[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C4F0B6FZPRFNMDMT53PPG9":3,"skill-same:01M7C4F0B6FZPRFNMDMT53PPG9":71},{"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":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7C4F0B6FZPRFNMDMT53PPG9","software-design-document",null,"Generate detailed software design documents from an existing L1\u002FL2 requirements set. Use this skill whenever the user wants to produce design docs, detailed designs, a software design document (SDD), architecture documentation, or per-feature \u002F per-subsystem design write-ups — especially when they mention a docs\u002Fspecs folder, L1\u002FL2 requirements, C4 diagrams, PlantUML, sequence or class diagrams, vertical slices, or a docs\u002Fdetailed-designs folder. Trigger this even when the user only says \"document the design\", \"write up the architecture\", \"turn these requirements into designs\", or \"create the detailed designs\" without naming the format. The skill scaffolds docs\u002Fdetailed-designs\u002F{subsystem}\u002F{feature}\u002F with a README written in a strict house style, plus rendered C4, class, and sequence diagrams shown inline.","QuinntyneBrown\u002Fquinntyne-brown-studio","QuinntyneBrown","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1749159?v=4","01M7C4DEMVW0A87TDN8PMZTNFG","Quinntyne Brown","01M7C4DENDYX1QYZDN3F0A5ZX0",1,"MIT","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsoftware-design-document\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: software-design-document\ndescription: >-\n  Generate detailed software design documents from an existing L1\u002FL2 requirements\n  set. Use this skill whenever the user wants to produce design docs, detailed\n  designs, a software design document (SDD), architecture documentation, or\n  per-feature \u002F per-subsystem design write-ups — especially when they mention a\n  docs\u002Fspecs folder, L1\u002FL2 requirements, C4 diagrams, PlantUML, sequence or class\n  diagrams, vertical slices, or a docs\u002Fdetailed-designs folder. Trigger this even\n  when the user only says \"document the design\", \"write up the architecture\",\n  \"turn these requirements into designs\", or \"create the detailed designs\"\n  without naming the format. The skill scaffolds\n  docs\u002Fdetailed-designs\u002F{subsystem}\u002F{feature}\u002F with a README written in a strict\n  house style, plus rendered C4, class, and sequence diagrams shown inline.\n---\n\n# Software design document\n\nThis skill turns a set of requirements into a browsable tree of detailed feature\ndesigns. The output is deterministic in shape, so a reader always knows where to\nlook:\n\n```\ndocs\u002Fdetailed-designs\u002F\n└── {subsystem}\u002F\n    └── {feature}\u002F\n        ├── README.md          detailed design (renders on GitHub, images inline)\n        └── diagrams\u002F\n            ├── *.puml          PlantUML sources\n            └── *.png           rendered images the README links to\n```\n\nThe design is written **against requirements** — every feature traces back to\nlevel-2 (L2) requirements, which in turn refine level-1 (L1) requirements. That\ntraceability is the reason for the requirements gate below: without L1\u002FL2\nrequirements there is nothing to design against, and inventing them would defeat\nthe purpose.\n\nRead the three references as you reach the steps that need them:\n- `references\u002Fwriting-style.md` — the house voice every README uses.\n- `references\u002Fdiagrams.md` — PlantUML templates for C4, class, and sequence.\n- `references\u002Fexample-design.md` — a complete finished feature to imitate.\n\n---\n\n## Step 0 — Requirements gate (do this first, every time)\n\nA detailed design is a refinement of requirements. If the requirements are not\npresent, stop and ask for them rather than fabricating a design that traces to\nnothing.\n\nCheck for a `docs\u002Fspecs\u002F` folder (relative to the repo root) that contains\nmarkdown holding **both** L1 and L2 requirements. Detect this by searching the\nmarkdown for requirement identifiers at both levels. The level token (`L1`\u002F`L2`)\nand the domain appear in **either order**, and a single spec set may **mix** the\ntwo conventions — treat both as valid:\n\n- level-first: `L1-\u003CDOMAIN>-\u003Cn>`, `L2-\u003CDOMAIN>-\u003Cn>` — e.g. `L1-INTAKE-001`, `L2-CONSENT-002`\n- domain-first: `\u003CDOMAIN>-L1-\u003Cn>`, `\u003CDOMAIN>-L2-\u003Cn>` — e.g. `INTAKE-L1-001`, `CONSENT-L2-002`\n\nSections or tables clearly labelled L1 and L2 also count. This regex catches both\norderings:\n\n```bash\nls docs\u002Fspecs 2>\u002Fdev\u002Fnull && grep -rroE \"(L[12]-[A-Z]+|[A-Z]+-L[12])-[0-9]+\" docs\u002Fspecs | sort -u | head\n```\n\nWhen you read an identifier, parse the **level** (does it contain `L1` or `L2`?)