[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74F8AFMASQGZKC75145SBZK":3,"skill-same:01M74F8AFMASQGZKC75145SBZK":146},{"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":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M74F8AFMASQGZKC75145SBZK","create-skill",null,"Expert guidance for creating, writing, building, and refining GSD skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.","open-gsd\u002Fgsd-pi","open-gsd","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F286935422?v=4","01M74F5F0MKW0B81YZHRVJMMWR","Open GSD","01M74F5F1782D325EYEM5GNXNC",1369,"MIT","https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: create-skill\ndescription: Expert guidance for creating, writing, building, and refining GSD skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.\n---\n\n\u003Cessential_principles>\n\n## How Skills Work\n\nSkills are modular, filesystem-based capabilities that provide domain expertise on demand. This skill teaches how to create effective skills.\n\n### 1. Skills Are Prompts\n\nAll prompting best practices apply. Be clear, be direct, use XML structure. Assume Claude is smart - only add context Claude doesn't have.\n\n### 2. SKILL.md Is Always Loaded\n\nWhen a skill is invoked, Claude reads SKILL.md. Use this guarantee:\n\n- Essential principles go in SKILL.md (can't be skipped)\n- Workflow-specific content goes in workflows\u002F\n- Reusable knowledge goes in references\u002F\n\n### 3. Router Pattern for Complex Skills\n\n```\nskill-name\u002F\n├── SKILL.md              # Router + principles\n├── workflows\u002F            # Step-by-step procedures (FOLLOW)\n├── references\u002F           # Domain knowledge (READ)\n├── templates\u002F            # Output structures (COPY + FILL)\n└── scripts\u002F              # Reusable code (EXECUTE)\n```\n\nSKILL.md asks \"what do you want to do?\" → routes to workflow → workflow specifies which references to read.\n\n**When to use each folder:**\n\n- **workflows\u002F** - Multi-step procedures Claude follows\n- **references\u002F** - Domain knowledge Claude reads for context\n- **templates\u002F** - Consistent output structures Claude copies and fills (plans, specs, configs)\n- **scripts\u002F** - Executable code Claude runs as-is (deploy, setup, API calls)\n\n### 4. Pure XML Structure\n\nNo markdown headings (#, ##, ###) in skill body. Use semantic XML tags:\n\n```xml\n\u003Cobjective>...\u003C\u002Fobjective>\n\u003Cprocess>...\u003C\u002Fprocess>\n\u003Csuccess_criteria>...\u003C\u002Fsuccess_criteria>\n```\n\nKeep markdown formatting within content (bold, lists, code blocks).\n\n### 5. Progressive Disclosure\n\nSKILL.md under 500 lines. Split detailed content into reference files. Load only what's needed for the current workflow.\n\u003C\u002Fessential_principles>\n\n\u003Crouting>\n## Understanding User Intent\n\nBased on the user's message, route directly to the appropriate workflow:\n\n**Creating new skills:**\n\n- Domain expertise (exhaustive knowledge base) → **Use `create-domain-expertise` skill instead** (separate skill with batched subagent orchestration)\n- Task-execution skill (does specific things) → workflows\u002Fcreate-new-skill.md\n\n**Working with existing skills:**\n\n- Audit, review, check → workflows\u002Faudit-skill.md\n- Verify content is current → workflows\u002Fverify-skill.md\n- Add workflow → workflows\u002Fadd-workflow.md\n- Add reference → workflows\u002Fadd-reference.md\n- Add template → workflows\u002Fadd-template.md\n- Add script → workflows\u002Fadd-script.md\n- Upgrade to router pattern → workflows\u002Fupgrade-to-router.md\n\n**Need help deciding:**\n\n- General guidance → workflows\u002Fget-guidance.md\n\n**If user intent is unclear, ask minimal clarifying questions:**\n\n- \"Create a MIDI skill\" → \"Task-execution skill (does MIDI tasks) or domain expertise (complete MIDI knowledge base)?\"\n- \"Work on my skill\" → \"Which skill? What do you want to do with it?\"\n- Ask one clarifying question round at a time, then wait for the user's actual response before asking another.\n- Never fabricate or simulate user responses while clarifying (for example, fake `[User]` markers or imagined answers).\n\nThen proceed directly to the workflow.\n\u003C\u002Frouting>\n\n\u003Cquick_reference>\n\n## Skill Structure Quick Reference\n\n**Skill directories:**\n\n- Bundled\u002Fread-only: `~\u002F.gsd\u002Fagent\u002Fskills\u002F{skill-name}\u002F`\n- Global: `~\u002F.agents\u002Fskills\u002F{skill-name}\u002F`\n- Project-local: `.agents\u002Fskills\u002F{skill-name}\u002F`\n\nUser-authored skills should target the global or project-local directories; GSD manages the bundled directory during install\u002Fupdate.\n\n**Simple skill (single file):**\n\n```yaml\n---\nname: skill-name\ndescription: What it does and when to use it.