[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M755ES8KW0306XX82VJHMJNJ":3,"skill-same:01M755ES8KW0306XX82VJHMJNJ":52},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M755ES8KW0306XX82VJHMJNJ","stacked",null,"Decompose LARGE, complex, or risky changes into a stack of small, dependent, independently reviewable units. Use only when the change is genuinely big: multiple architectural layers with functionally distinct concerns (models + storage + logic + API + UI), or a diff too large to review as one unit. Trigger on \"stacked\" \u002F \"stacked PRs\" \u002F \"stack this\" \u002F how to break down a large change — or when a \"build X\" \u002F \"refactor W\" request is clearly multi-layer and large. Do NOT use for small or moderate changes: bug fixes, tweaks, config, single-file or single-layer changes belong on ONE branch as ONE change — a stack of tiny branches adds overhead without value.","auth-02\u002Fhub","auth-02","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F146264364?v=4","01M755DW6DVATA25MM8323VK52","Atharva Shinde","01M755DW7CDZNCA30JT6VP7MQ5",3,"MIT","https:\u002F\u002Fgithub.com\u002Fauth-02\u002Fhub\u002Fblob\u002Fmain\u002Fhubspace\u002Fplugin\u002Fhub-agent\u002Fskills\u002Fstacked\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: stacked\ndescription: >\n  Decompose LARGE, complex, or risky changes into a stack of small, dependent, independently reviewable units. Use only when the change is genuinely big: multiple architectural layers with functionally distinct concerns (models + storage + logic + API + UI), or a diff too large to review as one unit. Trigger on \"stacked\" \u002F \"stacked PRs\" \u002F \"stack this\" \u002F how to break down a large change — or when a \"build X\" \u002F \"refactor W\" request is clearly multi-layer and large. Do NOT use for small or moderate changes: bug fixes, tweaks, config, single-file or single-layer changes belong on ONE branch as ONE change — a stack of tiny branches adds overhead without value.\n---\n\n# Stacked\n\nDecompose work into a stack of small, dependent, reviewable changes. Each change has a single responsibility and builds on the one below it.\n\n---\n\n## When to Use\n\nStack only when **all** of these hold:\n\n- The change is large — too big to review comfortably as a single unit\n- It spans multiple architectural layers with **functionally distinct** concerns\n- Each layer would carry substantial, self-contained work worth its own review\n\n## When NOT to Use\n\nDefault to a **single branch, single change** for:\n\n- Bug fixes, tweaks, styling adjustments, config or copy changes\n- Single-file or single-layer changes, however \"multi-step\" the edit feels\n- Small features a reviewer can absorb in one sitting\n- Related small changes — batch them into one coherent change rather than one branch each\n\nA stack of tiny branches is worse than one clear change: it multiplies review, CI, and merge overhead without improving reviewability. The size of the change decides, not the number of steps it took to write.\n\n---\n\n## Core Principle\n\nPrefer a stack of small changes over one massive change — and prefer one plain change over an unnecessary stack. Stacking is a tool for taming size, not a default workflow.\n\n```\nSmall Change   ← top (depends on everything below)\n    ↑\nSmall Change\n    ↑\nSmall Change\n    ↑\nSmall Change   ← bottom (no dependencies)\n```\n\nImplement from the **bottom up**. Review from the **bottom up**.\n\n---\n\n## Decomposition Strategy\n\nBefore writing any code:\n\n1. Understand the complete scope\n2. Identify architectural boundaries\n3. Separate concerns\n4. Build a proposed stack\n5. Validate each layer has a single responsibility\n\nThink in terms of:\n\n- **Data structures** — types, models, schemas\n- **Persistence** — storage, migrations, indexes\n- **Domain logic** — business rules, transformations\n- **Tools \u002F Services** — utilities, clients, adapters\n- **Workflows** — orchestration, pipelines, agents\n- **API** — interfaces, contracts, endpoints\n- **UI** — presentation, interaction\n\nNot every feature requires every layer.