[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6VCGVX6DGB1FKTA53QBBCQB":3,"skill-same:01M6VCGVX6DGB1FKTA53QBBCQB":70},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":13,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":55,"install":56,"resources":69},"01M6VCGVX6DGB1FKTA53QBBCQB","workspace-surface-audit",null,"Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.","sakamoto-family-smile\u002Fagent_monorepo","sakamoto-family-smile","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F132812403?v=4","01M6RTAT3H8PMWX5SJ65KP3VYF","01M6RTAV321WB5RAHCWTZMX5CV",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fecc\u002Fworkspace-surface-audit\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"workspace surface audit","audit","workspace","use","when","value","native","env","active","harness setup","hooks","up","MCP","environment","repo","harness","capabilities","code","connectors","workflows","2026-11-10 10:12:30",false,"---\nname: dispatch-subagent\ndescription: Controller\u002Fworker pattern for dispatching isolated subagents via the Agent tool with curated context, directory scope, and dispatch logging\n---\n\n# Dispatch Subagent Skill\n\nThis skill defines the controller\u002Fworker dispatch pattern. The\ncontroller curates context, declares a directory scope, logs the full\ndispatch prompt, and sends a fresh subagent to do the work.\n\n## Process\n\n### 1. Determine task scope\n\nIdentify:\n- Which agent to dispatch (by tier and role)\n- What directory the subagent may write to (`scope_directory`)\n- What files and instructions the subagent needs\n\n### 2. Curate context\n\nSelect only the files and instructions relevant to the task. Follow\n`instructions\u002Fsubagent-protocol` for include\u002Fexclude rules.\n\n**Include:**\n- Ticket description and acceptance criteria (if executing a ticket)\n- Ticket plan (approach, files to modify)\n- Content of source files the subagent will read or modify\n- Relevant architecture decisions\n- Applicable coding standards and testing instructions\n\n**For raw-text delegation** (e.g., TODO creation, sprint planning):\n- Pass the stakeholder's raw words verbatim\n- Provide file references (TODO paths, overview path) instead of\n  pre-digested content\n- Let the subordinate agent make structuring decisions\n\n**Exclude:**\n- Controller's conversation history\n- Other tickets in the sprint\n- Debug logs from prior attempts\n- Full directory listings\n- Sprint-level planning documents (unless the task is planning)\n\n### 3. Compose the prompt\n\nInclude in the subagent prompt:\n- The curated context\n- The scope constraint: \"You may only create or modify files under\n  `\u003Cscope_directory>`. You may read files from any location.\"\n- The specific task and acceptance criteria\n- Instructions for how to report results\n\n### 4. Log the dispatch (MANDATORY)\n\n**Before sending the prompt, you MUST call `log_subagent_dispatch`.**\nThis is not optional. Every dispatch at every tier must be logged. Pass:\n- `parent_agent`: your agent name (e.g., \"sprint-executor\")\n- `child_agent`: the subagent being dispatched (e.g., \"code-monkey\")\n- `sprint_id`: the sprint ID (if applicable)\n- `ticket_id`: the ticket ID (if applicable)\n- `prompt`: the full prompt text being sent\n\nThis creates an audit trail with a dispatch ID you will use in step 6.\n\n**If `log_subagent_dispatch` is unavailable or fails, STOP and report\nthe failure. Do not dispatch without logging.**\n\n### 5. Dispatch\n\nSend the subagent via the Agent tool with the composed prompt.\n\n### 6. Log the result and review (MANDATORY)\n\nWhen the subagent returns:\n- **First, call `update_dispatch_log`** with the dispatch ID from step 4,\n  the outcome (success\u002Ffailure), a summary of what the subagent\n  produced (files modified, key results), and the subagent's **response\n  text** (via the `response` parameter). This preserves both sides of\n  the conversation in the log. This is mandatory — do not skip it.\n- Read the output\n- Check that the work meets the task requirements\n- If issues found, compose a new prompt with feedback and re-dispatch\n  (max 2 retries, then escalate to the controller's parent). **Log\n  every re-dispatch** with `log_subagent_dispatch` and\n  `update_dispatch_log` as well.