\n---\n\n\u003Cobjective>What this skill does\u003C\u002Fobjective>\n\u003Cquick_start>Immediate actionable guidance\u003C\u002Fquick_start>\n\u003Cprocess>Step-by-step procedure\u003C\u002Fprocess>\n\u003Csuccess_criteria>How to know it worked\u003C\u002Fsuccess_criteria>\n```\n\n**Complex skill (router pattern):**\n\n```\nSKILL.md:\n  \u003Cessential_principles> - Always applies\n  \u003Cintake> - Question to ask\n  \u003Crouting> - Maps answers to workflows\n\nworkflows\u002F:\n  \u003Crequired_reading> - Which refs to load\n  \u003Cprocess> - Steps\n  \u003Csuccess_criteria> - Done when...\n\nreferences\u002F:\n  Domain knowledge, patterns, examples\n\ntemplates\u002F:\n  Output structures Claude copies and fills\n  (plans, specs, configs, documents)\n\nscripts\u002F:\n  Executable code Claude runs as-is\n  (deploy, setup, API calls, data processing)\n```\n\n\u003C\u002Fquick_reference>\n\n\u003Creference_index>\n\n## Domain Knowledge\n\nAll in `references\u002F`:\n\n**Structure:** recommended-structure.md, skill-structure.md\n**Principles:** core-principles.md, be-clear-and-direct.md, use-xml-tags.md\n**Patterns:** common-patterns.md, workflows-and-validation.md\n**Assets:** using-templates.md, using-scripts.md\n**Advanced:** executable-code.md, api-security.md, iteration-and-testing.md\n**GSD-specific:** gsd-skill-ecosystem.md\n\u003C\u002Freference_index>\n\n\u003Cworkflows_index>\n\n## Workflows\n\nAll in `workflows\u002F`:\n\n| Workflow | Purpose |\n|----------|---------|\n| create-new-skill.md | Build a task-execution skill from scratch |\n| audit-skill.md | Analyze skill against best practices |\n| verify-skill.md | Check if content is still accurate |\n| add-workflow.md | Add a workflow to existing skill |\n| add-reference.md | Add a reference to existing skill |\n| add-template.md | Add a template to existing skill |\n| add-script.md | Add a script to existing skill |\n| upgrade-to-router.md | Convert simple skill to router pattern |\n| get-guidance.md | Help decide what kind of skill to build |\n\u003C\u002Fworkflows_index>\n\n\u003Cyaml_requirements>\n\n## YAML Frontmatter\n\nRequired fields:\n\n```yaml\n---\nname: skill-name          # lowercase-with-hyphens, matches directory\ndescription: ...          # What it does AND when to use it (third person)\n---\n```\n\nFrontmatter must parse as YAML. Quote description values containing `:` or use\na folded block (`description: >`) for longer trigger descriptions.\n\nName conventions: `create-*`, `manage-*`, `setup-*`, `generate-*`, `build-*`\n\u003C\u002Fyaml_requirements>\n\n\u003Csuccess_criteria>\nA well-structured skill:\n\n- Has valid YAML frontmatter\n- Uses pure XML structure (no markdown headings in body)\n- Has essential principles inline in SKILL.md\n- Routes directly to appropriate workflows based on user intent\n- Keeps SKILL.md under 500 lines\n- Asks minimal clarifying questions only when truly needed\n- Has been tested with real usage\n\u003C\u002Fsuccess_criteria>\n","\u003Cessential_principles>\n\n## How Skills Work\n\nSkills are modular, filesystem-based capabilities that provide domain expertise on demand. This skill teaches how to create effective skills.\n\n### 1. Skills Are Prompts\n\nAll prompting best practices apply. Be clear, be direct, use XML structure. Assume Claude is smart - only add context Claude doesn't have.\n\n### 2. SKILL.md Is Always Loaded\n\nWhen a skill is invoked, Claude reads SKILL.md. Use this guarantee:\n\n- Essential principles go in SKILL.md (can't be skipped)\n- Workflow-specific content goes in workflows\u002F\n- Reusable knowledge goes in references\u002F\n\n### 3. Router Pattern for Complex Skills\n\n```\nskill-name\u002F\n├── SKILL.md              # Router + principles\n├── workflows\u002F            # Step-by-step procedures (FOLLOW)\n├── references\u002F           # Domain knowledge (READ)\n├── templates\u002F            # Output structures (COPY + FILL)\n└── scripts\u002F              # Reusable code (EXECUTE)\n```\n\nSKILL.md asks \"what do you want to do?\" → routes to workflow → workflow specifies which references to read.\n\n**When to use each folder:**\n\n- **workflows\u002F** - Multi-step procedures Claude follows\n- **references\u002F** - Domain knowledge Claude reads for context\n- **templates\u002F** - Consistent output structures Claude copies and fills (plans, specs, configs)\n- **scripts\u002F** - Executable code Claude runs as-is (deploy, setup, API calls)\n\n### 4. Pure XML Structure\n\nNo markdown headings (#, ##, ###) in skill body. Use semantic XML tags:\n\n```xml\n\u003Cobjective>...\u003C\u002Fobjective>\n\u003Cprocess>...\u003C\u002Fprocess>\n\u003Csuccess_criteria>...