\n\n---\n\n## Preferred Layering Order\n\n```\nTypes \u002F Models\n      ↓\n  Persistence\n      ↓\n Domain Logic\n      ↓\nTools \u002F Services\n      ↓\n  Workflows\n      ↓\n     API\n      ↓\n      UI\n```\n\nHigher layers depend on lower layers. Lower layers must not depend on higher layers.\n\n---\n\n## Naming\n\nName each change by **capability and responsibility** — not sequence.\n\n**Good:**\n```\nsearch\u002Findexing\nsearch\u002Fretrieval\nsearch\u002Franking\nsearch\u002Fapi\n\ndoc-parser\u002Fcore\ndoc-parser\u002Fchunking\ndoc-parser\u002Findexing\ndoc-parser\u002Fworkflow\n\nchat\u002Fsession-model\nchat\u002Fhistory-store\nchat\u002Fcontext-builder\nchat\u002Fagent\n```\n\n**Avoid:**\n```\npart-1\npart-2\nfinal\nmisc\nchanges\n```\n\nNames should explain what a change does without requiring additional context.\n\n---\n\n## Reviewability Rule\n\nEach change should answer **a single question**:\n\n> Does [this specific thing] look correct?\n\nExamples:\n- \"Does the indexing model look correct?\"\n- \"Does the retrieval implementation look correct?\"\n- \"Does the workflow orchestration look correct?\"\n\nIf a reviewer must answer multiple unrelated questions, the change is too large. Split it.\n\n---\n\n## Agent Behavior\n\n1. **Plan the full stack first** — propose it before writing any code\n2. **Explain the proposed stack** — show names, dependencies, and responsibilities\n3. **Implement bottom-up** — start with the lowest-dependency layer\n4. **Keep responsibilities isolated** — no mixing of architectural layers within a change\n5. **Avoid unrelated refactors** — scope each change tightly\n6. **Prefer incremental progress** — don't bundle work to seem efficient\n7. **Write into the manifest** — when a manifest exists for this task (`tasks\u002F\u003Cslug>\u002Fmanifest.md`), write the stack into its `## Stack` section rather than presenting it only in chat. The manifest is the canonical record; chat is ephemeral. Update layer `Status` cells as PRs open and merge.\n\nWhen uncertain whether the change is big enough to warrant a stack: **don't stack it — ship it as one change.** Only once you're inside a genuinely large stack and uncertain whether a layer is doing two jobs: split that layer.\n\nSizing floor: never create a layer that a reviewer would read in under a couple of minutes and think \"why is this its own PR?\" Merge such fragments into the adjacent layer they belong to.\n\n---\n\n## Output Format\n\nWhen proposing a stack, present it clearly:\n\n```\nfeature-name\u002Flayer-one       ← implement first\n      ↑\nfeature-name\u002Flayer-two\n      ↑\nfeature-name\u002Flayer-three\n      ↑\nfeature-name\u002Flayer-four      ← implement last\n```\n\nFor each layer, briefly state:\n- **What it does** (one sentence)\n- **What it depends on** (prior layers, if any)\n- **Why it's its own change** (the single reviewable question)\n\n---\n\n## Example\n\n**User request:** Build a document intelligence pipeline that can parse, chunk, index, and search documents.\n\n**Proposed stack:**\n\n```\ndoc-intelligence\u002Fmodels          ← types and schemas\n        ↑\ndoc-intelligence\u002Fparser          ← raw document ingestion\n        ↑\ndoc-intelligence\u002Fchunking        ← splitting and segmentation logic\n        ↑\ndoc-intelligence\u002Findexing        ← storage and index construction\n        ↑\ndoc-intelligence\u002Fsearch          ← retrieval and ranking\n        ↑\ndoc-intelligence\u002Fworkflow        ← end-to-end orchestration\n```\n\nEach layer has one job. Each layer can be reviewed independently. The story is clear from bottom to top.