\n\n## Notes\n\n- The controller never writes code directly — all implementation is\n  delegated to subagents.\n- Each subagent starts with fresh context. It does not inherit the\n  controller's conversation.\n- Scope enforcement is prompt-level + rule-level. Path-scoped rules\n  reinforce the constraint when the subagent accesses files.\n","# Dispatch Subagent Skill\n\nThis skill defines the controller\u002Fworker dispatch pattern. The\ncontroller curates context, declares a directory scope, logs the full\ndispatch prompt, and sends a fresh subagent to do the work.\n\n## Process\n\n### 1. Determine task scope\n\nIdentify:\n- Which agent to dispatch (by tier and role)\n- What directory the subagent may write to (`scope_directory`)\n- What files and instructions the subagent needs\n\n### 2. Curate context\n\nSelect only the files and instructions relevant to the task. Follow\n`instructions\u002Fsubagent-protocol` for include\u002Fexclude rules.\n\n**Include:**\n- Ticket description and acceptance criteria (if executing a ticket)\n- Ticket plan (approach, files to modify)\n- Content of source files the subagent will read or modify\n- Relevant architecture decisions\n- Applicable coding standards and testing instructions\n\n**For raw-text delegation** (e.g., TODO creation, sprint planning):\n- Pass the stakeholder's raw words verbatim\n- Provide file references (TODO paths, overview path) instead of\n  pre-digested content\n- Let the subordinate agent make structuring decisions\n\n**Exclude:**\n- Controller's conversation history\n- Other tickets in the sprint\n- Debug logs from prior attempts\n- Full directory listings\n- Sprint-level planning documents (unless the task is planning)\n\n### 3. Compose the prompt\n\nInclude in the subagent prompt:\n- The curated context\n- The scope constraint: \"You may only create or modify files under\n  `\u003Cscope_directory>`. You may read files from any location.\"\n- The specific task and acceptance criteria\n- Instructions for how to report results\n\n### 4. Log the dispatch (MANDATORY)\n\n**Before sending the prompt, you MUST call `log_subagent_dispatch`.**\nThis is not optional. Every dispatch at every tier must be logged. Pass:\n- `parent_agent`: your agent name (e.g., \"sprint-executor\")\n- `child_agent`: the subagent being dispatched (e.g., \"code-monkey\")\n- `sprint_id`: the sprint ID (if applicable)\n- `ticket_id`: the ticket ID (if applicable)\n- `prompt`: the full prompt text being sent\n\nThis creates an audit trail with a dispatch ID you will use in step 6.\n\n**If `log_subagent_dispatch` is unavailable or fails, STOP and report\nthe failure. Do not dispatch without logging.**\n\n### 5. Dispatch\n\nSend the subagent via the Agent tool with the composed prompt.\n\n### 6. Log the result and review (MANDATORY)\n\nWhen the subagent returns:\n- **First, call `update_dispatch_log`** with the dispatch ID from step 4,\n  the outcome (success\u002Ffailure), a summary of what the subagent\n  produced (files modified, key results), and the subagent's **response\n  text** (via the `response` parameter). This preserves both sides of\n  the conversation in the log. This is mandatory — do not skip it.\n- Read the output\n- Check that the work meets the task requirements\n- If issues found, compose a new prompt with feedback and re-dispatch\n  (max 2 retries, then escalate to the controller's parent). **Log\n  every re-dispatch** with `log_subagent_dispatch` and\n  `update_dispatch_log` as well.\n\n## Notes\n\n- The controller never writes code directly — all implementation is\n  delegated to subagents.\n- Each subagent starts with fresh context. It does not inherit the\n  controller's conversation.\n- Scope enforcement is prompt-level + rule-level. Path-scoped rules\n  reinforce the constraint when the subagent accesses files.