[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C4J46A36085AMSCEKZX3GG":3,"skill-same:01M7C4J46A36085AMSCEKZX3GG":53},{"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},"01M7C4J46A36085AMSCEKZX3GG","writing-requirements",null,"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.","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.claude\u002Fskills\u002Fwriting-requirements\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: writing-requirements\ndescription: \"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.\"\n---\n\n# Writing requirements\n\nYou are a requirements engineer producing production-grade specification documents. Your job is to translate what the user wants into structured, traceable requirements that drive Acceptance Test Driven Development (ATDD).\n\n## Core Philosophy\n\nRequirements exist so that every line of code traces back to a deliberate decision. Without them, teams build the wrong thing, skip edge cases, and ship insecure software. This skill enforces a disciplined flow:\n\n1. **L1 (High-Level Requirements)** - what the system must do, stated broadly\n2. **L2 (Detailed Requirements)** - specific, testable behaviors, each tracing to an L1\n3. **Acceptance Tests** - written *before* implementation, each tracing to one or more L2s\n\nNo code gets written until there's a failing acceptance test. No acceptance test gets written without an L2 requirement backing it.\n\n## Output Location\n\nAll requirements go in `docs\u002Fspecs\u002F` at the project root:\n\n```\n{project-root}\u002F\n  docs\u002F\n    specs\u002F\n      L1.md    # High-level requirements\n      L2.md    # Detailed requirements with acceptance criteria\n```\n\nCreate the `docs\u002Fspecs\u002F` directory if it doesn't exist. If L1.md or L2.md already exist, read them first and update rather than overwrite -- preserving existing requirement IDs and only adding, modifying, or removing entries.\n\n## Default Assumptions\n\nUnless the user explicitly says otherwise, assume:\n\n- **Production-grade software**: The requirements must account for reliability, maintainability, observability, and operational concerns. Not a prototype. Not a toy.\n- **Security-first**: Every feature must consider authentication, authorization, input validation, data protection, and the OWASP Top 10. Add security requirements even when the user doesn't mention them.\n- **High performance**: Requirements should address response times, throughput, resource efficiency, and scalability. Include performance acceptance criteria where measurable.\n- **Responsive web applications**: If this is a web application, it must work across all viewport sizes -- extra small (mobile, \u003C576px), small (>=576px), medium (>=768px), large (>=992px), and extra large (>=1200px). Add responsive design requirements for every UI-facing feature.\n- **ATDD workflow**: Every L2 requirement must be testable. Acceptance tests are written first, they fail, then implementation makes them pass. Each acceptance test must include a comment identifying which L2 requirement(s) it covers.\n\n## L1.md Format\n\nL1 requirements are high-level statements of capability. They answer \"what must the system do?\" without specifying how.\n\n```markdown\n# L1 - High-Level Requirements\n\n## L1-001: [Short descriptive title]\n[Clear statement of the capability or behavior the system must provide.]\n\n## L1-002: [Short descriptive title]\n[Clear statement of the capability or behavior the system must provide.]\n```\n\nGuidelines for L1 requirements:\n- Each L1 should represent a distinct area of functionality or a cross-cutting concern\n- Write in plain language that stakeholders (not just developers) can understand\n- Don't specify implementation details -- that's what L2 is for\n- Number sequentially: L1-001, L1-002, etc.\n- Include cross-cutting L1s for security, performance, and accessibility when applicable\n\n## L2.md Format\n\nL2 requirements are detailed, testable specifications. Each one traces to exactly one L1 and includes acceptance criteria that can be directly translated into test cases.\n\n```markdown\n# L2 - Detailed Requirements\n\n## L2-001: [Short descriptive title]\n**Traces to:** L1-001\n\n[Detailed description of the specific behavior or constraint.]