[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F1ME3QR9FJXY3XWXWDMD69":3,"skill-same:01M7F1ME3QR9FJXY3XWXWDMD69":56},{"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":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":45},"01M7F1ME3QR9FJXY3XWXWDMD69","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.","willgosnold\u002Fpatchbook","willgosnold","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F90176365?v=4","01M7F13J2VJ2R4DZHPQY7P92A0","Will Gosnold","01M7F1K8G0DXVG90J6F8WQR138",1,"MIT","https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhow\u002FSKILL.md",[],[],"2026-11-16 10:05:34",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\nEvery spawn is a `delegate_task` child with the whole brief in `task`, its own `clientRequestId`, and no `isolation`. Each brief says \"Do not edit, create, commit, or push files.\", and you run `git status` afterward. Explorers use the `how explorer` line in `.agents\u002Fpstack-models.md` in the project's main checkout (`\"$(dirname \"$(git rev-parse --path-format=absolute --git-common-dir)\")\u002F.agents\u002Fpstack-models.md\"`, which may not exist), else `claudeAgent\u002Fclaude-haiku-5-5 xhigh`, and every explainer uses the `how explainer` line, else `claudeAgent\u002Fclaude-opus-5-5 high`. A role line is `\u003Crole>: \u003Centry>, \u003Centry>, ...`, and a panel role runs one subagent per entry. An entry `\u003Cprovider>\u002F\u003Cmodel> \u003Ceffort>` becomes `target: {providerInstanceId: \u003Cprovider>, model: \u003Cmodel>, options: {effort: \u003Ceffort>}}`, with `reasoningEffort` instead of `effort` for `codex`. `inherit-parent` means omit `target`. The effort is a ceiling: lower it for routine work, never raise it, and never set `fastMode`.\n\n## 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. Spawn one explainer that explores and explains in one pass, built from `references\u002Fexplainer-prompt.md` without the explorer-findings section. Go to step 4.\n- **Complex** (a subsystem spanning multiple files or services, a cross-cutting feature, a full architectural overview): go to step 2.\n\nWhen in doubt, take the simple path.\n\n## 2. Explore (complex only)\n\nDecompose the question into 2 to 4 angles, each a distinct slice of the subsystem. Spawn all explorers in a single message, each with `references\u002Fexplorer-prompt.md` and its angle filled in.\n\n## 3. Synthesize (complex only)\n\nOnce all explorers have returned, spawn one explainer with `references\u002Fexplainer-prompt.md` and every explorer's findings filled in.\n\n## 4. Present\n\nPresent the explainer's output. 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\nEvery spawn is a `delegate_task` child with the whole brief in `task`, its own `clientRequestId`, and no `isolation`. Each brief says \"Do not edit, create, commit, or push files.\", and you run `git status` afterward. Explorers use the `how explorer` line in `.agents\u002Fpstack-models.md` in the project's main checkout (`\"$(dirname \"$(git rev-parse --path-format=absolute --git-common-dir)\")\u002F.agents\u002Fpstack-models.md\"`, which may not exist), else `claudeAgent\u002Fclaude-haiku-5-5 xhigh`, and every explainer uses the `how explainer` line, else `claudeAgent\u002Fclaude-opus-5-5 high`. A role line is `\u003Crole>: \u003Centry>, \u003Centry>, ...`, and a panel role runs one subagent per entry. An entry `\u003Cprovider>\u002F\u003Cmodel> \u003Ceffort>` becomes `target: {providerInstanceId: \u003Cprovider>, model: \u003Cmodel>, options: {effort: \u003Ceffort>}}`, with `reasoningEffort` instead of `effort` for `codex`. `inherit-parent` means omit `target`. The effort is a ceiling: lower it for routine work, never raise it, and never set `fastMode`.\n\n## 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. Spawn one explainer that explores and explains in one pass, built from `references\u002Fexplainer-prompt.md` without the explorer-findings section. Go to step 4.\n- **Complex** (a subsystem spanning multiple files or services, a cross-cutting feature, a full architectural overview): go to step 2.\n\nWhen in doubt, take the simple path.\n\n## 2. Explore (complex only)\n\nDecompose the question into 2 to 4 angles, each a distinct slice of the subsystem. Spawn all explorers in a single message, each with `references\u002Fexplorer-prompt.md` and its angle filled in.\n\n## 3. Synthesize (complex only)\n\nOnce all explorers have returned, spawn one explainer with `references\u002Fexplainer-prompt.md` and every explorer's findings filled in.\n\n## 4. Present\n\nPresent the explainer's output. 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","b47f5118e95c2c9791e6e975b6a9a97571d2dc67",".agents\u002Fskills\u002Fhow",0,"https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook","https:\u002F\u002Fgithub.com\u002Fwillgosnold","Independent AI safety research | London | MSc @ University of Exeter ","2026-10-28 06:42:27",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":24},[35,38,41],{"tool":36,"command":37},"npx","npx skills add willgosnold\u002Fpatchbook --skill how",{"tool":39,"command":40},"bunx","bunx skills add willgosnold\u002Fpatchbook --skill how",{"tool":42,"command":43},"pnpm","pnpm dlx skills add willgosnold\u002Fpatchbook --skill how","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhow\u002FSKILL.md",[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fexplainer-prompt.md","REFERENCE","参考文档",3085,"https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhow\u002Freferences\u002Fexplainer-prompt.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fexplorer-prompt.md",1135,"https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhow\u002Freferences\u002Fexplorer-prompt.md",[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7F1TFAS2GDQR010AV81M3H1","patchbook-update","Pull upstreams into a repo that keeps its changes in a patchbook (.patchbook\u002F), repair what broke from each change's intent, test and review, then merge and deploy only when the sync was clean or the test command passes, and otherwise ask, opening a pull request when there are commits to push. Use when a scheduled task or the user says to update a patchbook repo, or for \u002Fpatchbook-update or $patchbook-update.","https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002Fskills\u002Fpatchbook-update\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7F1T945FRSKCATSWWGM0HJG","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\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7F1T54ST6QFMHX8CX01DKNB","verify-patchbook","Drive the patchbook CLI from this checkout in a disposable sandbox (its own git repos, store, config and a fake model) and capture a transcript as proof. Use to reproduce a patchbook bug, run an issue's repro script, or prove a change to clone, init, record, the pre-commit hook, build, status, check, sync or upstream works the way a user would see it.","https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-patchbook\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7F1T3NHKBVGVD4BT2C5BG7A","unslop","Cut AI tells from any writing.","https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7F1T1SSJSW2KVN8JXXBGZNN","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7F1SXXN9RHQNWNG3JFBPZW0","technical-writing","Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for \u002Ftechnical-writing or $technical-writing, or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.","https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftechnical-writing\u002FSKILL.md",[],[]]