\nand the **domain** (the alphabetic segment on the other side of the level token)\nindependently of their order — `L2-INTAKE-002` and `INTAKE-L2-002` denote the\nsame level and domain. Keep each identifier **exactly as the spec writes it**;\nnever rewrite one convention into the other.\n\n**If `docs\u002Fspecs\u002F` is missing, has no markdown, or shows no recognizable L1 and\nL2 requirements: stop and tell the user.** Say plainly what is needed — a\n`docs\u002Fspecs\u002F` folder of markdown requirements at levels L1 and L2, each with an\nidentifier and L2 tracing to its parent L1 — and do not scaffold anything or\ninvent requirements. This is the one hard stop in the workflow.\n\n## Step 1 — Identify the subsystems\n\nThink of the system as a small number of subsystems (bounded contexts \u002F major\ncapability areas).\n\n- **If `docs\u002Fspecs\u002F` already has one folder per subsystem, reuse those names\n  exactly.** The specs are the source of truth for naming; matching them keeps\n  the two trees aligned and lets a reader move between spec and design without\n  translating names.\n- **Otherwise, infer the subsystems from the specs.** The domain segment of the\n  requirement IDs is a strong signal (`INTAKE`, `CONSENT`, `NFR`, …) — it is the\n  alphabetic segment of the identifier, on whichever side of the `L1`\u002F`L2` token\n  it sits (`L2-INTAKE-002` and `INTAKE-L2-002` both have domain `INTAKE`).\n  Headings and grouping in the spec markdown are further signals. Group related\n  requirements into named subsystems.\n\n## Step 2 — Slice each subsystem into vertical features\n\nWithin a subsystem, split the work into **vertically sliced features**. A\nvertical slice is one user-facing capability that cuts through every layer it\nneeds — UI → API → application\u002Fdomain → data — rather than a horizontal layer\nshared across capabilities. \"Decline an application\" is a vertical slice;\n\"the repository layer\" is not.\n\nGood slices map cleanly onto one or a few L2 requirements and can be described,\ndiagrammed, and reasoned about on their own. Name each slice as a short verb\nphrase (`decline-application`, `record-consent`, `submit-application`).\n\n## Step 3 — Scaffold the folders\n\nFor each subsystem and each of its features, create:\n\n```\ndocs\u002Fdetailed-designs\u002F{subsystem}\u002F{feature}\u002Fdiagrams\u002F\n```\n\nUse the subsystem naming from Step 1 and kebab-case feature names from Step 2.\n\n## Step 4 — Write each feature's README.md\n\nThe detailed-design file **is** the feature folder's `README.md` — GitHub renders\nit automatically and shows the diagram images inline. Use exactly these four\nheadings, in this order, and write all prose in the house voice\n(`references\u002Fwriting-style.md`). `references\u002Fexample-design.md` shows a complete,\nfinished target — imitate its shape.\n\n### Overview\nBackground, assuming the reader knows nothing. Explain what the feature is, why\nit exists, where it sits in the subsystem, and define every local domain term at\nfirst use. A newcomer should be able to read only this section and understand\nwhat the feature is for.\n\n### Description\nThe concrete building blocks of the slice: the components, types, functions, and\nclasses involved, and what each one does. If the codebase already contains these,\ninspect the source and describe what is really there, using the real names. If\nthe feature is greenfield, describe the components the design introduces. Where a\ndetail is genuinely undecided, mark it `\u003CTO SUPPLY>` rather than guessing.