\u003C\u002Fsuccess_criteria>\n```\n\nKeep markdown formatting within content (bold, lists, code blocks).\n\n### 5. Progressive Disclosure\n\nSKILL.md under 500 lines. Split detailed content into reference files. Load only what's needed for the current workflow.\n\u003C\u002Fessential_principles>\n\n\u003Crouting>\n## Understanding User Intent\n\nBased on the user's message, route directly to the appropriate workflow:\n\n**Creating new skills:**\n\n- Domain expertise (exhaustive knowledge base) → **Use `create-domain-expertise` skill instead** (separate skill with batched subagent orchestration)\n- Task-execution skill (does specific things) → workflows\u002Fcreate-new-skill.md\n\n**Working with existing skills:**\n\n- Audit, review, check → workflows\u002Faudit-skill.md\n- Verify content is current → workflows\u002Fverify-skill.md\n- Add workflow → workflows\u002Fadd-workflow.md\n- Add reference → workflows\u002Fadd-reference.md\n- Add template → workflows\u002Fadd-template.md\n- Add script → workflows\u002Fadd-script.md\n- Upgrade to router pattern → workflows\u002Fupgrade-to-router.md\n\n**Need help deciding:**\n\n- General guidance → workflows\u002Fget-guidance.md\n\n**If user intent is unclear, ask minimal clarifying questions:**\n\n- \"Create a MIDI skill\" → \"Task-execution skill (does MIDI tasks) or domain expertise (complete MIDI knowledge base)?\"\n- \"Work on my skill\" → \"Which skill? What do you want to do with it?\"\n- Ask one clarifying question round at a time, then wait for the user's actual response before asking another.\n- Never fabricate or simulate user responses while clarifying (for example, fake `[User]` markers or imagined answers).\n\nThen proceed directly to the workflow.\n\u003C\u002Frouting>\n\n\u003Cquick_reference>\n\n## Skill Structure Quick Reference\n\n**Skill directories:**\n\n- Bundled\u002Fread-only: `~\u002F.gsd\u002Fagent\u002Fskills\u002F{skill-name}\u002F`\n- Global: `~\u002F.agents\u002Fskills\u002F{skill-name}\u002F`\n- Project-local: `.agents\u002Fskills\u002F{skill-name}\u002F`\n\nUser-authored skills should target the global or project-local directories; GSD manages the bundled directory during install\u002Fupdate.\n\n**Simple skill (single file):**\n\n```yaml\n---\nname: skill-name\ndescription: What it does and when to use it.\n---\n\n\u003Cobjective>What this skill does\u003C\u002Fobjective>\n\u003Cquick_start>Immediate actionable guidance\u003C\u002Fquick_start>\n\u003Cprocess>Step-by-step procedure\u003C\u002Fprocess>\n\u003Csuccess_criteria>How to know it worked\u003C\u002Fsuccess_criteria>\n```\n\n**Complex skill (router pattern):**\n\n```\nSKILL.md:\n  \u003Cessential_principles> - Always applies\n  \u003Cintake> - Question to ask\n  \u003Crouting> - Maps answers to workflows\n\nworkflows\u002F:\n  \u003Crequired_reading> - Which refs to load\n  \u003Cprocess> - Steps\n  \u003Csuccess_criteria> - Done when...\n\nreferences\u002F:\n  Domain knowledge, patterns, examples\n\ntemplates\u002F:\n  Output structures Claude copies and fills\n  (plans, specs, configs, documents)\n\nscripts\u002F:\n  Executable code Claude runs as-is\n  (deploy, setup, API calls, data processing)\n```\n\n\u003C\u002Fquick_reference>\n\n\u003Creference_index>\n\n## Domain Knowledge\n\nAll in `references\u002F`:\n\n**Structure:** recommended-structure.md, skill-structure.md\n**Principles:** core-principles.md, be-clear-and-direct.md, use-xml-tags.md\n**Patterns:** common-patterns.md, workflows-and-validation.md\n**Assets:** using-templates.md, using-scripts.md\n**Advanced:** executable-code.md, api-security.md, iteration-and-testing.md\n**GSD-specific:** gsd-skill-ecosystem.md\n\u003C\u002Freference_index>\n\n\u003Cworkflows_index>\n\n## Workflows\n\nAll in `workflows\u002F`:\n\n| Workflow | Purpose |\n|----------|---------|\n| create-new-skill.md | Build a task-execution skill from scratch |\n| audit-skill.md | Analyze skill against best practices |\n| verify-skill.md | Check if content is still accurate |\n| add-workflow.md | Add a workflow to existing skill |\n| add-reference.md | Add a reference to existing skill |\n| add-template.md | Add a template to existing skill |\n| add-script.md | Add a script to existing skill |\n| upgrade-to-router.md | Convert simple skill to router pattern |\n| get-guidance.md | Help decide what kind of skill to build |\n\u003C\u002Fworkflows_index>\n\n\u003Cyaml_requirements>\n\n## YAML Frontmatter\n\nRequired fields:\n\n```yaml\n---\nname: skill-name          # lowercase-with-hyphens, matches directory\ndescription: ...          # What it does AND when to use it (third person)\n---\n```\n\nFrontmatter must parse as YAML. Quote description values containing `:` or use\na folded block (`description: >`) for longer trigger descriptions.