh session but need to retain the current conversation./prototype - (built-in) - Stay in the same conversation and let earlier turns be summarized. Use only at clear breakpoints between phases; do not compact mid-phase, otherwise the agent may get lost.
/compactis for forking;/handoffis for continuing./compact
Standalone
Standalone
完全在 main flow 之外。
- - 与
/grill-me一样的持续访谈,但用于 没有 codebase 的情境。它是 stateless 的:不在本地保存内容,也不构建/grill-with-docs。用它来打磨任何不属于 repo 的计划或设计。CONTEXT.md - - 一个小型 throwaway program,用来回答一个设计问题:这个 state model 感觉对吗,或者这个 UI 应该是什么样。它从第一天起就是 throwaway:保留答案,删除代码。它是 main flow 第 2 步的绕行,但任何难以纸面解决的 design question 都可以直接用它。
/prototype - - 把阅读工作委托给 background agent:它对照 primary sources 调研问题,然后在 repo 中留下带引用的 Markdown 文件。你可以在它阅读时继续工作。产物应带入
/research的 main flow;research 提供思考材料,但不取代思考。/grill-with-docs - - 使用当前目录作为 stateful workspace,跨多个 sessions 学习一个概念。
/teach - - 编写和编辑 skills 的 reference。
/writing-great-skills
Completely outside the main flow.
- - The same continuous interview as
/grill-me, but for scenarios without a codebase. It is stateless: it doesn't save content locally or build/grill-with-docs. Use it to refine any plan or design that doesn't belong to a repo.CONTEXT.md - - A small throwaway program used to answer a design question: does this state model feel right, or what should this UI look like? It's throwaway from day one: keep the answer, delete the code. It's a detour in step 2 of the main flow, but any design question that's hard to solve on paper can use it directly.
/prototype - - Delegate reading work to a background agent: it researches the question against primary sources and leaves a referenced Markdown file in the repo. You can continue working while it reads. The output should be brought into the main flow of
/research; research provides thinking materials but does not replace thinking./grill-with-docs - - Use the current directory as a stateful workspace to learn a concept across multiple sessions.
/teach - - Reference for writing and editing skills.
/writing-great-skills
Precondition
Precondition
/setup-matt-pocock-skills/setup-matt-pocock-skills