\n\n---\n\n## Success Criteria\n\nA stack is successful when:\n\n- Each change has one responsibility\n- Dependencies are obvious from the names and order\n- Changes are independently reviewable\n- The implementation story is clear from bottom to top\n- Testing can happen incrementally\n- Merging can happen incrementally\n- A reviewer can understand the full stack without confusion\n\n---\n\n## Worked example (in `examples\u002F`)\n\n`examples\u002Fnotifications-system.md` is a worked example showing how a **complex** feature — an in-app notifications system spanning schema, storage, delivery, API, and UI — decomposes into one tight bottom-up stack. Only the Stack section is shown: each layer's responsibility, its dependency on the layer below, the single reviewable question it answers, and its status. Note how even a large, multi-concern feature reduces to a short ladder where each layer is independently reviewable and nothing above can be built until the layer below it is tested.\n","# Stacked\n\nDecompose work into a stack of small, dependent, reviewable changes. Each change has a single responsibility and builds on the one below it.\n\n---\n\n## When to Use\n\nStack only when **all** of these hold:\n\n- The change is large — too big to review comfortably as a single unit\n- It spans multiple architectural layers with **functionally distinct** concerns\n- Each layer would carry substantial, self-contained work worth its own review\n\n## When NOT to Use\n\nDefault to a **single branch, single change** for:\n\n- Bug fixes, tweaks, styling adjustments, config or copy changes\n- Single-file or single-layer changes, however \"multi-step\" the edit feels\n- Small features a reviewer can absorb in one sitting\n- Related small changes — batch them into one coherent change rather than one branch each\n\nA stack of tiny branches is worse than one clear change: it multiplies review, CI, and merge overhead without improving reviewability. The size of the change decides, not the number of steps it took to write.\n\n---\n\n## Core Principle\n\nPrefer a stack of small changes over one massive change — and prefer one plain change over an unnecessary stack. Stacking is a tool for taming size, not a default workflow.\n\n```\nSmall Change   ← top (depends on everything below)\n    ↑\nSmall Change\n    ↑\nSmall Change\n    ↑\nSmall Change   ← bottom (no dependencies)\n```\n\nImplement from the **bottom up**. Review from the **bottom up**.\n\n---\n\n## Decomposition Strategy\n\nBefore writing any code:\n\n1. Understand the complete scope\n2. Identify architectural boundaries\n3. Separate concerns\n4. Build a proposed stack\n5. Validate each layer has a single responsibility\n\nThink in terms of:\n\n- **Data structures** — types, models, schemas\n- **Persistence** — storage, migrations, indexes\n- **Domain logic** — business rules, transformations\n- **Tools \u002F Services** — utilities, clients, adapters\n- **Workflows** — orchestration, pipelines, agents\n- **API** — interfaces, contracts, endpoints\n- **UI** — presentation, interaction\n\nNot every feature requires every layer.\n\n---\n\n## Preferred Layering Order\n\n```\nTypes \u002F Models\n      ↓\n  Persistence\n      ↓\n Domain Logic\n      ↓\nTools \u002F Services\n      ↓\n  Workflows\n      ↓\n     API\n      ↓\n      UI\n```\n\nHigher layers depend on lower layers. Lower layers must not depend on higher layers.\n\n---\n\n## Naming\n\nName each change by **capability and responsibility** — not sequence.\n\n**Good:**\n```\nsearch\u002Findexing\nsearch\u002Fretrieval\nsearch\u002Franking\nsearch\u002Fapi\n\ndoc-parser\u002Fcore\ndoc-parser\u002Fchunking\ndoc-parser\u002Findexing\ndoc-parser\u002Fworkflow\n\nchat\u002Fsession-model\nchat\u002Fhistory-store\nchat\u002Fcontext-builder\nchat\u002Fagent\n```\n\n**Avoid:**\n```\npart-1\npart-2\nfinal\nmisc\nchanges\n```\n\nNames should explain what a change does without requiring additional context.\n\n---\n\n## Reviewability Rule\n\nEach change should answer **a single question**:\n\n> Does [this specific thing] look correct?\n\nExamples:\n- \"Does the indexing model look correct?\"\n- \"Does the retrieval implementation look correct?\"\n- \"Does the workflow orchestration look correct?\"\n\nIf a reviewer must answer multiple unrelated questions, the change is too large. Split it.