[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E7DZSQ9HCFK3PDXCFFCZFQ":3,"skill-same:01M7E7DZSQ9HCFK3PDXCFFCZFQ":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":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":46},"01M7E7DZSQ9HCFK3PDXCFFCZFQ","how",null,"Use for \"how does X work\", code walkthroughs before changing something, and placement \u002F ownership \u002F layering questions (\"where should this live\", \"which package owns this\", \"is this the right layer\"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.","giuseppecrj\u002Fpi-herdr-pstack","giuseppecrj","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5714678?v=4","01M7E7A7DZHS53J4N29EW0XYZX","Giuseppe Rodriguez","01M7E7A7EHHKRDDBPPFPKNHFDY",3,"MIT","https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fhow\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: how\ndescription: \"Use for \\\"how does X work\\\", code walkthroughs before changing something, and placement \u002F ownership \u002F layering questions (\\\"where should this live\\\", \\\"which package owns this\\\", \\\"is this the right layer\\\"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.\"\ndisable-model-invocation: true\n---\n\n# How\n\nExplore the codebase to answer \"how does X work?\" questions. Produce architectural explanations at the level of a senior engineer onboarding onto a subsystem, enough to build a working mental model, not so much that it reads like annotated source code.\n\n## Step 1. Assess Complexity\n\nIf the scope is ambiguous, state your interpretation and explore. The user can redirect.\n\n- **Simple** (a single module, a small utility, a narrow question such as \"how does function X work\"): no explorers. One explainer explores and explains in a single pass. Go to Step 2b.\n- **Complex** (a subsystem spanning multiple files or services, a cross-cutting feature, a full architectural overview): spawn parallel explorers first, then hand off to the explainer. Go to Step 2a.\n\nWhen in doubt, take the simple path.\n\n## Step 2a. Explore (complex questions only)\n\nDecompose the question into 2 to 4 exploration angles, each a distinct slice of the subsystem. Before that launch, follow the architecture preflight in `..\u002Fpoteto-mode\u002Freferences\u002Fdelegation.md`. The explainer needs `task:architecture`, and a missing category throws only after these explorers return. Launch all explorers as independent bare `subagent` calls in one turn, per `..\u002Fpoteto-mode\u002Freferences\u002Ffan-out.md`, then end the turn:\n\n- `model`: `task:recon`\n- do not grant write\u002Fedit tools\n\nEach explorer gets the prompt in `references\u002Fexplorer-prompt.md` with its angle filled in, as its `task`. Then go to Step 3.\n\n```json subagent\n{\n  \"name\": \"\u003Cslug>-explore-1\",\n  \"task\": \"\u003Creferences\u002Fexplorer-prompt.md with the question and this explorer's angle filled in>. Read-only. You are a leaf: launch nothing.\",\n  \"systemPrompt\": \"\u003Cthe Investigator prompt in ..\u002Fpoteto-mode\u002Freferences\u002Fdelegation.md, verbatim>\",\n  \"model\": \"task:recon\",\n  \"tools\": \"read, bash\",\n  \"fork\": false\n}\n```\n\n## Step 2b. Direct Explain (simple questions)\n\nSpawn one bare subagent that explores and explains in one pass. The explainer is judgment and prose synthesis, so it does not use the explorers' category. Follow the architecture preflight in `..\u002Fpoteto-mode\u002Freferences\u002Fdelegation.md` before this launch:\n\n- `model`: `task:architecture`\n- `thinking`: omit it when `architecture` has configured thinking; otherwise `high` or above\n- do not grant write\u002Fedit tools\n\nBuild its prompt from `references\u002Fexplainer-prompt.md` without the explorer-findings section. Go to Step 4.\n\n## Step 3. Synthesize (complex questions only)\n\nOnce all explorers have returned, spawn one bare subagent to synthesize their findings into one explanation. This is the same judgment seat as Step 2b:\n\n- `model`: `task:architecture`\n- `thinking`: omit it when `architecture` has configured thinking; otherwise `high` or above\n- do not grant write\u002Fedit tools\n\nBuild its prompt from `references\u002Fexplainer-prompt.md` with every explorer's findings filled in.\n\n```json subagent\n{\n  \"name\": \"\u003Cslug>-explain\",\n  \"task\": \"\u003Creferences\u002Fexplainer-prompt.md with the question and every explorer's findings filled in>. Read-only. You are a leaf: launch nothing.\",\n  \"systemPrompt\": \"\u003Cthe Investigator prompt in ..\u002Fpoteto-mode\u002Freferences\u002Fdelegation.md, verbatim>\",\n  \"model\": \"task:architecture\",\n  \"tools\": \"read, bash\",\n  \"fork\": false\n}\n```\n\nThe Step 2b explainer takes the same launch, with the explorer-findings section dropped from its `task`. See `..\u002Fpoteto-mode\u002Freferences\u002Fdelegation.md` for why synthesis uses `task:architecture`.\n\n## Step 4. Present\n\nPresent the explainer's output to the user. Light edits for clarity or context from the conversation are fine. Do not substantially rewrite it.\n\n## Output Format\n\nThe explanation uses the sections defined in `references\u002Fexplainer-prompt.md`, dropping any that do not apply: Overview, Key Concepts, How It Works, Where Things Live, Gotchas.\n","# How\n\nExplore the codebase to answer \"how does X work?\" questions. Produce architectural explanations at the level of a senior engineer onboarding onto a subsystem, enough to build a working mental model, not so much that it reads like annotated source code.\n\n## Step 1. Assess Complexity\n\nIf the scope is ambiguous, state your interpretation and explore. The user can redirect.\n\n- **Simple** (a single module, a small utility, a narrow question such as \"how does function X work\"): no explorers. One explainer explores and explains in a single pass. Go to Step 2b.\n- **Complex** (a subsystem spanning multiple files or services, a cross-cutting feature, a full architectural overview): spawn parallel explorers first, then hand off to the explainer. Go to Step 2a.