[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JQ03MYHDXRBFQ8SBFFF8QG":3,"skill-same:01M6JQ03MYHDXRBFQ8SBFFF8QG":85},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":61,"ownerHtmlUrl":62,"ownerBlogUrl":63,"ownerDescription":6,"updatedAt":64,"install":65,"resources":78},"01M6JQ03MYHDXRBFQ8SBFFF8QG","sdd-init",null,"Initialize Spec-Driven Development context in any project. Detects stack, conventions, and bootstraps the active persistence backend. Trigger: When user wants to initialize SDD in a project, or says \"sdd init\", \"iniciar sdd\", \"openspec init\".","LongLeo287\u002FOmniClaw","LongLeo287","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F141803367?v=4","01M6JK75C62VCNZKR5BRZ386YV","LongLeo","01M6JK75GQ78TSP1ZPXNKK3MCH",9,"MIT","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fpayload\u002Fskills\u002Fsdd_init\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"init","sdd","sdd init","openspec","openspec init","spec-driven","trigger","driven","spec","project","conventions","active","persistence","development","backend","user","initialize","context","programming","stack","2026-11-10 10:12:30",false,"---\nname: sdd-init\ndescription: >\n  Initialize Spec-Driven Development context in any project. Detects stack, conventions, and bootstraps the active persistence backend.\n  Trigger: When user wants to initialize SDD in a project, or says \"sdd init\", \"iniciar sdd\", \"openspec init\".\nlicense: MIT\nmetadata:\n  author: gentleman-programming\n  version: \"2.0\"\n---\n\n## Purpose\n\nYou are a sub-agent responsible for initializing the Spec-Driven Development (SDD) context in a project. You detect the project stack and conventions, then bootstrap the active persistence backend.\n\nYou are an EXECUTOR for this phase, not the orchestrator. Do the initialization work yourself. Do NOT launch sub-agents, do NOT call `delegate` or `task`, and do NOT hand execution back unless you hit a real blocker that must be reported upstream.\n\n## Execution and Persistence Contract\n\n- If mode is `engram`:\n  Do NOT create `openspec\u002F` directory.\n\n  **Save project context**:\n  ```\n  mem_save(\n    title: \"sdd-init\u002F{project-name}\",\n    topic_key: \"sdd-init\u002F{project-name}\",\n    type: \"architecture\",\n    project: \"{project-name}\",\n    content: \"{detected project context markdown}\"\n  )\n  ```\n  `topic_key` enables upserts — re-running init updates the existing context, not duplicates.\n\n  (See `skills\u002F_shared\u002Fengram-convention.md` for full naming conventions.)\n- If mode is `openspec`: Read and follow `skills\u002F_shared\u002Fopenspec-convention.md`. Run full bootstrap.\n- If mode is `hybrid`: Read and follow BOTH convention files. Run openspec bootstrap AND persist context to Engram.\n- If mode is `none`: Return detected context without writing project files.\n\n## What to Do\n\n### Step 1: Detect Project Context\n\nRead the project to understand:\n- Tech stack (check package.json, go.mod, pyproject.toml, etc.)\n- Existing conventions (linters, test frameworks, CI)\n- Architecture patterns in use\n\n### Step 2: Initialize Persistence Backend\n\nIf mode resolves to `openspec`, create this directory structure:\n\n```\nopenspec\u002F\n├── config.yaml              ← Project-specific SDD config\n├── specs\u002F                   ← Source of truth (empty initially)\n└── changes\u002F                 ← Active changes\n    └── archive\u002F             ← Completed changes\n```\n\n### Step 3: Generate Config (openspec mode)\n\nBased on what you detected, create the config when in `openspec` mode:\n\n```yaml\n# openspec\u002Fconfig.yaml\nschema: spec-driven\n\ncontext: |\n  Tech stack: {detected stack}\n  Architecture: {detected patterns}\n  Testing: {detected test framework}\n  Style: {detected linting\u002Fformatting}\n\nrules:\n  proposal:\n    - Include rollback plan for risky changes\n    - Identify affected modules\u002Fpackages\n  specs:\n    - Use Given\u002FWhen\u002FThen format for scenarios\n    - Use RFC 2119 keywords (MUST, SHALL, SHOULD, MAY)\n  design:\n    - Include sequence diagrams for complex flows\n    - Document architecture decisions with rationale\n  tasks:\n    - Group tasks by phase (infrastructure, implementation, testing)\n    - Use hierarchical numbering (1.1, 1.2, etc.)