[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FAT4F46JCWZTVNXVF2JMBE":3,"skill-same:01M7FAT4F46JCWZTVNXVF2JMBE":49},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":13,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":42},"01M7FAT4F46JCWZTVNXVF2JMBE","mpc_ask-matt",null,"Ask which skill or flow fits your situation. A router over the skills in this plugin.","boarlabsxyz\u002Fskills","boarlabsxyz","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F183485413?v=4","01M7FAAY4JD8XATY5VPC07M8PA","01M7FAAY574ZFBK3KWT1V57ETE",0,"MIT","https:\u002F\u002Fgithub.com\u002Fboarlabsxyz\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmpc_ask-matt\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: mpc_ask-matt\ndescription: Ask which skill or flow fits your situation. A router over the skills in this plugin.\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\nThis plugin is for work whose results are not code: articles, reports, plans, documents, boards. The tickets and specs live in the repository's issue tracker, the context (Q&A logs, `GLOSSARY.md`, ADRs, research notes) lives in the repository and is committed, and every **result** lives on the platform its ticket names (a Google Doc or Drive file, a ClickUp task or doc, a Miro board, a Claude artifact).\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 → results\n\nThe route most work travels. You have a task and want it done.\n\n1. **`\u002Fboarlabs:mpc_grill-with-docs`** sharpens the task by interview, one question at a time, researching before each one (Codex takes the legwork through `boar_codex`). It retains what it learns in `GLOSSARY.md`, ADRs and a Q&A log under `docs\u002Fqna\u002F`, and commits them at the end. (No working directory? Use `\u002Fboarlabs:mpc_grill-me`, covered under Standalone.) Before it ends, every result the task needs has a place: its platform, where on it, and its name; and whether the work is marketing.\n2. **Branch: is this more than one session of work?**\n   - **Yes** → **`\u002Fboarlabs:mpc_to-spec`** (turn the thread into a spec; Codex reads the draft before it is published), then **`\u002Fboarlabs:mpc_to-tickets`** to split it into tickets, each declaring its **blocking edges**, its **Result** (platform, place, name) and its **Marketing** line (`yes` or `no`). Neither line has a default. Then work the tickets one of two ways:\n     - **`\u002Fboarlabs:mpc_implement`** per ticket, **`\u002Fclear`ing context between each one**. Each ticket is self-contained, so the last one's context is disposable.\n     - **`\u002Fboarlabs:mpc_implement-spec`** for the whole spec in one run. It reads the tickets as a **task graph**, has maker subagents make the ready **frontier**'s results in parallel, and checks them one at a time.\n   - **No** → **`\u002Fboarlabs:mpc_implement`** right here, in the same context window.\n\n   Either way, every result is checked by **`\u002Fboarlabs:boar_review`** before its ticket closes: Playwright opens the result on its platform and takes screenshots, and five models (Fable, Codex and three from OpenRouter) read the text and the screenshots against the ticket and the repository's own rules. A finding counts when two of them raise it. The report goes into the ticket's closing comment.\n\n### Context hygiene\n\nKeep steps 1–2 in **one unbroken context window** (don't compact or clear until after `\u002Fboarlabs:mpc_to-tickets`) so the grilling, spec, and tickets all build on the same thinking. Each `\u002Fboarlabs:mpc_implement` then starts fresh, working from the ticket.\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 `\u002Fboarlabs:mpc_to-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- **Requests piling up** → **`\u002Fboarlabs:mpc_triage`**. It moves issues through triage roles and produces agent-ready issues, which **`\u002Fboarlabs:mpc_implement`** later picks up. Triage is only for issues **you didn't create**; tickets that `\u002Fboarlabs:mpc_to-tickets` produced are already agent-ready, so don't triage them.\n\n- **A huge, foggy effort, too big for one session** → **`\u002Fboarlabs:mpc_wayfinder`**. 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 way is clear. When the map clears, **it hands off, it doesn't build**: merge onto the main flow at **`\u002Fboarlabs:mpc_to-spec`**.