\n\n---\n\n## Agent Behavior\n\n1. **Plan the full stack first** — propose it before writing any code\n2. **Explain the proposed stack** — show names, dependencies, and responsibilities\n3. **Implement bottom-up** — start with the lowest-dependency layer\n4. **Keep responsibilities isolated** — no mixing of architectural layers within a change\n5. **Avoid unrelated refactors** — scope each change tightly\n6. **Prefer incremental progress** — don't bundle work to seem efficient\n7. **Write into the manifest** — when a manifest exists for this task (`tasks\u002F\u003Cslug>\u002Fmanifest.md`), write the stack into its `## Stack` section rather than presenting it only in chat. The manifest is the canonical record; chat is ephemeral. Update layer `Status` cells as PRs open and merge.\n\nWhen uncertain whether the change is big enough to warrant a stack: **don't stack it — ship it as one change.** Only once you're inside a genuinely large stack and uncertain whether a layer is doing two jobs: split that layer.\n\nSizing floor: never create a layer that a reviewer would read in under a couple of minutes and think \"why is this its own PR?\" Merge such fragments into the adjacent layer they belong to.\n\n---\n\n## Output Format\n\nWhen proposing a stack, present it clearly:\n\n```\nfeature-name\u002Flayer-one       ← implement first\n      ↑\nfeature-name\u002Flayer-two\n      ↑\nfeature-name\u002Flayer-three\n      ↑\nfeature-name\u002Flayer-four      ← implement last\n```\n\nFor each layer, briefly state:\n- **What it does** (one sentence)\n- **What it depends on** (prior layers, if any)\n- **Why it's its own change** (the single reviewable question)\n\n---\n\n## Example\n\n**User request:** Build a document intelligence pipeline that can parse, chunk, index, and search documents.\n\n**Proposed stack:**\n\n```\ndoc-intelligence\u002Fmodels          ← types and schemas\n        ↑\ndoc-intelligence\u002Fparser          ← raw document ingestion\n        ↑\ndoc-intelligence\u002Fchunking        ← splitting and segmentation logic\n        ↑\ndoc-intelligence\u002Findexing        ← storage and index construction\n        ↑\ndoc-intelligence\u002Fsearch          ← retrieval and ranking\n        ↑\ndoc-intelligence\u002Fworkflow        ← end-to-end orchestration\n```\n\nEach layer has one job. Each layer can be reviewed independently. The story is clear from bottom to top.\n\n---\n\n## Success Criteria\n\nA stack is successful when:\n\n- Each change has one responsibility\n- Dependencies are obvious from the names and order\n- Changes are independently reviewable\n- The implementation story is clear from bottom to top\n- Testing can happen incrementally\n- Merging can happen incrementally\n- A reviewer can understand the full stack without confusion\n\n---\n\n## Worked example (in `examples\u002F`)\n\n`examples\u002Fnotifications-system.md` is a worked example showing how a **complex** feature — an in-app notifications system spanning schema, storage, delivery, API, and UI — decomposes into one tight bottom-up stack. Only the Stack section is shown: each layer's responsibility, its dependency on the layer below, the single reviewable question it answers, and its status. Note how even a large, multi-concern feature reduces to a short ladder where each layer is independently reviewable and nothing above can be built until the layer below it is tested.\n",{"name":5,"description":7},"main","dc89ede1053a613e8f3cbe025b605a2486ffb8c1","hubspace\u002Fplugin\u002Fhub-agent\u002Fskills\u002Fstacked",0,"https:\u002F\u002Fgithub.com\u002Fauth-02\u002Fhub","https:\u002F\u002Fauth-02.github.io\u002Fhub\u002F","https:\u002F\u002Fgithub.com\u002Fauth-02","2026-08-12 15:23:18",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add auth-02\u002Fhub --skill stacked",{"tool":38,"command":39},"bunx","bunx skills add auth-02\u002Fhub --skill stacked",{"tool":41,"command":42},"pnpm","pnpm dlx skills add auth-02\u002Fhub --skill