\n    - Keep tasks small enough to complete in one session\n  apply:\n    - Follow existing code patterns and conventions\n    - Load relevant coding skills for the project stack\n  verify:\n    - Run tests if test infrastructure exists\n    - Compare implementation against every spec scenario\n  archive:\n    - Warn before merging destructive deltas (large removals)\n```\n\n### Step 4: Build Skill Registry\n\nFollow the same logic as the `skill-registry` skill (`skills\u002Fskill-registry\u002FSKILL.md`):\n\n1. Scan user skills: glob `*\u002FSKILL.md` across ALL known skill directories. **User-level**: `~\u002F.claude\u002Fskills\u002F`, `~\u002F.config\u002Fopencode\u002Fskills\u002F`, `~\u002F.gemini\u002Fskills\u002F`, `~\u002F.cursor\u002Fskills\u002F`, `~\u002F.copilot\u002Fskills\u002F`, parent of this skill file. **Project-level**: `.claude\u002Fskills\u002F`, `.gemini\u002Fskills\u002F`, `.agent\u002Fskills\u002F`, `skills\u002F`. Skip `sdd-*`, `_shared`, `skill-registry`. Deduplicate by name (project-level wins). Read frontmatter triggers.\n2. Scan project conventions: check for `agents.md`, `AGENTS.md`, `CLAUDE.md` (project-level), `.cursorrules`, `GEMINI.md`, `copilot-instructions.md` in the project root. If an index file is found (e.g., `agents.md`), READ it and extract all referenced file paths — include both the index and its referenced files in the registry.\n3. **ALWAYS write `.atl\u002Fskill-registry.md`** in the project root (create `.atl\u002F` if needed). This file is mode-independent — it's infrastructure, not an SDD artifact.\n4. If engram is available, **ALSO save to engram**: `mem_save(title: \"skill-registry\", topic_key: \"skill-registry\", type: \"config\", project: \"{project}\", content: \"{registry markdown}\")`\n\nSee `skills\u002Fskill-registry\u002FSKILL.md` for the full registry format and scanning details.\n\n### Step 5: Persist Project Context\n\n**This step is MANDATORY — do NOT skip it.**\n\nIf mode is `engram`:\n```\nmem_save(\n  title: \"sdd-init\u002F{project-name}\",\n  topic_key: \"sdd-init\u002F{project-name}\",\n  type: \"architecture\",\n  project: \"{project-name}\",\n  content: \"{your detected project context from Steps 1-4}\"\n)\n```\n\nIf mode is `openspec` or `hybrid`: the config was already written in Step 3.\n\nIf mode is `hybrid`: also call `mem_save` as above (write to BOTH backends).\n\n### Step 6: Return Summary\n\nReturn a structured summary adapted to the resolved mode:\n\n#### If mode is `engram`:\n\nPersist project context following `skills\u002F_shared\u002Fengram-convention.md` with title and topic_key `sdd-init\u002F{project-name}`.\n\nReturn:\n```\n## SDD Initialized\n\n**Project**: {project name}\n**Stack**: {detected stack}\n**Persistence**: engram\n\n### Context Saved\nProject context persisted to Engram.\n- **Engram ID**: #{observation-id}\n- **Topic key**: sdd-init\u002F{project-name}\n\nNo project files created.\n\n### Next Steps\nReady for \u002Fsdd-explore \u003Ctopic> or \u002Fsdd-new \u003Cchange-name>.\n```\n\n#### If mode is `openspec`:\n```\n## SDD Initialized\n\n**Project**: {project name}\n**Stack**: {detected stack}\n**Persistence**: openspec\n\n### Structure Created\n- openspec\u002Fconfig.yaml ← Project config with detected context\n- openspec\u002Fspecs\u002F      ← Ready for specifications\n- openspec\u002Fchanges\u002F    ← Ready for change proposals\n\n### Next Steps\nReady for \u002Fsdd-explore \u003Ctopic> or \u002Fsdd-new \u003Cchange-name>.\n```\n\n#### If mode is `none`:\n```\n## SDD Initialized\n\n**Project**: {project name}\n**Stack**: {detected stack}\n**Persistence**: none (ephemeral)\n\n### Context Detected\n{summary of detected stack and conventions}\n\n### Recommendation\nEnable `engram` or `openspec` for artifact persistence across sessions. Without persistence, all SDD artifacts will be lost when the conversation ends.\n\n### Next Steps\nReady for \u002Fsdd-explore \u003Ctopic> or \u002Fsdd-new \u003Cchange-name>.\n```\n\n## Rules\n\n- NEVER create placeholder spec files - specs are created via sdd-spec during a change\n- ALWAYS detect the real tech stack, don't guess\n- NEVER behave like the orchestrator from this phase - execute directly and return results\n- If the project already has an `openspec\u002F` directory, report what exists and ask the orchestrator if it should be updated\n- Keep config.yaml context CONCISE - no more than 10 lines\n- Return a structured envelope with: `status`, `executive_summary`, `detailed_report` (optional), `artifacts`, `next_recommended`, and `risks`\n","## Purpose\n\nYou are a sub-agent responsible for initializing the Spec-Driven Development (SDD) context in a project. You detect the project stack and conventions, then bootstrap the active persistence backend.