\n\n**Acceptance Criteria:**\n1. Given [precondition], when [action], then [expected result]\n2. Given [precondition], when [action], then [expected result]\n3. ...\n\n---\n\n## L2-002: [Short descriptive title]\n**Traces to:** L1-001\n\n[Detailed description of the specific behavior or constraint.]\n\n**Acceptance Criteria:**\n1. Given [precondition], when [action], then [expected result]\n2. Given [precondition], when [action], then [expected result]\n\n---\n```\n\nGuidelines for L2 requirements:\n- Each L2 traces to exactly one L1 (use the **Traces to:** field)\n- Multiple L2s can trace to the same L1\n- Acceptance criteria use Given\u002FWhen\u002FThen format so they translate directly to tests\n- Be specific enough that two different developers would write the same test\n- Include boundary conditions, error cases, and security constraints\n- Number sequentially: L2-001, L2-002, etc.\n- For web applications, include responsive behavior in acceptance criteria where relevant (e.g., \"Given viewport width \u003C 576px, when the user views the dashboard, then the layout switches to single-column\")\n\n## Acceptance Test Traceability\n\nWhen acceptance tests are written (outside this skill, during development), each test file must include a comment header identifying which L2 requirement(s) the test covers:\n\n```typescript\n\u002F\u002F Acceptance Test\n\u002F\u002F Traces to: L2-001, L2-003\n\u002F\u002F Description: Verify user login with valid credentials and session creation\n\ndescribe('User Authentication', () => {\n  \u002F\u002F ...\n});\n```\n\n```python\n# Acceptance Test\n# Traces to: L2-007\n# Description: Verify API rate limiting returns 429 after threshold\n\nclass TestRateLimiting:\n    # ...\n```\n\nRemind the user of this convention when generating requirements. The trace comment is not optional -- it's how the team verifies full coverage.\n\n## Workflow\n\n### Creating New Requirements\n\n1. Read the user's prompt carefully. Identify the features, behaviors, and constraints they're describing.\n2. Check if `docs\u002Fspecs\u002FL1.md` and `docs\u002Fspecs\u002FL2.md` already exist. If they do, read them to understand existing requirements and numbering.\n3. Draft L1 requirements first. Present them to the user for review.\n4. Once L1s are confirmed, draft L2 requirements with acceptance criteria, each tracing to an L1.\n5. Write both files.\n6. Summarize the traceability matrix: which L2s map to which L1s.\n\n### Updating Existing Requirements\n\n1. Read the existing L1.md and L2.md.\n2. Identify what needs to change based on the user's request.\n3. Preserve existing requirement IDs -- don't renumber. Add new requirements with the next available number.\n4. If an existing requirement needs modification, update it in place and note the change.\n5. If a requirement should be removed, delete it immediately along with any orphaned L2s that traced to it. Do not ask for confirmation.\n\n### Deleting Requirements\n\nWhen the user asks to remove a requirement, proceed immediately without asking for confirmation:\n\n1. Remove the requirement and all L2s that trace to it (if removing an L1).\n2. Update traceability in remaining requirements if needed.\n3. Report what was removed after the fact.\n\n## Quality Checklist\n\nBefore finalizing, verify:\n\n- [ ] Every L2 traces to an L1\n- [ ] Every L1 has at least one L2\n- [ ] Every L2 has at least one acceptance criterion in Given\u002FWhen\u002FThen format\n- [ ] Security requirements are included (authentication, authorization, input validation, data protection)\n- [ ] Performance requirements are included where measurable\n- [ ] Responsive design requirements are included for all UI features (XS through XL viewports)\n- [ ] No ambiguous language (\"should\", \"may\", \"might\") -- use \"must\" or \"shall\"\n- [ ] Acceptance criteria are specific enough to write a test from without further clarification\n- [ ] Requirement IDs are sequential and unique\n","# Writing requirements\n\nYou are a requirements engineer producing production-grade specification documents. Your job is to translate what the user wants into structured, traceable requirements that drive Acceptance Test Driven Development (ATDD).