[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AWT7AZTSP9JCMB3RNHS1DT":3,"skill-same:01M7AWT7AZTSP9JCMB3RNHS1DT":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":46},"01M7AWT7AZTSP9JCMB3RNHS1DT","ask-matt",null,"Ask which skill or flow fits your situation. A router over the skills in this repo.","wangmiaozero\u002Fpi-harness","wangmiaozero","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F45121589?v=4","01M7AWPWCP23VHFH4433FG7SV8","seedling","01M7AWPWDBEBWBMPCA6VSEFJBB",385,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Fwangmiaozero\u002Fpi-harness\u002Fblob\u002Fmain\u002Fresources\u002Fbuiltin-skills\u002Fmattpocock\u002Fskills\u002Fengineering\u002Fask-matt\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ask-matt\ndescription: Ask which skill or flow fits your situation. A router over the skills in this repo.\ndisable-model-invocation: true\n---\n\n# Ask Matt\n\nYou don't remember every skill, so ask.\n\nBefore stating what a skill does or recommending a step be skipped, read that skill's SKILL.md: the summaries here are for orientation only.\n\nA **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.\n\n## The main flow: idea → ship\n\nThe route most work travels. You have an idea and want it built.\n\n1. **`\u002Fgrill-with-docs`** sharpens the idea by interview. Start here whenever you are **working in a working directory**: it's stateful, retaining what it learns in `GLOSSARY.md` and ADRs. (No working directory? Use `\u002Fgrill-me` instead, covered under Standalone. Both run the same `\u002Fgrilling` primitive; `grill-with-docs` is the one that leaves a paper trail, which makes it the better of the two whenever a repo is there to leave it in.)\n2. **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 **`\u002Fhandoff`** in both directions (a prototype lives in its own directory, which is exactly what `\u002Fhandoff` is for; see Phase boundaries):\n   - **`\u002Fhandoff`** out, then open a fresh session against that file,\n   - **`\u002Fprototype`** to answer the question with throwaway code,\n   - **`\u002Fhandoff`** back what you learned, and reference it from the original idea thread.\n3. **Branch: is this a multi-session build?**\n   - **Yes** → **`\u002Fto-spec`** (turn the thread into a spec), then **`\u002Fto-tickets`** to split it into tracer-bullet tickets, each declaring its **blocking edges**. Then work the tickets one of two ways:\n     - **`\u002Fimplement`** per ticket, **`\u002Fclear`ing context between each one**. On a local tracker that's one file per ticket under `.scratch\u002F\u003Cfeature>\u002Fissues\u002F`, 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 is self-contained, so the last one's context is disposable.\n     - **`\u002Fimplement-spec`** for the whole spec in one run. It reads the tickets as a **task graph**, runs implementer subagents across the ready **frontier** in parallel, and lands everything on one **integration branch**. Reach for it when you'd rather orchestrate the build than drive each ticket yourself.\n   - **No** → **`\u002Fimplement`** right here, in the same context window.\n\n   Either way, the code gets built by driving **`\u002Ftdd`** (one red-green slice at a time) and closes out with **`\u002Fcode-review`**, a two-axis review (Standards + Spec) of the diff. `\u002Fimplement` runs both per ticket; `\u002Fimplement-spec`'s implementers each drive `\u002Ftdd`, and it runs one `\u002Fcode-review` over the integration branch. Reach for **`\u002Ftdd`** on its own when you just want to build a concrete behaviour test-first without a full spec, and **`\u002Fcode-review`** on its own whenever you want to review a branch or PR against a fixed point.\n\n   When the work goes up as a pull request, **`\u002Fpr`** shapes the body: the smallest visual that shows the change, before\u002Fafter 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.\n\n4. **`\u002Fretro`** closes 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 `\u002Fcode-review` enforces, steering files, tooling. Mechanical mistakes become deterministic checks; judgement calls become coding standards. The next build then starts from a better environment.\n\n### Context hygiene\n\nKeep steps 1–3 in **one unbroken context window** (don't compact or clear until after `\u002Fto-tickets`) so the grilling, spec, and tickets all build on the same thinking. Each `\u002Fimplement` then starts fresh, working from the ticket. Run `\u002Fretro` in the session it's looking back on, before you clear; after clearing, point it at that session's log instead.