\n\nYou are an EXECUTOR for this phase, not the orchestrator. Do the initialization work yourself. Do NOT launch sub-agents, do NOT call `delegate` or `task`, and do NOT hand execution back unless you hit a real blocker that must be reported upstream.\n\n## Execution and Persistence Contract\n\n- If mode is `engram`:\n  Do NOT create `openspec\u002F` directory.\n\n  **Save project context**:\n  ```\n  mem_save(\n    title: \"sdd-init\u002F{project-name}\",\n    topic_key: \"sdd-init\u002F{project-name}\",\n    type: \"architecture\",\n    project: \"{project-name}\",\n    content: \"{detected project context markdown}\"\n  )\n  ```\n  `topic_key` enables upserts — re-running init updates the existing context, not duplicates.\n\n  (See `skills\u002F_shared\u002Fengram-convention.md` for full naming conventions.)\n- If mode is `openspec`: Read and follow `skills\u002F_shared\u002Fopenspec-convention.md`. Run full bootstrap.\n- If mode is `hybrid`: Read and follow BOTH convention files. Run openspec bootstrap AND persist context to Engram.\n- If mode is `none`: Return detected context without writing project files.\n\n## What to Do\n\n### Step 1: Detect Project Context\n\nRead the project to understand:\n- Tech stack (check package.json, go.mod, pyproject.toml, etc.)\n- Existing conventions (linters, test frameworks, CI)\n- Architecture patterns in use\n\n### Step 2: Initialize Persistence Backend\n\nIf mode resolves to `openspec`, create this directory structure:\n\n```\nopenspec\u002F\n├── config.yaml              ← Project-specific SDD config\n├── specs\u002F                   ← Source of truth (empty initially)\n└── changes\u002F                 ← Active changes\n    └── archive\u002F             ← Completed changes\n```\n\n### Step 3: Generate Config (openspec mode)\n\nBased on what you detected, create the config when in `openspec` mode:\n\n```yaml\n# openspec\u002Fconfig.yaml\nschema: spec-driven\n\ncontext: |\n  Tech stack: {detected stack}\n  Architecture: {detected patterns}\n  Testing: {detected test framework}\n  Style: {detected linting\u002Fformatting}\n\nrules:\n  proposal:\n    - Include rollback plan for risky changes\n    - Identify affected modules\u002Fpackages\n  specs:\n    - Use Given\u002FWhen\u002FThen format for scenarios\n    - Use RFC 2119 keywords (MUST, SHALL, SHOULD, MAY)\n  design:\n    - Include sequence diagrams for complex flows\n    - Document architecture decisions with rationale\n  tasks:\n    - Group tasks by phase (infrastructure, implementation, testing)\n    - Use hierarchical numbering (1.1, 1.2, etc.)\n    - Keep tasks small enough to complete in one session\n  apply:\n    - Follow existing code patterns and conventions\n    - Load relevant coding skills for the project stack\n  verify:\n    - Run tests if test infrastructure exists\n    - Compare implementation against every spec scenario\n  archive:\n    - Warn before merging destructive deltas (large removals)\n```\n\n### Step 4: Build Skill Registry\n\nFollow the same logic as the `skill-registry` skill (`skills\u002Fskill-registry\u002FSKILL.md`):\n\n1. Scan user skills: glob `*\u002FSKILL.md` across ALL known skill directories. **User-level**: `~\u002F.claude\u002Fskills\u002F`, `~\u002F.config\u002Fopencode\u002Fskills\u002F`, `~\u002F.gemini\u002Fskills\u002F`, `~\u002F.cursor\u002Fskills\u002F`, `~\u002F.copilot\u002Fskills\u002F`, parent of this skill file. **Project-level**: `.claude\u002Fskills\u002F`, `.gemini\u002Fskills\u002F`, `.agent\u002Fskills\u002F`, `skills\u002F`. Skip `sdd-*`, `_shared`, `skill-registry`. Deduplicate by name (project-level wins). Read frontmatter triggers.\n2. Scan project conventions: check for `agents.md`, `AGENTS.md`, `CLAUDE.md` (project-level), `.cursorrules`, `GEMINI.md`, `copilot-instructions.md` in the project root. If an index file is found (e.g., `agents.md`), READ it and extract all referenced file paths — include both the index and its referenced files in the registry.