\n\nName conventions: `create-*`, `manage-*`, `setup-*`, `generate-*`, `build-*`\n\u003C\u002Fyaml_requirements>\n\n\u003Csuccess_criteria>\nA well-structured skill:\n\n- Has valid YAML frontmatter\n- Uses pure XML structure (no markdown headings in body)\n- Has essential principles inline in SKILL.md\n- Routes directly to appropriate workflows based on user intent\n- Keeps SKILL.md under 500 lines\n- Asks minimal clarifying questions only when truly needed\n- Has been tested with real usage\n\u003C\u002Fsuccess_criteria>\n",{"name":5,"description":7},"main","c0bc9c4e7e0a8581aeac3af397031dc3a63d012e","src\u002Fresources\u002Fskills\u002Fcreate-skill",118,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi","https:\u002F\u002Fwww.opengsd.net","https:\u002F\u002Fgithub.com\u002Fopen-gsd","opengsd.net","Most AI coding setups rot as the context window fills. Open GSD keeps the context clean, the work verified, and the git history honest — ship more, worry less.","2026-11-15 00:38:19",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add open-gsd\u002Fgsd-pi --skill create-skill",{"tool":40,"command":41},"bunx","bunx skills add open-gsd\u002Fgsd-pi --skill create-skill",{"tool":43,"command":44},"pnpm","pnpm dlx skills add open-gsd\u002Fgsd-pi --skill create-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002FSKILL.md",true,[48,54,58,62,66,70,74,78,82,86,90,94,98,102,106,110,114,118,122,126,130,134,138,142],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fapi-security.md","REFERENCE","参考文档",6214,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Freferences\u002Fapi-security.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fbe-clear-and-direct.md",13068,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Freferences\u002Fbe-clear-and-direct.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fcommon-patterns.md",14466,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Freferences\u002Fcommon-patterns.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fcore-principles.md",12716,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Freferences\u002Fcore-principles.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fexecutable-code.md",4391,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Freferences\u002Fexecutable-code.md",{"path":71,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fgsd-skill-ecosystem.md",3482,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Freferences\u002Fgsd-skill-ecosystem.md",{"path":75,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fiteration-and-testing.md",13532,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Freferences\u002Fiteration-and-testing.md",{"path":79,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Frecommended-structure.md",4018,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Freferences\u002Frecommended-structure.md",{"path":83,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fskill-structure.md",11274,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Freferences\u002Fskill-structure.md",{"path":87,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fuse-xml-tags.md",11502,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Freferences\u002Fuse-xml-tags.md",{"path":91,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fusing-scripts.md",3031,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Freferences\u002Fusing-scripts.md",{"path":95,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fusing-templates.md",2931,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Freferences\u002Fusing-templates.md",{"path":99,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fworkflows-and-validation.md",11869,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Freferences\u002Fworkflows-and-validation.md",{"path":103,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":104,"sourceHtmlUrl":105},"templates\u002Frouter-skill.md",1504,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Ftemplates\u002Frouter-skill.md",{"path":107,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":108,"sourceHtmlUrl":109},"templates\u002Fsimple-skill.md",637,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Ftemplates\u002Fsimple-skill.md",{"path":111,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":112,"sourceHtmlUrl":113},"workflows\u002Fadd-reference.md",2572,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Fworkflows\u002Fadd-reference.md",{"path":115,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":116,"sourceHtmlUrl":117},"workflows\u002Fadd-script.md",2372,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Fworkflows\u002Fadd-script.md",{"path":119,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":120,"sourceHtmlUrl":121},"workflows\u002Fadd-template.md",2158,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