\n\nThe limit on this is the **[smart zone](https:\u002F\u002Fwww.aihero.dev\u002Fai-coding-dictionary\u002Fsmart-zone)**: the window (~150k tokens on state-of-the-art models) within which the model still reasons sharply. If a session approaches it before `\u002Fto-tickets`, don't push on degraded; `\u002Fcompact` at the nearest phase boundary and carry on (see Phase boundaries).\n\n## On-ramps\n\nA starting situation that generates work, then merges onto the main flow.\n\n- **Bugs and requests piling up** → **`\u002Ftriage`**. It moves issues through triage roles and produces agent-ready issues, which **`\u002Fimplement`** later picks up.\n\n  Triage is only for issues **you didn't create**: bug reports, incoming feature requests, anything that arrives raw. Tickets that `\u002Fto-tickets` produced are already agent-ready, so **don't triage them**.\n\n- **Something's broken** → **`\u002Fdiagnosing-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 **`\u002Fretro`** in 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, that's a job for **`\u002Fimprove-codebase-architecture`**.\n\n- **A huge, foggy effort: a greenfield project or a huge feature build, too big for one session** → **`\u002Fwayfinder`**, 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 **`\u002Fgrill-with-docs`** sharpens 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.\n\n  When the map clears, **it hands off, it doesn't build**: merge onto the main flow at **`\u002Fto-spec`**, which collapses the map's linked decisions into a buildable plan, then `\u002Fto-tickets` and `\u002Fimplement` as usual. Looping the map straight into `\u002Fimplement` skips that collapse and throws the linked detail away, so go straight to `\u002Fimplement` only when the effort turned out genuinely small.\n\n## Codebase health\n\nNot feature work, just upkeep.\n\n- **`\u002Fimprove-codebase-architecture`** runs 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 `\u002Fgrill-with-docs`. It's the survey that finds the candidates; **`\u002Fcodebase-design`** (below) is the bench you design the chosen one on.\n\n## Vocabulary underneath\n\nTwo 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.\n\n- **`\u002Fdomain-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 `\u002Fgrill-with-docs` drives to keep `GLOSSARY.md` a clean glossary.\n- **`\u002Fcodebase-design`** is 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. `\u002Ftdd` and `\u002Fimprove-codebase-architecture` both speak it.\n\n## Phase boundaries\n\nA **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:\n\n- **Continue**: stay put. Costs nothing, loses nothing.\n- **`\u002Fclear`**: empty the window, when nothing here matters to what's next.\n- **`\u002Fhandoff`** writes 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.\n- **Subagent**: send a tightly-scoped task to its own window and get a report back.\n- **`\u002Fcompact`** compresses this context and seeds a fresh session with it. The **default**, at the bottom of the tree rather than the first reach.\n\nRead [PHASE-BOUNDARIES.md](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.\n\n## Standalone\n\nOff the main flow entirely.\n\n- **`\u002Fgrill-me`**: the same relentless interview as `\u002Fgrill-with-docs`, but **stateless**: it saves nothing locally and builds no `GLOSSARY.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 `\u002Fgrill-with-docs` instead: it runs the same interview and leaves a paper trail, so it is strictly the better one.\n- **`\u002Fgrilling`** is the interview primitive itself: rounds, the frontier, facts are the agent's job and decisions are yours. `\u002Fgrill-me` and `\u002Fgrill-with-docs` are the two named ways in, and `\u002Ftriage`, `\u002Fwayfinder` and `\u002Fimprove-codebase-architecture` all run it internally. Reach for it directly only when you want the interview with no wrapper around it.\n- **`\u002Fprototype`** is 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 a `prototype\u002F\u003Cname>` 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.\n- **`\u002Fresearch`**: 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 `\u002Fgrill-with-docs`, since research feeds the thinking rather than replacing it.