\n3. **ALWAYS write `.atl\u002Fskill-registry.md`** in the project root (create `.atl\u002F` if needed). This file is mode-independent — it's infrastructure, not an SDD artifact.\n4. If engram is available, **ALSO save to engram**: `mem_save(title: \"skill-registry\", topic_key: \"skill-registry\", type: \"config\", project: \"{project}\", content: \"{registry markdown}\")`\n\nSee `skills\u002Fskill-registry\u002FSKILL.md` for the full registry format and scanning details.\n\n### Step 5: Persist Project Context\n\n**This step is MANDATORY — do NOT skip it.**\n\nIf mode is `engram`:\n```\nmem_save(\n  title: \"sdd-init\u002F{project-name}\",\n  topic_key: \"sdd-init\u002F{project-name}\",\n  type: \"architecture\",\n  project: \"{project-name}\",\n  content: \"{your detected project context from Steps 1-4}\"\n)\n```\n\nIf mode is `openspec` or `hybrid`: the config was already written in Step 3.\n\nIf mode is `hybrid`: also call `mem_save` as above (write to BOTH backends).\n\n### Step 6: Return Summary\n\nReturn a structured summary adapted to the resolved mode:\n\n#### If mode is `engram`:\n\nPersist project context following `skills\u002F_shared\u002Fengram-convention.md` with title and topic_key `sdd-init\u002F{project-name}`.\n\nReturn:\n```\n## SDD Initialized\n\n**Project**: {project name}\n**Stack**: {detected stack}\n**Persistence**: engram\n\n### Context Saved\nProject context persisted to Engram.\n- **Engram ID**: #{observation-id}\n- **Topic key**: sdd-init\u002F{project-name}\n\nNo project files created.\n\n### Next Steps\nReady for \u002Fsdd-explore \u003Ctopic> or \u002Fsdd-new \u003Cchange-name>.\n```\n\n#### If mode is `openspec`:\n```\n## SDD Initialized\n\n**Project**: {project name}\n**Stack**: {detected stack}\n**Persistence**: openspec\n\n### Structure Created\n- openspec\u002Fconfig.yaml ← Project config with detected context\n- openspec\u002Fspecs\u002F      ← Ready for specifications\n- openspec\u002Fchanges\u002F    ← Ready for change proposals\n\n### Next Steps\nReady for \u002Fsdd-explore \u003Ctopic> or \u002Fsdd-new \u003Cchange-name>.\n```\n\n#### If mode is `none`:\n```\n## SDD Initialized\n\n**Project**: {project name}\n**Stack**: {detected stack}\n**Persistence**: none (ephemeral)\n\n### Context Detected\n{summary of detected stack and conventions}\n\n### Recommendation\nEnable `engram` or `openspec` for artifact persistence across sessions. Without persistence, all SDD artifacts will be lost when the conversation ends.\n\n### Next Steps\nReady for \u002Fsdd-explore \u003Ctopic> or \u002Fsdd-new \u003Cchange-name>.\n```\n\n## Rules\n\n- NEVER create placeholder spec files - specs are created via sdd-spec during a change\n- ALWAYS detect the real tech stack, don't guess\n- NEVER behave like the orchestrator from this phase - execute directly and return results\n- If the project already has an `openspec\u002F` directory, report what exists and ask the orchestrator if it should be updated\n- Keep config.yaml context CONCISE - no more than 10 lines\n- Return a structured envelope with: `status`, `executive_summary`, `detailed_report` (optional), `artifacts`, `next_recommended`, and `risks`\n",{"name":5,"license":15,"metadata":52,"description":55},{"author":53,"version":54},"gentleman-programming","2.0","Initialize Spec-Driven Development context in any project. Detects stack, conventions, and bootstraps the active persistence backend. Trigger: When user wants to initialize SDD in a project, or says \"sdd init\", \"iniciar sdd\", \"openspec init\".\n","main","c173cdffe08e788a99b91928a831b476b8434838","ecosystem\u002Fskills\u002Fpayload\u002Fskills\u002Fsdd_init",0,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw","https:\u002F\u002Fportfolio-longleo.vercel.app\u002Flabs\u002Fomniclaw.html","https:\u002F\u002Fgithub.com\u002FLongLeo287","https:\u002F\u002Fwww.facebook.com\u002FResourceRookie2023","2026-09-30 00:58:05",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add LongLeo287\u002FOmniClaw --skill sdd-init",{"tool":71,"command":72},"bunx","bunx skills add LongLeo287\u002FOmniClaw --skill sdd-init",{"tool":74,"command":75},"pnpm","pnpm dlx skills add LongLeo287\u002FOmniClaw --skill sdd-init","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fpayload\u002Fskills\u002Fsdd_init\u002FSKILL.md",true,[79],{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"_DIR_IDENTITY.md","REFERENCE","参考文档",327,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fpayload\u002Fskills\u002Fsdd_init\u002F_DIR_IDENTITY.md",[86,124,146,174,189,216],{"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":104,"publishedAt":47},"01M6JR0KQP4MHT32TN40D9CBFX","UI-UX Pro Max","Advanced UI\u002FUX analysis and generation skills with data-driven patterns. Python scripts (core.py, search.py) for systematic UI pattern extraction, design system generation, and component search from curated data sources.