\n\n### Requirements\nList **only L2 requirements** — no L1 specs stand on their own here. Present them\nas a table of the L2 identifier, the L1 identifier it refines, and the\nrequirement text:\n\n```markdown\n| L2 ID | Refines (L1) | Requirement |\n|-------|--------------|-------------|\n| `L2-INTAKE-002` | `L1-INTAKE-001` | The system shall record a decline decision with a reason. |\n```\n\nPull the exact text and IDs from `docs\u002Fspecs\u002F`; keep requirement wording in the\n`shall\u002Fshould\u002Fmay` form. Copy each identifier **verbatim** in whatever convention\nthe spec uses — if the specs write `INTAKE-L2-002` \u002F `INTAKE-L1-001`, the table\ncells read `INTAKE-L2-002` and `INTAKE-L1-001`, not a reordered form. Consistency\nwith the source of truth matters more than a uniform house ordering, so that\nevery id in the design still resolves back to a real line in the specs.\n\n### Diagrams\nEmbed the rendered diagrams with a one- or two-sentence prose lead-in before each\n(the prose introduces and interprets the picture; no significant fact should live\nonly inside an image). Reference the **`.png`**, with a relative path, so it shows\ninline:\n\n```markdown\n![C4 component view for declining an application](diagrams\u002Fc4-component.png)\n```\n\nInclude, per feature: the C4 diagrams (context, container, component), a class\ndiagram (structure + relationships), and a sequence diagram per behaviour.\n\n## Step 5 — Author the diagrams\n\nWrite a `.puml` per diagram into the feature's `diagrams\u002F` folder, following\n`references\u002Fdiagrams.md`. The essentials:\n\n- **C4** uses the offline standard library: `!include \u003CC4\u002FC4_Context>`,\n  `\u003CC4\u002FC4_Container>`, `\u003CC4\u002FC4_Component>`. Build the diagram **from the C4 macros\n  that include defines** — `Person(...)`, `System(...)`, `Container(...)`,\n  `Component(...)`, the `*_Boundary(...) { }` blocks, and `Rel(...)` for every\n  relationship. Never draw raw `rectangle`\u002F`component` shapes or bare `a --> b`\n  arrows inside a C4 diagram; that discards the styling and semantics the include\n  exists to give. Scope each diagram to what the feature touches.\n- **Class** diagrams show fields, methods, and typed relationships (association,\n  dependency, inheritance, composition).\n- **Sequence** diagrams show behaviour with `box` groupings that separate\n  **Frontend** from **Backend** and name the specific application\u002Flayer, coloured\n  by tier. The sequence template in `references\u002Fdiagrams.md` is the gold standard;\n  match its skin and box structure. Trace steps to requirement IDs in the message\n  text where a step enforces one.\n\n## Step 6 — Render every diagram to PNG\n\nThe README links to `.png` files, so each `.puml` must have a rendered sibling.\nRender the whole tree with the bundled script (it locates `plantuml.jar` or\n`plantuml` on PATH and writes each `.png` next to its source):\n\n```bash\npython \u003Cskill>\u002Fscripts\u002Frender_puml.py docs\u002Fdetailed-designs\n```\n\nA non-zero exit means at least one diagram failed to render — an image the README\npoints at does not exist. Read the reported error, fix the `.puml`, and re-run\nuntil the exit is clean. (Equivalent direct call if needed:\n`java -jar $PLANTUML_JAR -tpng docs\u002Fdetailed-designs\u002F**\u002Fdiagrams\u002F*.puml`.)\n\n## Step 7 — Verify before finishing\n\n- **Every `.puml` has a `.png`** — the render step exited clean.\n- **Every image link resolves** — each `![...](diagrams\u002Fx.png)` in a README\n  points to a file that exists.\n- **C4 diagrams use the C4 macros** — each C4 `.puml` includes a `\u003CC4\u002F...>`\n  header and is composed of `Person`\u002F`System`\u002F`Container`\u002F`Component`\u002F`Rel` (and\n  boundary) macro calls, with no raw `rectangle`\u002F`component`\u002F`node` shapes or bare\n  arrows standing in for them.\n- **Requirements are L2-only**, each with its L1 parent and exact text from the\n  specs.\n- **Prose passes the house-style self-check** in `references\u002Fwriting-style.md`\n  (no `we`\u002F`you`, obligation only via `shall\u002Fshould\u002Fmay`, no hype or fillers,\n  gaps marked `\u003CTO SUPPLY>` not invented).\n\n## Quality bar\n\nA finished design tree lets a reader open any feature folder on GitHub and see a\nself-contained page: plain-language background, the concrete parts, the L2\nrequirements it satisfies, and diagrams that render inline — all in one steady\nvoice, every claim tracing to a requirement or marked as an open question.