\n- **`\u002Fto-questionnaire`** comes 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 `\u002Fgrill-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 `\u002Fgrill-with-docs` or `\u002Fto-spec`.\n- **`\u002Fwizard`** is 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 `.env` and 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.\n- **`\u002Fwait-what`** is 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 the `GLOSSARY.md` vocabulary. It works after the fact; `\u002Fgrill-with-docs` is the upfront cure, because a shared language agreed early is what stops the jargon arriving at all.\n- **`\u002Fteach`**: learn a concept over multiple sessions, using the current directory as a stateful workspace.\n- **`\u002Fwriting-for-agents`** is the reference for writing documents agents consume: skills, AGENTS.md, pointed-at docs.\n\n## Precondition\n\n**`\u002Fsetup-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.\n","# Ask Matt\n\nYou don't remember every skill, so ask.\n\nBefore stating what a skill does or recommending a step be skipped, read that skill's SKILL.md: the summaries here are for orientation only.\n\nA **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.\n\n## The main flow: idea → ship\n\nThe route most work travels. You have an idea and want it built.\n\n1. **`\u002Fgrill-with-docs`** sharpens the idea by interview. Start here whenever you are **working in a working directory**: it's stateful, retaining what it learns in `GLOSSARY.md` and ADRs. (No working directory? Use `\u002Fgrill-me` instead, covered under Standalone. Both run the same `\u002Fgrilling` primitive; `grill-with-docs` is the one that leaves a paper trail, which makes it the better of the two whenever a repo is there to leave it in.)\n2. **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 **`\u002Fhandoff`** in both directions (a prototype lives in its own directory, which is exactly what `\u002Fhandoff` is for; see Phase boundaries):\n   - **`\u002Fhandoff`** out, then open a fresh session against that file,\n   - **`\u002Fprototype`** to answer the question with throwaway code,\n   - **`\u002Fhandoff`** back what you learned, and reference it from the original idea thread.\n3. **Branch: is this a multi-session build?**\n   - **Yes** → **`\u002Fto-spec`** (turn the thread into a spec), then **`\u002Fto-tickets`** to split it into tracer-bullet tickets, each declaring its **blocking edges**. Then work the tickets one of two ways:\n     - **`\u002Fimplement`** per ticket, **`\u002Fclear`ing context between each one**. On a local tracker that's one file per ticket under `.scratch\u002F\u003Cfeature>\u002Fissues\u002F`, 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 is self-contained, so the last one's context is disposable.\n     - **`\u002Fimplement-spec`** for the whole spec in one run. It reads the tickets as a **task graph**, runs implementer subagents across the ready **frontier** in parallel, and lands everything on one **integration branch**. Reach for it when you'd rather orchestrate the build than drive each ticket yourself.\n   - **No** → **`\u002Fimplement`** right here, in the same context window.\n\n   Either way, the code gets built by driving **`\u002Ftdd`** (one red-green slice at a time) and closes out with **`\u002Fcode-review`**, a two-axis review (Standards + Spec) of the diff. `\u002Fimplement` runs both per ticket; `\u002Fimplement-spec`'s implementers each drive `\u002Ftdd`, and it runs one `\u002Fcode-review` over the integration branch. Reach for **`\u002Ftdd`** on its own when you just want to build a concrete behaviour test-first without a full spec, and **`\u002Fcode-review`** on its own whenever you want to review a branch or PR against a fixed point.\n\n   When the work goes up as a pull request, **`\u002Fpr`** shapes the body: the smallest visual that shows the change, before\u002Fafter 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.\n\n4. **`\u002Fretro`** closes 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 `\u002Fcode-review` enforces, steering files, tooling. Mechanical mistakes become deterministic checks; judgement calls become coding standards. The next build then starts from a better environment.\n\n### Context hygiene\n\nKeep steps 1–3 in **one unbroken context window** (don't compact or clear until after `\u002Fto-tickets`) so the grilling, spec, and tickets all build on the same thinking. Each `\u002Fimplement` then starts fresh, working from the ticket. Run `\u002Fretro` in the session it's looking back on, before you clear; after clearing, point it at that session's log instead.