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fui_components\u002Fui_ux_pro_max\u002FSKILL.md",[92,95,96,101],{"categoryNo":93,"categoryName":94,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",{"categoryNo":102,"categoryName":103,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000033","数据分析师",[105,106,107,108,109,110,111,112,113,114,115,116,117,38,118,119,120,121,122,123],"ux","ui","ui ux pro max","max","pro","ui ux","design","component","search","analysis","team","rd","ui-ux","systematic","scripts","pattern extraction","sources","advanced","data-driven",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":131,"publishedAt":47},"01M6JR0EF5AEQHP2FSTB57H05P","shadcn-ui","Expert guidance for integrating and building applications with shadcn\u002Fui components, including component discovery, installation, customization, and best practices.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fui_components\u002Fshadcn_ui\u002FSKILL.md",[130],{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},[132,106,133,134,112,135,136,137,138,115,139,140,141,38,142,143,144,145],"shadcn","shadcn ui","components","core","best practices","applications","discovery","customization","guidance","expert","installation","ui components","with","for",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":155,"publishedAt":47},"01M6JR08F51BEN17RHFYX65WVE","zustand_store_ts","Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state\u002Faction separation. Use when building React state management, creating global stores, or implementing reactive state patterns with Zustand.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fzustand_store_ts\u002FSKILL.md",[152],{"categoryNo":153,"categoryName":154,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,144,172,173],"zustand store ts","zustand","store","typescript","microsoft","react","create","state management","state","react state management","management","global","use","patterns","separation","middleware","action","implementing",{"skillNo":175,"name":157,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":47},"01M6JR00TDMVAFFCZXZ04AN7Q7","Zustand state management guide. Use when working with store code (src\u002Fstore\u002F**), implementing actions, managing state, or creating slices. Triggers on Zustand store development, state management questions, or action implementation.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fzustand\u002FSKILL.md",[],[157,40,163,180,164,181,182,166,183,168,184,185,186,158,144,187,188,172,173],"code","actions","src","guide","implementation","zustand state","triggers","questions","zustand state management",{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":199,"publishedAt":47},"01M6JQZSWV4KWJP112G6XHEP44","youtube_summarizer","Automatically fetch YouTube video transcripts, generate structured summaries, and send full transcripts to messaging platforms. Detects YouTube URLs and provides metadata, key insights, and downloadable transcripts.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fyoutube_summarizer\u002FSKILL.md",[195,198],{"categoryNo":196,"categoryName":197,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215],"youtube","youtube summarizer","summarizer","generate","metadata","messaging","Video","fetch","telegram","transcription","summarization","structured","full","insights","transcripts","summaries",{"skillNo":217,"name":218,"nameZh":6,"description":219,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":220,"categories":221,"keywords":222,"publishedAt":47},"01M6JQZN3QJB6B77JGKJD62DQT","youtube_clipper","YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fyoutube_clipper\u002FSKILL.md",[],[200,223,224,206,225,226,227,228,229,230,231,232,233,234,235,236,237],"clipper","youtube clipper","Bash","下载","视频","生成","关键词","翻译","read","write","clip","总结","工具","文案","sonnet"]