\n","# Software design document\n\nThis skill turns a set of requirements into a browsable tree of detailed feature\ndesigns. The output is deterministic in shape, so a reader always knows where to\nlook:\n\n```\ndocs\u002Fdetailed-designs\u002F\n└── {subsystem}\u002F\n    └── {feature}\u002F\n        ├── README.md          detailed design (renders on GitHub, images inline)\n        └── diagrams\u002F\n            ├── *.puml          PlantUML sources\n            └── *.png           rendered images the README links to\n```\n\nThe design is written **against requirements** — every feature traces back to\nlevel-2 (L2) requirements, which in turn refine level-1 (L1) requirements. That\ntraceability is the reason for the requirements gate below: without L1\u002FL2\nrequirements there is nothing to design against, and inventing them would defeat\nthe purpose.\n\nRead the three references as you reach the steps that need them:\n- `references\u002Fwriting-style.md` — the house voice every README uses.\n- `references\u002Fdiagrams.md` — PlantUML templates for C4, class, and sequence.\n- `references\u002Fexample-design.md` — a complete finished feature to imitate.\n\n---\n\n## Step 0 — Requirements gate (do this first, every time)\n\nA detailed design is a refinement of requirements. If the requirements are not\npresent, stop and ask for them rather than fabricating a design that traces to\nnothing.\n\nCheck for a `docs\u002Fspecs\u002F` folder (relative to the repo root) that contains\nmarkdown holding **both** L1 and L2 requirements. Detect this by searching the\nmarkdown for requirement identifiers at both levels. The level token (`L1`\u002F`L2`)\nand the domain appear in **either order**, and a single spec set may **mix** the\ntwo conventions — treat both as valid:\n\n- level-first: `L1-\u003CDOMAIN>-\u003Cn>`, `L2-\u003CDOMAIN>-\u003Cn>` — e.g. `L1-INTAKE-001`, `L2-CONSENT-002`\n- domain-first: `\u003CDOMAIN>-L1-\u003Cn>`, `\u003CDOMAIN>-L2-\u003Cn>` — e.g. `INTAKE-L1-001`, `CONSENT-L2-002`\n\nSections or tables clearly labelled L1 and L2 also count. This regex catches both\norderings:\n\n```bash\nls docs\u002Fspecs 2>\u002Fdev\u002Fnull && grep -rroE \"(L[12]-[A-Z]+|[A-Z]+-L[12])-[0-9]+\" docs\u002Fspecs | sort -u | head\n```\n\nWhen you read an identifier, parse the **level** (does it contain `L1` or `L2`?)\nand the **domain** (the alphabetic segment on the other side of the level token)\nindependently of their order — `L2-INTAKE-002` and `INTAKE-L2-002` denote the\nsame level and domain. Keep each identifier **exactly as the spec writes it**;\nnever rewrite one convention into the other.\n\n**If `docs\u002Fspecs\u002F` is missing, has no markdown, or shows no recognizable L1 and\nL2 requirements: stop and tell the user.** Say plainly what is needed — a\n`docs\u002Fspecs\u002F` folder of markdown requirements at levels L1 and L2, each with an\nidentifier and L2 tracing to its parent L1 — and do not scaffold anything or\ninvent requirements. This is the one hard stop in the workflow.\n\n## Step 1 — Identify the subsystems\n\nThink of the system as a small number of subsystems (bounded contexts \u002F major\ncapability areas).\n\n- **If `docs\u002Fspecs\u002F` already has one folder per subsystem, reuse those names\n  exactly.** The specs are the source of truth for naming; matching them keeps\n  the two trees aligned and lets a reader move between spec and design without\n  translating names.\n- **Otherwise, infer the subsystems from the specs.** The domain segment of the\n  requirement IDs is a strong signal (`INTAKE`, `CONSENT`, `NFR`, …) — it is the\n  alphabetic segment of the identifier, on whichever side of the `L1`\u002F`L2` token\n  it sits (`L2-INTAKE-002` and `INTAKE-L2-002` both have domain `INTAKE`).\n  Headings and grouping in the spec markdown are further signals. Group related\n  requirements into named subsystems.\n\n## Step 2 — Slice each subsystem into vertical features\n\nWithin a subsystem, split the work into **vertically sliced features**. A\nvertical slice is one user-facing capability that cuts through every layer it\nneeds — UI → API → application\u002Fdomain → data — rather than a horizontal layer\nshared across capabilities. \"Decline an application\" is a vertical slice;\n\"the repository layer\" is not.\n\nGood slices map cleanly onto one or a few L2 requirements and can be described,\ndiagrammed, and reasoned about on their own. Name each slice as a short verb\nphrase (`decline-application`, `record-consent`, `submit-application`).