\n\nThe limit on this is the **[smart zone](https:\u002F\u002Fwww.aihero.dev\u002Fai-coding-dictionary\u002Fsmart-zone)**: the window (~150k tokens on state-of-the-art models) within which the model still reasons sharply. If a session approaches it before `\u002Fto-tickets`, don't push on degraded; `\u002Fcompact` at the nearest phase boundary and carry on (see Phase boundaries).\n\n## On-ramps\n\nA starting situation that generates work, then merges onto the main flow.\n\n- **Bugs and requests piling up** → **`\u002Ftriage`**. It moves issues through triage roles and produces agent-ready issues, which **`\u002Fimplement`** later picks up.\n\n  Triage is only for issues **you didn't create**: bug reports, incoming feature requests, anything that arrives raw. Tickets that `\u002Fto-tickets` produced are already agent-ready, so **don't triage them**.\n\n- **Something's broken** → **`\u002Fdiagnosing-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 **`\u002Fretro`** in 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, that's a job for **`\u002Fimprove-codebase-architecture`**.\n\n- **A huge, foggy effort: a greenfield project or a huge feature build, too big for one session** → **`\u002Fwayfinder`**, 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 **`\u002Fgrill-with-docs`** sharpens 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.\n\n  When the map clears, **it hands off, it doesn't build**: merge onto the main flow at **`\u002Fto-spec`**, which collapses the map's linked decisions into a buildable plan, then `\u002Fto-tickets` and `\u002Fimplement` as usual. Looping the map straight into `\u002Fimplement` skips that collapse and throws the linked detail away, so go straight to `\u002Fimplement` only when the effort turned out genuinely small.\n\n## Codebase health\n\nNot feature work, just upkeep.\n\n- **`\u002Fimprove-codebase-architecture`** runs 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 `\u002Fgrill-with-docs`. It's the survey that finds the candidates; **`\u002Fcodebase-design`** (below) is the bench you design the chosen one on.\n\n## Vocabulary underneath\n\nTwo 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.\n\n- **`\u002Fdomain-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 `\u002Fgrill-with-docs` drives to keep `GLOSSARY.md` a clean glossary.\n- **`\u002Fcodebase-design`** is 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. `\u002Ftdd` and `\u002Fimprove-codebase-architecture` both speak it.\n\n## Phase boundaries\n\nA **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:\n\n- **Continue**: stay put. Costs nothing, loses nothing.\n- **`\u002Fclear`**: empty the window, when nothing here matters to what's next.\n- **`\u002Fhandoff`** writes 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.\n- **Subagent**: send a tightly-scoped task to its own window and get a report back.\n- **`\u002Fcompact`** compresses this context and seeds a fresh session with it. The **default**, at the bottom of the tree rather than the first reach.\n\nRead [PHASE-BOUNDARIES.md](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.\n\n## Standalone\n\nOff the main flow entirely.\n\n- **`\u002Fgrill-me`**: the same relentless interview as `\u002Fgrill-with-docs`, but **stateless**: it saves nothing locally and builds no `GLOSSARY.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 `\u002Fgrill-with-docs` instead: it runs the same interview and leaves a paper trail, so it is strictly the better one.\n- **`\u002Fgrilling`** is the interview primitive itself: rounds, the frontier, facts are the agent's job and decisions are yours. `\u002Fgrill-me` and `\u002Fgrill-with-docs` are the two named ways in, and `\u002Ftriage`, `\u002Fwayfinder` and `\u002Fimprove-codebase-architecture` all run it internally. Reach for it directly only when you want the interview with no wrapper around it.\n- **`\u002Fprototype`** is 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 a `prototype\u002F\u003Cname>` 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.\n- **`\u002Fresearch`**: 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 `\u002Fgrill-with-docs`, since research feeds the thinking rather than replacing it.