\n\n## Marketing\n\nCorey Haines's marketing skills (`chs_*`) sit beside the flow. Run **`\u002Fboarlabs:chs_product-marketing`** once per product: it writes the context document every other `chs_*` skill reads first. Call any of them directly (`\u002Fboarlabs:chs_copywriting`, `\u002Fboarlabs:chs_social`, …), or let a ticket with `Marketing: yes` have `\u002Fboarlabs:mpc_implement` pick the ones that fit.\n\n## Vocabulary underneath\n\n- **`\u002Fboarlabs:mpc_domain-modeling`**: sharpen the project's *domain* language: challenge a fuzzy term, resolve an overloaded word, record a hard-to-reverse decision as an ADR. It's the active discipline `\u002Fboarlabs:mpc_grill-with-docs` drives to keep `GLOSSARY.md` a clean glossary.\n\n## Phase boundaries\n\nA **phase** is a chunk of work inside a session: the grilling, the making, the checking. At the **boundary** between two of them you have five options: **Continue**, **`\u002Fclear`**, **`\u002Fboarlabs:mpc_handoff`**, a **subagent**, or **`\u002Fcompact`** (the default, at the bottom of the tree rather than the first reach). Read [PHASE-BOUNDARIES.md](PHASE-BOUNDARIES.md) for the ordered tree. 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- **`\u002Fboarlabs:mpc_grill-me`**: the same relentless interview as `\u002Fboarlabs:mpc_grill-with-docs`, but it builds no `GLOSSARY.md` or ADRs: its only trail is the Q&A log every grilling session writes to `docs\u002Fqna\u002F`. If you are in a working directory, use `\u002Fboarlabs:mpc_grill-with-docs` instead.\n- **`\u002Fboarlabs:mpc_grilling`** is the interview primitive itself: one question at a time with research before each, the frontier, facts are the agent's job and decisions are yours. `\u002Fboarlabs:mpc_grill-me` and `\u002Fboarlabs:mpc_grill-with-docs` are the two named ways in, and `\u002Fboarlabs:mpc_triage` and `\u002Fboarlabs:mpc_wayfinder` run it internally.\n- **`\u002Fboarlabs:mpc_research`**: hand reading legwork to Codex: it investigates one question against **primary sources**, Claude checks its evidence, and the cited findings land as a Markdown file in the repository. The file is something to take *into* the main flow at `\u002Fboarlabs:mpc_grill-with-docs`.\n- **`\u002Fboarlabs:boar_codex`**: Codex as a second reader. A **plan-read** of a spec draft, a research file or a decision before it is relied on; a **research** run for one precise question.\n- **`\u002Fboarlabs:mpc_to-questionnaire`**: when the thing blocking you is in **someone else's** head, it writes them a questionnaire. What comes back is material for `\u002Fboarlabs:mpc_grill-with-docs` or `\u002Fboarlabs:mpc_to-spec`.\n- **`\u002Fboarlabs:mpc_wait-what`** is the corrective for a message that didn't land: the agent re-pitches it with the context you were missing, in plain English, using the `GLOSSARY.md` vocabulary.\n- **`\u002Fboarlabs:mpc_teach`**: learn a concept over multiple sessions, using the current directory as a stateful workspace.\n- **`\u002Fboarlabs:mpc_writing-fragments`**, **`\u002Fboarlabs:mpc_writing-shape`** and **`\u002Fboarlabs:mpc_writing-beats`**: mine raw material for an article, then shape it paragraph by paragraph or as a journey of beats.\n- **`\u002Fboarlabs:mpc_writing-for-agents`** is the reference for writing documents agents consume: skills, AGENTS.md, pointed-at docs.\n\n## Precondition\n\n**`\u002Fboarlabs:boar_setup`**: run once per repository. It checks the prerequisites, writes `start.sh` and `.env.example`, prepares the Playwright browser, configures the issue tracker, triage labels and doc layout the other skills assume (Matt's `\u002Fboarlabs:mpc_setup-matt-pocock-skills`), and commits.\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\nThis plugin is for work whose results are not code: articles, reports, plans, documents, boards. The tickets and specs live in the repository's issue tracker, the context (Q&A logs, `GLOSSARY.md`, ADRs, research notes) lives in the repository and is committed, and every **result** lives on the platform its ticket names (a Google Doc or Drive file, a ClickUp task or doc, a Miro board, a Claude artifact).\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 → results\n\nThe route most work travels. You have a task and want it done.\n\n1. **`\u002Fboarlabs:mpc_grill-with-docs`** sharpens the task by interview, one question at a time, researching before each one (Codex takes the legwork through `boar_codex`). It retains what it learns in `GLOSSARY.md`, ADRs and a Q&A log under `docs\u002Fqna\u002F`, and commits them at the end. (No working directory? Use `\u002Fboarlabs:mpc_grill-me`, covered under Standalone.) Before it ends, every result the task needs has a place: its platform, where on it, and its name; and whether the work is marketing.