\n\n## Step 3 — Scaffold the folders\n\nFor each subsystem and each of its features, create:\n\n```\ndocs\u002Fdetailed-designs\u002F{subsystem}\u002F{feature}\u002Fdiagrams\u002F\n```\n\nUse the subsystem naming from Step 1 and kebab-case feature names from Step 2.\n\n## Step 4 — Write each feature's README.md\n\nThe detailed-design file **is** the feature folder's `README.md` — GitHub renders\nit automatically and shows the diagram images inline. Use exactly these four\nheadings, in this order, and write all prose in the house voice\n(`references\u002Fwriting-style.md`). `references\u002Fexample-design.md` shows a complete,\nfinished target — imitate its shape.\n\n### Overview\nBackground, assuming the reader knows nothing. Explain what the feature is, why\nit exists, where it sits in the subsystem, and define every local domain term at\nfirst use. A newcomer should be able to read only this section and understand\nwhat the feature is for.\n\n### Description\nThe concrete building blocks of the slice: the components, types, functions, and\nclasses involved, and what each one does. If the codebase already contains these,\ninspect the source and describe what is really there, using the real names. If\nthe feature is greenfield, describe the components the design introduces. Where a\ndetail is genuinely undecided, mark it `\u003CTO SUPPLY>` rather than guessing.\n\n### Requirements\nList **only L2 requirements** — no L1 specs stand on their own here. Present them\nas a table of the L2 identifier, the L1 identifier it refines, and the\nrequirement text:\n\n```markdown\n| L2 ID | Refines (L1) | Requirement |\n|-------|--------------|-------------|\n| `L2-INTAKE-002` | `L1-INTAKE-001` | The system shall record a decline decision with a reason. |\n```\n\nPull the exact text and IDs from `docs\u002Fspecs\u002F`; keep requirement wording in the\n`shall\u002Fshould\u002Fmay` form. Copy each identifier **verbatim** in whatever convention\nthe spec uses — if the specs write `INTAKE-L2-002` \u002F `INTAKE-L1-001`, the table\ncells read `INTAKE-L2-002` and `INTAKE-L1-001`, not a reordered form. Consistency\nwith the source of truth matters more than a uniform house ordering, so that\nevery id in the design still resolves back to a real line in the specs.\n\n### Diagrams\nEmbed the rendered diagrams with a one- or two-sentence prose lead-in before each\n(the prose introduces and interprets the picture; no significant fact should live\nonly inside an image). Reference the **`.png`**, with a relative path, so it shows\ninline:\n\n```markdown\n![C4 component view for declining an application](diagrams\u002Fc4-component.png)\n```\n\nInclude, per feature: the C4 diagrams (context, container, component), a class\ndiagram (structure + relationships), and a sequence diagram per behaviour.\n\n## Step 5 — Author the diagrams\n\nWrite a `.puml` per diagram into the feature's `diagrams\u002F` folder, following\n`references\u002Fdiagrams.md`. The essentials:\n\n- **C4** uses the offline standard library: `!include \u003CC4\u002FC4_Context>`,\n  `\u003CC4\u002FC4_Container>`, `\u003CC4\u002FC4_Component>`. Build the diagram **from the C4 macros\n  that include defines** — `Person(...)`, `System(...)`, `Container(...)`,\n  `Component(...)`, the `*_Boundary(...) { }` blocks, and `Rel(...)` for every\n  relationship. Never draw raw `rectangle`\u002F`component` shapes or bare `a --> b`\n  arrows inside a C4 diagram; that discards the styling and semantics the include\n  exists to give. Scope each diagram to what the feature touches.\n- **Class** diagrams show fields, methods, and typed relationships (association,\n  dependency, inheritance, composition).\n- **Sequence** diagrams show behaviour with `box` groupings that separate\n  **Frontend** from **Backend** and name the specific application\u002Flayer, coloured\n  by tier. The sequence template in `references\u002Fdiagrams.md` is the gold standard;\n  match its skin and box structure. Trace steps to requirement IDs in the message\n  text where a step enforces one.\n\n## Step 6 — Render every diagram to PNG\n\nThe README links to `.png` files, so each `.puml` must have a rendered sibling.