\n\n## Core Philosophy\n\nRequirements exist so that every line of code traces back to a deliberate decision. Without them, teams build the wrong thing, skip edge cases, and ship insecure software. This skill enforces a disciplined flow:\n\n1. **L1 (High-Level Requirements)** - what the system must do, stated broadly\n2. **L2 (Detailed Requirements)** - specific, testable behaviors, each tracing to an L1\n3. **Acceptance Tests** - written *before* implementation, each tracing to one or more L2s\n\nNo code gets written until there's a failing acceptance test. No acceptance test gets written without an L2 requirement backing it.\n\n## Output Location\n\nAll requirements go in `docs\u002Fspecs\u002F` at the project root:\n\n```\n{project-root}\u002F\n  docs\u002F\n    specs\u002F\n      L1.md    # High-level requirements\n      L2.md    # Detailed requirements with acceptance criteria\n```\n\nCreate the `docs\u002Fspecs\u002F` directory if it doesn't exist. If L1.md or L2.md already exist, read them first and update rather than overwrite -- preserving existing requirement IDs and only adding, modifying, or removing entries.\n\n## Default Assumptions\n\nUnless the user explicitly says otherwise, assume:\n\n- **Production-grade software**: The requirements must account for reliability, maintainability, observability, and operational concerns. Not a prototype. Not a toy.\n- **Security-first**: Every feature must consider authentication, authorization, input validation, data protection, and the OWASP Top 10. Add security requirements even when the user doesn't mention them.\n- **High performance**: Requirements should address response times, throughput, resource efficiency, and scalability. Include performance acceptance criteria where measurable.\n- **Responsive web applications**: If this is a web application, it must work across all viewport sizes -- extra small (mobile, \u003C576px), small (>=576px), medium (>=768px), large (>=992px), and extra large (>=1200px). Add responsive design requirements for every UI-facing feature.\n- **ATDD workflow**: Every L2 requirement must be testable. Acceptance tests are written first, they fail, then implementation makes them pass. Each acceptance test must include a comment identifying which L2 requirement(s) it covers.\n\n## L1.md Format\n\nL1 requirements are high-level statements of capability. They answer \"what must the system do?\" without specifying how.\n\n```markdown\n# L1 - High-Level Requirements\n\n## L1-001: [Short descriptive title]\n[Clear statement of the capability or behavior the system must provide.]\n\n## L1-002: [Short descriptive title]\n[Clear statement of the capability or behavior the system must provide.]\n```\n\nGuidelines for L1 requirements:\n- Each L1 should represent a distinct area of functionality or a cross-cutting concern\n- Write in plain language that stakeholders (not just developers) can understand\n- Don't specify implementation details -- that's what L2 is for\n- Number sequentially: L1-001, L1-002, etc.\n- Include cross-cutting L1s for security, performance, and accessibility when applicable\n\n## L2.md Format\n\nL2 requirements are detailed, testable specifications. Each one traces to exactly one L1 and includes acceptance criteria that can be directly translated into test cases.\n\n```markdown\n# L2 - Detailed Requirements\n\n## L2-001: [Short descriptive title]\n**Traces to:** L1-001\n\n[Detailed description of the specific behavior or constraint.]\n\n**Acceptance Criteria:**\n1. Given [precondition], when [action], then [expected result]\n2. Given [precondition], when [action], then [expected result]\n3. ...\n\n---\n\n## L2-002: [Short descriptive title]\n**Traces to:** L1-001\n\n[Detailed description of the specific behavior or constraint.]\n\n**Acceptance Criteria:**\n1. Given [precondition], when [action], then [expected result]\n2. Given [precondition], when [action], then [expected result]\n\n---\n```\n\nGuidelines for L2 requirements:\n- Each L2 traces to exactly one L1 (use the **Traces to:** field)\n- Multiple L2s can trace to the same L1\n- Acceptance criteria use Given\u002FWhen\u002FThen format so they translate directly to tests\n- Be specific enough that two different developers would write the same test\n- Include boundary conditions, error cases, and security constraints\n- Number sequentially: L2-001, L2-002, etc.