Fworkflows\u002Fadd-template.md",{"path":123,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":124,"sourceHtmlUrl":125},"workflows\u002Fadd-workflow.md",3223,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Fworkflows\u002Fadd-workflow.md",{"path":127,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":128,"sourceHtmlUrl":129},"workflows\u002Faudit-skill.md",3723,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Fworkflows\u002Faudit-skill.md",{"path":131,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":132,"sourceHtmlUrl":133},"workflows\u002Fcreate-new-skill.md",6111,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Fworkflows\u002Fcreate-new-skill.md",{"path":135,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":136,"sourceHtmlUrl":137},"workflows\u002Fget-guidance.md",3110,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Fworkflows\u002Fget-guidance.md",{"path":139,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":140,"sourceHtmlUrl":141},"workflows\u002Fupgrade-to-router.md",4052,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Fworkflows\u002Fupgrade-to-router.md",{"path":143,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":144,"sourceHtmlUrl":145},"workflows\u002Fverify-skill.md",5635,"https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fcreate-skill\u002Fworkflows\u002Fverify-skill.md",[147,154,161,168,175,182],{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":19},"01M74FAXPHS0QT1S067QDKYDBX","write-milestone-brief","Synthesize the current conversation into a milestone brief (PRD). Saves it as the milestone CONTEXT (`gsd_summary_save`) by default, or files a GitHub issue only with explicit user confirmation. Use when asked to \"turn this into a PRD\", \"draft a milestone brief\", \"capture this context\", \"write it up\", or when enough has been discussed to commit the plan to paper. Does not interview — it synthesizes what is already known.","https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fwrite-milestone-brief\u002FSKILL.md",[],[],{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":160,"publishedAt":19},"01M74FATJT7WZX5CSSG8RJDCF1","write-docs","Collaborative authoring workflow for proposals, technical specs, decision docs, READMEs, ADRs, and long-form prose that must work for fresh readers. Three stages: gather context, iterate on structure, reader-test for a stranger. Use when asked to \"write the docs\", \"draft a proposal\", \"write a spec\", \"write an RFC\", \"write the README\", or when a doc must be understandable without this session's context.","https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fwrite-docs\u002FSKILL.md",[],[],{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":19},"01M74FAQ8HKNVGCZ5ZBHW03A76","web-quality-audit","Comprehensive web quality audit covering performance, accessibility, SEO, and best practices. Use when asked to \"audit my site\", \"review web quality\", \"run lighthouse audit\", \"check page quality\", or \"optimize my website\".","https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fweb-quality-audit\u002FSKILL.md",[],[],{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":174,"publishedAt":19},"01M74FAMZ7WP4RPAG20F448MVF","web-design-guidelines","Review UI code for Web Interface Guidelines compliance. Use when asked to \"review my UI\", \"check accessibility\", \"audit design\", \"review UX\", or \"check my site against best practices\".","https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fweb-design-guidelines\u002FSKILL.md",[],[],{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":181,"publishedAt":19},"01M74FAHYM672GKGGS8KMY9CKC","verify-before-complete","Block completion claims until verification evidence has been produced in the current message. Use before marking a task\u002Fslice\u002Fmilestone complete, before creating a commit or PR, before saying \"it works\" or \"tests pass\", and any time you are about to claim work is done. The rule is: evidence before claims, always — running the verification must happen now, not \"earlier in the session\". Fresh output or no claim.","https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fverify-before-complete\u002FSKILL.md",[],[],{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":188,"publishedAt":19},"01M74FADG78GX090P4YE5ZHR2A","userinterface-wiki","UI\u002FUX best practices for web interfaces. Use when reviewing animations, CSS, audio, typography, UX patterns, prefetching, or icon implementations. Covers 11 categories from animation principles to typography. Outputs file:line findings.","https:\u002F\u002Fgithub.com\u002Fopen-gsd\u002Fgsd-pi\u002Fblob\u002Fmain\u002Fsrc\u002Fresources\u002Fskills\u002Fuserinterface-wiki\u002FSKILL.md",[],[]]