\n- **`\u002Fto-questionnaire`** comes 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 `\u002Fgrill-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 `\u002Fgrill-with-docs` or `\u002Fto-spec`.\n- **`\u002Fwizard`** is 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 `.env` and 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.\n- **`\u002Fwait-what`** is 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 the `GLOSSARY.md` vocabulary. It works after the fact; `\u002Fgrill-with-docs` is the upfront cure, because a shared language agreed early is what stops the jargon arriving at all.\n- **`\u002Fteach`**: learn a concept over multiple sessions, using the current directory as a stateful workspace.\n- **`\u002Fwriting-for-agents`** is the reference for writing documents agents consume: skills, AGENTS.md, pointed-at docs.\n\n## Precondition\n\n**`\u002Fsetup-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.\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","ab32e788f56afdb9367c3a1a6b33a19e5d0058cd","resources\u002Fbuiltin-skills\u002Fmattpocock\u002Fskills\u002Fengineering\u002Fask-matt",26,"https:\u002F\u002Fgithub.com\u002Fwangmiaozero\u002Fpi-harness","https:\u002F\u002Fwangmiaozero.github.io\u002Fpi-harness-website\u002F","https:\u002F\u002Fgithub.com\u002Fwangmiaozero","Sometimes you need to applaud yourself!\r\n有时候我们需要为自己鼓掌","2026-11-15 00:08:20",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":24},[36,39,42],{"tool":37,"command":38},"npx","npx skills add wangmiaozero\u002Fpi-harness --skill ask-matt",{"tool":40,"command":41},"bunx","bunx skills add wangmiaozero\u002Fpi-harness --skill ask-matt",{"tool":43,"command":44},"pnpm","pnpm dlx skills add wangmiaozero\u002Fpi-harness --skill ask-matt","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fwangmiaozero\u002Fpi-harness\u002Fblob\u002Fmain\u002Fresources\u002Fbuiltin-skills\u002Fmattpocock\u002Fskills\u002Fengineering\u002Fask-matt\u002FSKILL.md",[47,53],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"agents\u002Fopenai.yaml","REFERENCE","参考文档",137,"https:\u002F\u002Fgithub.com\u002Fwangmiaozero\u002Fpi-harness\u002Fblob\u002Fmain\u002Fresources\u002Fbuiltin-skills\u002Fmattpocock\u002Fskills\u002Fengineering\u002Fask-matt\u002Fagents\u002Fopenai.yaml",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"PHASE-BOUNDARIES.md",4249,"https:\u002F\u002Fgithub.com\u002Fwangmiaozero\u002Fpi-harness\u002Fblob\u002Fmain\u002Fresources\u002Fbuiltin-skills\u002Fmattpocock\u002Fskills\u002Fengineering\u002Fask-matt\u002FPHASE-BOUNDARIES.md",[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7AWWZY5GKH53CCVBRWM189E","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fwangmiaozero\u002Fpi-harness\u002Fblob\u002Fmain\u002Fresources\u002Fbuiltin-skills\u002Fmattpocock\u002Fskills\u002Fproductivity\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7AWWX17A9H17BRHCHHN0PYQ","wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002Fwangmiaozero\u002Fpi-harness\u002Fblob\u002Fmain\u002Fresources\u002Fbuiltin-skills\u002Fmattpocock\u002Fskills\u002Fproductivity\u002Fwait-what\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7AWWTJXPFBG1WB5ASW1C9XF","to-questionnaire","Turn a decision you can't fully answer into a questionnaire for someone else to fill in.","https:\u002F\u002Fgithub.com\u002Fwangmiaozero\u002Fpi-harness\u002Fblob\u002Fmain\u002Fresources\u002Fbuiltin-skills\u002Fmattpocock\u002Fskills\u002Fproductivity\u002Fto-questionnaire\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7AWWR5NW24TGSN342CMHJ5P","teach","Teach the user a new skill or concept, within this workspace.","https:\u002F\u002Fgithub.com\u002Fwangmiaozero\u002Fpi-harness\u002Fblob\u002Fmain\u002Fresources\u002Fbuiltin-skills\u002Fmattpocock\u002Fskills\u002Fproductivity\u002Fteach\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7AWWNYR6NZ1J9BA059WWGZ4","handoff","Compact the current conversation into a handoff document for another agent to pick up.","https:\u002F\u002Fgithub.com\u002Fwangmiaozero\u002Fpi-harness\u002Fblob\u002Fmain\u002Fresources\u002Fbuiltin-skills\u002Fmattpocock\u002Fskills\u002Fproductivity\u002Fhandoff\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7AWWKJKST2EVB9N4QH9DVGT","grilling","Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.","https:\u002F\u002Fgithub.com\u002Fwangmiaozero\u002Fpi-harness\u002Fblob\u002Fmain\u002Fresources\u002Fbuiltin-skills\u002Fmattpocock\u002Fskills\u002Fproductivity\u002Fgrilling\u002FSKILL.md",[],[]]