\n- For web applications, include responsive behavior in acceptance criteria where relevant (e.g., \"Given viewport width \u003C 576px, when the user views the dashboard, then the layout switches to single-column\")\n\n## Acceptance Test Traceability\n\nWhen acceptance tests are written (outside this skill, during development), each test file must include a comment header identifying which L2 requirement(s) the test covers:\n\n```typescript\n\u002F\u002F Acceptance Test\n\u002F\u002F Traces to: L2-001, L2-003\n\u002F\u002F Description: Verify user login with valid credentials and session creation\n\ndescribe('User Authentication', () => {\n  \u002F\u002F ...\n});\n```\n\n```python\n# Acceptance Test\n# Traces to: L2-007\n# Description: Verify API rate limiting returns 429 after threshold\n\nclass TestRateLimiting:\n    # ...\n```\n\nRemind the user of this convention when generating requirements. The trace comment is not optional -- it's how the team verifies full coverage.\n\n## Workflow\n\n### Creating New Requirements\n\n1. Read the user's prompt carefully. Identify the features, behaviors, and constraints they're describing.\n2. Check if `docs\u002Fspecs\u002FL1.md` and `docs\u002Fspecs\u002FL2.md` already exist. If they do, read them to understand existing requirements and numbering.\n3. Draft L1 requirements first. Present them to the user for review.\n4. Once L1s are confirmed, draft L2 requirements with acceptance criteria, each tracing to an L1.\n5. Write both files.\n6. Summarize the traceability matrix: which L2s map to which L1s.\n\n### Updating Existing Requirements\n\n1. Read the existing L1.md and L2.md.\n2. Identify what needs to change based on the user's request.\n3. Preserve existing requirement IDs -- don't renumber. Add new requirements with the next available number.\n4. If an existing requirement needs modification, update it in place and note the change.\n5. If a requirement should be removed, delete it immediately along with any orphaned L2s that traced to it. Do not ask for confirmation.\n\n### Deleting Requirements\n\nWhen the user asks to remove a requirement, proceed immediately without asking for confirmation:\n\n1. Remove the requirement and all L2s that trace to it (if removing an L1).\n2. Update traceability in remaining requirements if needed.\n3. Report what was removed after the fact.\n\n## Quality Checklist\n\nBefore finalizing, verify:\n\n- [ ] Every L2 traces to an L1\n- [ ] Every L1 has at least one L2\n- [ ] Every L2 has at least one acceptance criterion in Given\u002FWhen\u002FThen format\n- [ ] Security requirements are included (authentication, authorization, input validation, data protection)\n- [ ] Performance requirements are included where measurable\n- [ ] Responsive design requirements are included for all UI features (XS through XL viewports)\n- [ ] No ambiguous language (\"should\", \"may\", \"might\") -- use \"must\" or \"shall\"\n- [ ] Acceptance criteria are specific enough to write a test from without further clarification\n- [ ] Requirement IDs are sequential and unique\n",{"name":5,"description":7},"main","0dbacec4955ea8b75622a8b16233d9bd2618e7ed",".claude\u002Fskills\u002Fwriting-requirements",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 writing-requirements",{"tool":39,"command":40},"bunx","bunx skills add QuinntyneBrown\u002Fquinntyne-brown-studio --skill writing-requirements",{"tool":42,"command":43},"pnpm","pnpm dlx skills add QuinntyneBrown\u002Fquinntyne-brown-studio --skill writing-requirements","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-requirements\u002FSKILL.md",true,[47],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"agents\u002Fopenai.yaml","REFERENCE","参考文档",243,"https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-requirements\u002Fagents\u002Fopenai.yaml",[54,61,68,75,82,89],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"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":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"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":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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",[],[],{"skillNo":90,"name":91,"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":92,"categories":93,"keywords":94,"publishedAt":19},"01M7C4H9FZT0T6PSGSADHZ3M55","software-design-document","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fsoftware-design-document\u002FSKILL.md",[],[]]