\nRender the whole tree with the bundled script (it locates `plantuml.jar` or\n`plantuml` on PATH and writes each `.png` next to its source):\n\n```bash\npython \u003Cskill>\u002Fscripts\u002Frender_puml.py docs\u002Fdetailed-designs\n```\n\nA non-zero exit means at least one diagram failed to render — an image the README\npoints at does not exist. Read the reported error, fix the `.puml`, and re-run\nuntil the exit is clean. (Equivalent direct call if needed:\n`java -jar $PLANTUML_JAR -tpng docs\u002Fdetailed-designs\u002F**\u002Fdiagrams\u002F*.puml`.)\n\n## Step 7 — Verify before finishing\n\n- **Every `.puml` has a `.png`** — the render step exited clean.\n- **Every image link resolves** — each `![...](diagrams\u002Fx.png)` in a README\n  points to a file that exists.\n- **C4 diagrams use the C4 macros** — each C4 `.puml` includes a `\u003CC4\u002F...>`\n  header and is composed of `Person`\u002F`System`\u002F`Container`\u002F`Component`\u002F`Rel` (and\n  boundary) macro calls, with no raw `rectangle`\u002F`component`\u002F`node` shapes or bare\n  arrows standing in for them.\n- **Requirements are L2-only**, each with its L1 parent and exact text from the\n  specs.\n- **Prose passes the house-style self-check** in `references\u002Fwriting-style.md`\n  (no `we`\u002F`you`, obligation only via `shall\u002Fshould\u002Fmay`, no hype or fillers,\n  gaps marked `\u003CTO SUPPLY>` not invented).\n\n## Quality bar\n\nA finished design tree lets a reader open any feature folder on GitHub and see a\nself-contained page: plain-language background, the concrete parts, the L2\nrequirements it satisfies, and diagrams that render inline — all in one steady\nvoice, every claim tracing to a requirement or marked as an open question.\n",{"name":5,"description":7},"main","0dbacec4955ea8b75622a8b16233d9bd2618e7ed",".agents\u002Fskills\u002Fsoftware-design-document",0,"https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown","https:\u002F\u002Fquinntynebrown.com","Microsoft Certified Solutions Developer specializing in C#, ASP.NET Core, TypeScript, Azure, Angular, Web Components, RxJS, SignalR Core & Entity Framework Core","2026-10-19 10:28:28",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add QuinntyneBrown\u002Fquinntyne-brown-studio --skill software-design-document",{"tool":39,"command":40},"bunx","bunx skills add QuinntyneBrown\u002Fquinntyne-brown-studio --skill software-design-document",{"tool":42,"command":43},"pnpm","pnpm dlx skills add QuinntyneBrown\u002Fquinntyne-brown-studio --skill software-design-document","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsoftware-design-document\u002FSKILL.md",true,[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"evals\u002Fevals.json","REFERENCE","参考文档",5867,"https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsoftware-design-document\u002Fevals\u002Fevals.json",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fdiagrams.md",10451,"https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsoftware-design-document\u002Freferences\u002Fdiagrams.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fexample-design.md",5228,"https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsoftware-design-document\u002Freferences\u002Fexample-design.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fwriting-style.md",5239,"https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsoftware-design-document\u002Freferences\u002Fwriting-style.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Frender_puml.py","SCRIPT","脚本",4929,"https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsoftware-design-document\u002Fscripts\u002Frender_puml.py",[72,79,86,93,100,107],{"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},"01M7C4JA8SJ18P9JERCKVN799X","writing-screen-composition","Create or update docs\u002Fscreen-composition.md, a document that itemizes every page, dialog, notification and shell part from the HTML mocks and lists, for each, the component-library components it shall be composed of plus the UI that must be built locally. Also ensures AGENTS.md has the \"Components library is mandatory (CRITICAL)\" section. Use when the user mentions screen composition, which components a page uses, mapping mocks to a component library, local vs library UI, or before implementing an application against a component library; and whenever docs\u002Fmocks and a component catalogue exist but docs\u002Fscreen-composition.md does not or is out of date.","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-screen-composition\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},"01M7C4J46A36085AMSCEKZX3GG","writing-requirements","Create