\n2. **Branch: is this more than one session of work?**\n   - **Yes** → **`\u002Fboarlabs:mpc_to-spec`** (turn the thread into a spec; Codex reads the draft before it is published), then **`\u002Fboarlabs:mpc_to-tickets`** to split it into tickets, each declaring its **blocking edges**, its **Result** (platform, place, name) and its **Marketing** line (`yes` or `no`). Neither line has a default. Then work the tickets one of two ways:\n     - **`\u002Fboarlabs:mpc_implement`** per ticket, **`\u002Fclear`ing context between each one**. Each ticket is self-contained, so the last one's context is disposable.\n     - **`\u002Fboarlabs:mpc_implement-spec`** for the whole spec in one run. It reads the tickets as a **task graph**, has maker subagents make the ready **frontier**'s results in parallel, and checks them one at a time.\n   - **No** → **`\u002Fboarlabs:mpc_implement`** right here, in the same context window.\n\n   Either way, every result is checked by **`\u002Fboarlabs:boar_review`** before its ticket closes: Playwright opens the result on its platform and takes screenshots, and five models (Fable, Codex and three from OpenRouter) read the text and the screenshots against the ticket and the repository's own rules. A finding counts when two of them raise it. The report goes into the ticket's closing comment.\n\n### Context hygiene\n\nKeep steps 1–2 in **one unbroken context window** (don't compact or clear until after `\u002Fboarlabs:mpc_to-tickets`) so the grilling, spec, and tickets all build on the same thinking. Each `\u002Fboarlabs:mpc_implement` then starts fresh, working from the ticket.\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 `\u002Fboarlabs:mpc_to-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- **Requests piling up** → **`\u002Fboarlabs:mpc_triage`**. It moves issues through triage roles and produces agent-ready issues, which **`\u002Fboarlabs:mpc_implement`** later picks up. Triage is only for issues **you didn't create**; tickets that `\u002Fboarlabs:mpc_to-tickets` produced are already agent-ready, so don't triage them.\n\n- **A huge, foggy effort, too big for one session** → **`\u002Fboarlabs:mpc_wayfinder`**. 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 way is clear. When the map clears, **it hands off, it doesn't build**: merge onto the main flow at **`\u002Fboarlabs:mpc_to-spec`**.\n\n## Marketing\n\nCorey Haines's marketing skills (`chs_*`) sit beside the flow. Run **`\u002Fboarlabs:chs_product-marketing`** once per product: it writes the context document every other `chs_*` skill reads first. Call any of them directly (`\u002Fboarlabs:chs_copywriting`, `\u002Fboarlabs:chs_social`, …), or let a ticket with `Marketing: yes` have `\u002Fboarlabs:mpc_implement` pick the ones that fit.\n\n## Vocabulary underneath\n\n- **`\u002Fboarlabs:mpc_domain-modeling`**: sharpen the project's *domain* language: challenge a fuzzy term, resolve an overloaded word, record a hard-to-reverse decision as an ADR. It's the active discipline `\u002Fboarlabs:mpc_grill-with-docs` drives to keep `GLOSSARY.md` a clean glossary.\n\n## Phase boundaries\n\nA **phase** is a chunk of work inside a session: the grilling, the making, the checking. At the **boundary** between two of them you have five options: **Continue**, **`\u002Fclear`**, **`\u002Fboarlabs:mpc_handoff`**, a **subagent**, or **`\u002Fcompact`** (the default, at the bottom of the tree rather than the first reach). Read [PHASE-BOUNDARIES.md](PHASE-BOUNDARIES.md) for the ordered tree. 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- **`\u002Fboarlabs:mpc_grill-me`**: the same relentless interview as `\u002Fboarlabs:mpc_grill-with-docs`, but it builds no `GLOSSARY.md` or ADRs: its only trail is the Q&A log every grilling session writes to `docs\u002Fqna\u002F`. If you are in a working directory, use `\u002Fboarlabs:mpc_grill-with-docs` instead.\n- **`\u002Fboarlabs:mpc_grilling`** is the interview primitive itself: one question at a time with research before each, the frontier, facts are the agent's job and decisions are yours. `\u002Fboarlabs:mpc_grill-me` and `\u002Fboarlabs:mpc_grill-with-docs` are the two named ways in, and `\u002Fboarlabs:mpc_triage` and `\u002Fboarlabs:mpc_wayfinder` run it internally.