stacked","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fauth-02\u002Fhub\u002Fblob\u002Fmain\u002Fhubspace\u002Fplugin\u002Fhub-agent\u002Fskills\u002Fstacked\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"examples\u002Fnotifications-system.md","REFERENCE","参考文档",2009,"https:\u002F\u002Fgithub.com\u002Fauth-02\u002Fhub\u002Fblob\u002Fmain\u002Fhubspace\u002Fplugin\u002Fhub-agent\u002Fskills\u002Fstacked\u002Fexamples\u002Fnotifications-system.md",[53,60,67,73,80,86],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M755EKGJEC3AXNZJ1T1C6582","manifest","Use when starting a non-trivial feature, migration, refactor, or multi-step task in ANY repo. Creates and continuously maintains a living markdown manifest at `\u003Crepo-root>\u002Ftasks\u002F\u003Cslug>\u002Fmanifest.md` (inside the repo being worked on — NEVER the skill dir or ~\u002F) capturing the problem, decisions, exploration results, plan, open questions, test + rollout plans, and final review. Trigger on \"build X\", \"add X\", \"migrate X\", \"refactor X\", tasks needing 3+ steps, or whenever a plan-before-code loop would help. NOT for single-line fixes, obvious bugs, or one-shot questions.","https:\u002F\u002Fgithub.com\u002Fauth-02\u002Fhub\u002Fblob\u002Fmain\u002Fhubspace\u002Fplugin\u002Fhub-agent\u002Fskills\u002Fmanifest\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M755EBMJGHXN2WGF9T0RG755","kagaz","Kagaz (कागज़) — a personal design system for all frontend and document work — editorial-technical-archival, serif display + mono metadata on warm paper tones with a single rust accent. Use for ANY frontend, UI, web page, landing page, dashboard, artifact, component, mockup, poster, slide deck, report, or PDF\u002Fdocument design, for HTML→PDF conversion, and for any \"make this look good\" \u002F \"style this\" \u002F \"make slides\" \u002F \"turn this into a PDF\" request — even when no design preference is mentioned. Overrides generic AI defaults (Inter-on-white, purple gradients, cool grays). Ships an HTML-to-PDF converter with visual QA and on-brand SVG charts.","https:\u002F\u002Fgithub.com\u002Fauth-02\u002Fhub\u002Fblob\u002Fmain\u002Fhubspace\u002Fplugin\u002Fhub-agent\u002Fskills\u002Fkagaz\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M755E9RR0Q8FNNXS5XKY88AZ","dak","https:\u002F\u002Fgithub.com\u002Fauth-02\u002Fhub\u002Fblob\u002Fmain\u002Fhubspace\u002Fplugin\u002Fhub-agent\u002Fskills\u002Fdak\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M755E0WG3N8XGTS291CWECCE","change-log","Map a task's changes as an editable draw that renders an interactive change-map on Save — nodes are functional CHANGES (a capability that moved), arrows are dependencies, and clicking a change deep-dives into its file \u002F function \u002F test detail in a side inspector. Use when someone asks \"what changed\", \"map this change\", \"diagram this PR\u002Fbranch\", \"show how the changes connect\", or as the closing step of a task once code has landed. Reads the diff + the task's manifest (the *why*) + Hub's MCP task context, then writes ONE `.excalidraw` into `tasks\u002F\u003Cslug>\u002Fchange-log\u002F`; the user edits it and Saving renders the sibling HTML. The agent does the reading — Hub has no model. `\u002Fchange-log \u003Ctask-slug> [--since \u003Cref>] [--doc]`.","https:\u002F\u002Fgithub.com\u002Fauth-02\u002Fhub\u002Fblob\u002Fmain\u002Fhubspace\u002Fplugin\u002Fhub-agent\u002Fskills\u002Fchange-log\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":6,"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},"01M755DZDR0YRNBDE7RXEFDAXA","auth","https:\u002F\u002Fgithub.com\u002Fauth-02\u002Fhub\u002Fblob\u002Fmain\u002Fexample\u002Fweb-dashboard\u002Fapp\u002Fskills\u002Fauth\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":6,"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},"01M755DY7A7MEMV28B9DYWXAJZ","rate_limiting","https:\u002F\u002Fgithub.com\u002Fauth-02\u002Fhub\u002Fblob\u002Fmain\u002Fexample\u002Facme-api\u002Fapp\u002Fskills\u002Frate_limiting\u002FSKILL.md",[],[]]