\n",{"name":48,"description":49},"dispatch-subagent","Controller\u002Fworker pattern for dispatching isolated subagents via the Agent tool with curated context, directory scope, and dispatch logging","master","401bf4193750743bded5ac4e2c20345e39c51d8b",".claude\u002Fskills\u002Fecc\u002Fworkspace-surface-audit","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile","2026-11-08 20:29:14",{"source":8,"skillName":48,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add sakamoto-family-smile\u002Fagent_monorepo --skill dispatch-subagent",{"tool":62,"command":63},"bunx","bunx skills add sakamoto-family-smile\u002Fagent_monorepo --skill dispatch-subagent",{"tool":65,"command":66},"pnpm","pnpm dlx skills add sakamoto-family-smile\u002Fagent_monorepo --skill dispatch-subagent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fecc\u002Fworkspace-surface-audit\u002FSKILL.md",true,[],[71,104,112,131,151,177],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":83,"publishedAt":43},"01M6RW50THEFSKK42YNR8XFZA1","remotion-video-creation","Best practices for Remotion - Video creation in React. 29 domain-specific rules covering 3D, animations, audio, captions, charts, transitions, and more.","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fecc\u002Fremotion-video-creation\u002FSKILL.md",[77,80],{"categoryNo":78,"categoryName":79,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":81,"categoryName":82,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",[84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103],"remotion video creation","remotion video","Video","Remotion","creation","Charts","Captions","Audio","3D","Composition","Animation","best practices","more","animations","domain-specific","domain","three","Rules","Lottie","for",{"skillNo":105,"name":106,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":43},"01M6VCJ23NPECPSZJKGY691F75","hotcook-recipes","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo\u002Fblob\u002Fmain\u002Fhotcook-agent\u002Fdata\u002Fskills\u002Fhotcook-recipes\u002FSKILL.md",[],[110,111],"recipes","hotcook recipes",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":126,"publishedAt":43},"01M6VCHHE00X5XHSDRD1KH1BW2","code-helper","Code review and assistance skill","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo\u002Fblob\u002Fmain\u002Fagent-system-2\u002Fskills\u002Fcode-helper\u002Fskill.md",[118,121],{"categoryNo":119,"categoryName":120,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":122,"categoryName":123,"taxonomyType":124,"taxonomyTypeDesc":125},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[40,127,128,129,130],"helper","code helper","code review","review",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":141,"publishedAt":43},"01M6VCH3Q31A20H6SQ1H0J7JB2","research-assistant","Web research assistant skill using Brave Search MCP","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo\u002Fblob\u002Fmain\u002Fagent-system-1\u002Fskills\u002Fresearch-assistant\u002Fskill.md",[137,140],{"categoryNo":138,"categoryName":139,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[142,143,144,145,35,146,147,148,149,150],"assistant","research","research assistant","search","web","brave search","web research","brave","web research assistant",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":161,"publishedAt":43},"01M6VCGZZGPNVJSCZ1JTMNZAHY","x-api","X\u002FTwitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fecc\u002Fx-api\u002FSKILL.md",[157,160],{"categoryNo":158,"categoryName":159,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":122,"categoryName":123,"taxonomyType":124,"taxonomyTypeDesc":125},[162,163,164,29,165,166,167,103,168,169,27,170,171,172,173,145,174,175,26,176],"api","x api","posting","with","reading","threads","rate","limits","patterns","platform","auth","analytics","OAuth","twitter","api integration",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":186,"publishedAt":43},"01M6VCGE22A0XJ8T90EFYD9Y3B","windows-desktop-e2e","E2E testing for Windows native desktop apps (WPF, WinForms, Win32\u002FMFC, Qt) using pywinauto and Windows UI Automation.","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fecc\u002Fwindows-desktop-e2e\u002FSKILL.md",[183],{"categoryNo":184,"categoryName":185,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",[187,188,189,190,29,191,192,193,194,195,196,197,198,199,103],"windows","desktop","e2e","windows desktop e2e","testing","automation","e2e testing","win32","wpf","ui","apps","winforms","desktop apps"]