and manage software requirements documents (L1 high-level and L2 detailed with acceptance criteria) in docs\u002Fspecs\u002F. Use this skill whenever the user mentions requirements, specs, specifications, user stories, features to build, acceptance criteria, ATDD, or wants to define what a system should do before coding. Also use when the user says things like 'what should we build', 'let's plan the feature', 'write up what this needs to do', 'define the behavior', or describes functionality they want implemented -- even if they don't explicitly say 'requirements'. If the user is about to start coding a feature and there are no requirements yet, proactively suggest using this skill first. Requirements come before code. Always.","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-requirements\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},"01M7C4HWSMCNEE8H922B4W4BT7","writing-html-mocks","Write static HTML mocks in docs\u002Fmocks\u002F for EVERY page, dialog and notification of a product in EVERY state (default, loading, empty, error, invalid, busy, success, no-results, forbidden, stacked...), responsive, light and dark, keyboard-accessible, with real copy and a coverage matrix. Use this skill BEFORE writing any frontend code, component, template, view or page; whenever the user says mock, mockup, wireframe, prototype, UI, UX, screen, layout, dialog, modal, toast, banner, empty\u002Ferror\u002Floading state, \"what should this look like\", \"show me the UI\", or describes a feature with a visible result; and whenever docs\u002Fspecs or docs\u002Fdetailed-designs exist but docs\u002Fmocks does not. Also use it to add missing states to existing mocks. Mocks come before implementation: if asked for frontend code with no mocks, say so and offer this first. Pair with extracting-design-systems to turn finished mocks into docs\u002Fdesign-system\u002F.","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-html-mocks\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},"01M7C4HQZ8AM15WF2PHH3G2BGN","writing-feature-prompts","Write a ready-to-run implementation prompt for a feature request or a bug fix in the current repository, save it outside the repository and open it in a text editor (Notepad on Windows). A feature prompt drives mocks, design system, requirements, detailed design, estimate update and incremental acceptance-test-driven implementation end to end without stopping; a bug-fix prompt drives reproduce, root cause, fix and documentation alignment. Use whenever the user asks to \"create a prompt\", \"write a prompt for this feature\" or \"for this bug\", wants a \"prompt to build X\" or \"prompt to fix Y\", or asks to open a prompt in Notepad.","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-feature-prompts\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7C4HJHMY4ESK2M82BXXJNT9","writing-design-documents","Create software design documents and architecture write-ups from existing L1\u002FL2 requirements in docs\u002Fspecs\u002F. Use for detailed designs organized by subsystem and feature, with requirement traceability and rendered PlantUML C4, class, and sequence diagrams in docs\u002Fdetailed-designs\u002F.","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-design-documents\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7C4HAJZ2JQKS09VASR3XM4T","writing-agent-instructions","Writes the agent instruction files a repository needs so coding agents know how to work in it - AGENTS.md plus the CLAUDE.md, GEMINI.md, and .github\u002Fcopilot-instructions.md pointers - generated from a description of what the project shall be, for a project that does not exist yet. Use this whenever someone mentions AGENTS.md, CLAUDE.md, GEMINI.md, copilot-instructions, \"agent instructions\", \"agent context files\", \"coding agent guidance\", or asks to set up, scaffold, bootstrap, or initialise the conventions for a new project or repository. Use it too when someone describes a project they are about to start and wants an agent to follow its conventions, even if they never name any of these files - if they are standing at an empty directory describing what they intend to build, this is the skill.","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-agent-instructions\u002FSKILL.md",[],[]]