\n\nWhen in doubt, take the simple path.\n\n## Step 2a. Explore (complex questions only)\n\nDecompose the question into 2 to 4 exploration angles, each a distinct slice of the subsystem. Before that launch, follow the architecture preflight in `..\u002Fpoteto-mode\u002Freferences\u002Fdelegation.md`. The explainer needs `task:architecture`, and a missing category throws only after these explorers return. Launch all explorers as independent bare `subagent` calls in one turn, per `..\u002Fpoteto-mode\u002Freferences\u002Ffan-out.md`, then end the turn:\n\n- `model`: `task:recon`\n- do not grant write\u002Fedit tools\n\nEach explorer gets the prompt in `references\u002Fexplorer-prompt.md` with its angle filled in, as its `task`. Then go to Step 3.\n\n```json subagent\n{\n  \"name\": \"\u003Cslug>-explore-1\",\n  \"task\": \"\u003Creferences\u002Fexplorer-prompt.md with the question and this explorer's angle filled in>. Read-only. You are a leaf: launch nothing.\",\n  \"systemPrompt\": \"\u003Cthe Investigator prompt in ..\u002Fpoteto-mode\u002Freferences\u002Fdelegation.md, verbatim>\",\n  \"model\": \"task:recon\",\n  \"tools\": \"read, bash\",\n  \"fork\": false\n}\n```\n\n## Step 2b. Direct Explain (simple questions)\n\nSpawn one bare subagent that explores and explains in one pass. The explainer is judgment and prose synthesis, so it does not use the explorers' category. Follow the architecture preflight in `..\u002Fpoteto-mode\u002Freferences\u002Fdelegation.md` before this launch:\n\n- `model`: `task:architecture`\n- `thinking`: omit it when `architecture` has configured thinking; otherwise `high` or above\n- do not grant write\u002Fedit tools\n\nBuild its prompt from `references\u002Fexplainer-prompt.md` without the explorer-findings section. Go to Step 4.\n\n## Step 3. Synthesize (complex questions only)\n\nOnce all explorers have returned, spawn one bare subagent to synthesize their findings into one explanation. This is the same judgment seat as Step 2b:\n\n- `model`: `task:architecture`\n- `thinking`: omit it when `architecture` has configured thinking; otherwise `high` or above\n- do not grant write\u002Fedit tools\n\nBuild its prompt from `references\u002Fexplainer-prompt.md` with every explorer's findings filled in.\n\n```json subagent\n{\n  \"name\": \"\u003Cslug>-explain\",\n  \"task\": \"\u003Creferences\u002Fexplainer-prompt.md with the question and every explorer's findings filled in>. Read-only. You are a leaf: launch nothing.\",\n  \"systemPrompt\": \"\u003Cthe Investigator prompt in ..\u002Fpoteto-mode\u002Freferences\u002Fdelegation.md, verbatim>\",\n  \"model\": \"task:architecture\",\n  \"tools\": \"read, bash\",\n  \"fork\": false\n}\n```\n\nThe Step 2b explainer takes the same launch, with the explorer-findings section dropped from its `task`. See `..\u002Fpoteto-mode\u002Freferences\u002Fdelegation.md` for why synthesis uses `task:architecture`.\n\n## Step 4. Present\n\nPresent the explainer's output to the user. Light edits for clarity or context from the conversation are fine. Do not substantially rewrite it.\n\n## Output Format\n\nThe explanation uses the sections defined in `references\u002Fexplainer-prompt.md`, dropping any that do not apply: Overview, Key Concepts, How It Works, Where Things Live, Gotchas.\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","43aca90238855614654b0222294818ec6ad2e846","skills\u002Fpstack\u002Fhow",0,"https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-pstack","https:\u002F\u002Fgithub.com\u002Fgiuseppecrj","giuseppecrj.com","Building agent infrastructure, protocol systems, and real-time product software.","2026-11-13 09:05:00",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":24},[36,39,42],{"tool":37,"command":38},"npx","npx skills add giuseppecrj\u002Fpi-herdr-pstack --skill how",{"tool":40,"command":41},"bunx","bunx skills add giuseppecrj\u002Fpi-herdr-pstack --skill how",{"tool":43,"command":44},"pnpm","pnpm dlx skills add giuseppecrj\u002Fpi-herdr-pstack --skill how","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fhow\u002FSKILL.md",[47,53],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fexplainer-prompt.md","REFERENCE","参考文档",3085,"https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fhow\u002Freferences\u002Fexplainer-prompt.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fexplorer-prompt.md",2684,"https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fhow\u002Freferences\u002Fexplorer-prompt.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},"01M7E7JPTA02FFGS96SQYQ678W","poteto-mode","Test fixture. A different skill that reuses the poteto-mode name, to check shadowing diagnostics.","https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-pstack\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fshadow-skills\u002Fpoteto-mode\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},"01M7E7JGE95NH51A731ZTRWECS","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fwhy\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},"01M7E7JEEJ2303D2M1897CCR8N","unslop","Cut AI tells from any writing. Must always apply.","https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Funslop\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},"01M7E7JCM06BKK08YM1HZ7MW67","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Ftypescript-best-practices\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},"01M7E7J7SHT7XMV128283BE35W","technical-writing","Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for \u002Fskill:technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.","https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Ftechnical-writing\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},"01M7E7J525CXJN2FKSN7HTW2X0","swarm","Fan out N parallel workers, drain them, and return one report. Use for \u002Fswarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.","https:\u002F\u002Fgithub.com\u002Fgiuseppecrj\u002Fpi-herdr-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fswarm\u002FSKILL.md",[],[]]