\n- **`\u002Fboarlabs:mpc_research`**: hand reading legwork to Codex: it investigates one question against **primary sources**, Claude checks its evidence, and the cited findings land as a Markdown file in the repository. The file is something to take *into* the main flow at `\u002Fboarlabs:mpc_grill-with-docs`.\n- **`\u002Fboarlabs:boar_codex`**: Codex as a second reader. A **plan-read** of a spec draft, a research file or a decision before it is relied on; a **research** run for one precise question.\n- **`\u002Fboarlabs:mpc_to-questionnaire`**: when the thing blocking you is in **someone else's** head, it writes them a questionnaire. What comes back is material for `\u002Fboarlabs:mpc_grill-with-docs` or `\u002Fboarlabs:mpc_to-spec`.\n- **`\u002Fboarlabs:mpc_wait-what`** is the corrective for a message that didn't land: the agent re-pitches it with the context you were missing, in plain English, using the `GLOSSARY.md` vocabulary.\n- **`\u002Fboarlabs:mpc_teach`**: learn a concept over multiple sessions, using the current directory as a stateful workspace.\n- **`\u002Fboarlabs:mpc_writing-fragments`**, **`\u002Fboarlabs:mpc_writing-shape`** and **`\u002Fboarlabs:mpc_writing-beats`**: mine raw material for an article, then shape it paragraph by paragraph or as a journey of beats.\n- **`\u002Fboarlabs:mpc_writing-for-agents`** is the reference for writing documents agents consume: skills, AGENTS.md, pointed-at docs.\n\n## Precondition\n\n**`\u002Fboarlabs:boar_setup`**: run once per repository. It checks the prerequisites, writes `start.sh` and `.env.example`, prepares the Playwright browser, configures the issue tracker, triage labels and doc layout the other skills assume (Matt's `\u002Fboarlabs:mpc_setup-matt-pocock-skills`), and commits.\n",{"name":5,"description":7,"disable-model-invocation":23},true,"main","70822f79cdb0fbf902c74433bbb4a7bc4ac033cc","skills\u002Fmpc_ask-matt","https:\u002F\u002Fgithub.com\u002Fboarlabsxyz\u002Fskills","https:\u002F\u002Fgithub.com\u002Fboarlabsxyz","2026-10-21 20:41:04",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":23},[32,35,38],{"tool":33,"command":34},"npx","npx skills add boarlabsxyz\u002Fskills --skill mpc_ask-matt",{"tool":36,"command":37},"bunx","bunx skills add boarlabsxyz\u002Fskills --skill mpc_ask-matt",{"tool":39,"command":40},"pnpm","pnpm dlx skills add boarlabsxyz\u002Fskills --skill mpc_ask-matt","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fboarlabsxyz\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmpc_ask-matt\u002FSKILL.md",[43],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},"PHASE-BOUNDARIES.md","REFERENCE","参考文档",4301,"https:\u002F\u002Fgithub.com\u002Fboarlabsxyz\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmpc_ask-matt\u002FPHASE-BOUNDARIES.md",[50,57,64,71,78,85],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":18},"01M7FAW878DNGW855BTMPHJGGT","mpc_writing-shape","Writing, exploit: shape raw material into an article, paragraph by paragraph.","https:\u002F\u002Fgithub.com\u002Fboarlabsxyz\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmpc_writing-shape\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":18},"01M7FAW53VT22GATJ9VNEQ21HY","mpc_writing-fragments","Writing, explore: mine raw fragments, no structure yet.","https:\u002F\u002Fgithub.com\u002Fboarlabsxyz\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmpc_writing-fragments\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M7FAW2E42FBEKVX4RH82RZ55","mpc_writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fboarlabsxyz\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmpc_writing-for-agents\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M7FAVZ8S0KT45XMZPWMA2KCS","mpc_writing-beats","Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.","https:\u002F\u002Fgithub.com\u002Fboarlabsxyz\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmpc_writing-beats\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M7FAVV4EQBCDJA10KAHRKFSQ","mpc_wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fboarlabsxyz\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmpc_wayfinder\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M7FAVR30JXV3830GWCJSVJZP","mpc_wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002Fboarlabsxyz\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmpc_wait-what\u002FSKILL.md",[],[]]