[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70FPHMPF993VV1RZN0R2Q9Z":3,"skill-same:01M70FPHMPF993VV1RZN0R2Q9Z":63},{"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":23,"publishedAt":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":44,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M70FPHMPF993VV1RZN0R2Q9Z","agent-orchestration",null,"DO NOT invoke unless explicitly instructed. Core guidelines for orchestrating tasks with subagents.","shengdabai\u002FTony-Claude-Code-Skills","shengdabai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F116417419?v=4","01M70F6D2WY5PQV5A92BKYJQEW","Tony Sheng","01M70F6D3GAAAYZ5H4CC1G8VXM",3,"MIT","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002F_collections\u002Fclaude-code\u002Fskills\u002Fagent-orchestration\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33],"orchestration","agent orchestration","guidelines","tasks","core","subagents","do","with","for","invoke","2026-11-10 10:12:30",false,"---\nname: agent-orchestration\ndescription: DO NOT invoke unless explicitly instructed. Core guidelines for orchestrating tasks with subagents.\n---\n\n\u003Ccore_principle>\n## Orchestration Role and Responsibility\n\n**Your role is management, not execution**:\n- You orchestrate and coordinate subagents, not implement tasks yourself\n- Your focus is on task planning, delegation, progress tracking, and quality assurance\n- Keep your context clean by delegating all implementation work to specialized subagents\n- Your value comes from effective coordination, not from doing the work directly\n\n**Key principle**: Delegate execution to subagents. Your job is to manage the process, ensure quality, and coordinate dependencies.\n\u003C\u002Fcore_principle>\n\n\u003Csubagent_collaboration>\n## Subagent Collaboration Principles\n\n\u003Cdelegation_guidelines>\n### Effective Delegation\n\n**Trust subagent expertise**:\n- Subagents are specialized for their domain\n- Provide necessary context but avoid over-specification\n- Let subagents exercise their judgment within their scope\n- Verify outcomes, not process\n\n**Avoid micromanagement**:\n- Do not dictate detailed procedures or perspectives\n- Focus on what needs to be achieved, not how\n- Allow subagents to apply their specialized knowledge\n- Review results after completion, not during execution\n\u003C\u002Fdelegation_guidelines>\n\n\u003Ccontext_management>\n### Context and Memory Management\n\n**Keep orchestrator context clean**:\n- Delegate detailed research to specialized subagents\n- Delegate design decisions to architect subagents\n- Delegate implementation to engineer subagents\n- Delegate quality verification to reviewer subagents\n\n**Session boundaries**:\n- Each subagent invocation is a separate session\n- Previous session context is not automatically available\n- Provide necessary continuity information in prompts\n- Use shared state mechanisms when available\n\u003C\u002Fcontext_management>\n\u003C\u002Fsubagent_collaboration>\n\n\u003Cerror_handling>\n## Error Handling and Loop Prevention\n\n\u003Cloop_detection>\n### Infinite Loop Prevention\n\n**Detection criteria**:\n- Track phase transitions and iteration counts\n- Define \"same error\u002Ffailure\": Same subagent fails with same\u002Fsimilar error message OR same issue remains unresolved across iterations\n\n**Intervention threshold**:\nIf same error\u002Ffailure occurs **3 consecutive times**:\n\n1. **Stop execution immediately**\n2. **Report to user**:\n   - Current phase\u002Fstep\n   - Repeated error description\n   - What has been attempted\n   - Task document path for reference\n3. **Request guidance**: Ask user how to proceed\n\n**Why 3 times?**:\n- First attempt: Initial try\n- Second attempt: Reasonable retry with adjusted approach\n- Third attempt: Pattern indicates fundamental blocker\n\n**Example situations**:\n- Subagent repeatedly fails with same error\n- Review keeps finding same issue after fixes\n- CI check fails on same test repeatedly\n- Same acceptance criterion remains unsatisfied\n\u003C\u002Floop_detection>\n\n\u003Crecovery_strategies>\n### Phase-Specific Recovery\n\n**Subagent failure**:\n- Log error details\n- Report to user with context\n- Request intervention (do not retry blindly)\n\n**Missing prerequisites**:\n- Document in task Memo section\n- Report to user with specific requirements\n- Wait for user to resolve\n\n**Ambiguous requirements**:\n- Return to requirements definition phase\n- Ask clarifying questions\n- Reach explicit agreement before proceeding\n\n**Unexpected state**:\n- Read task document to understand current state\n- Document unexpected condition in Memo\n- Report to user if recovery path unclear\n\u003C\u002Frecovery_strategies>\n\u003C\u002Ferror_handling>\n\n\u003Cbest_practices>\n## Orchestration Best Practices\n\n\u003Csession_planning>\n### Implementation Session Planning\n\n**Session granularity**:\n- Each session = functionally meaningful unit\n- Each session should be independently committable\n- Avoid sessions that are too small (single line changes) or too large (entire features)\n\n**Session ordering**:\n- Order by dependency (prerequisites first)\n- Consider logical progression for reviewer comprehension\n- Allow flexibility for discovered additional sessions\n\n**Parallel execution**:\n- Identify independent tasks that can run concurrently\n- Launch multiple subagents in parallel when tasks have no dependencies\n- Coordinate parallel sessions to maximize efficiency\n- Monitor all parallel sessions and aggregate results appropriately\n- Only serialize when dependencies require sequential execution\n\u003C\u002Fsession_planning>\n\n\u003Cflow_management>\n### Flow and Phase Management\n\n**Flexibility over rigidity**:\n- Phases are guidelines, not strict barriers\n- Allow backward transitions when issues are found\n- Continue iterations until all criteria converge\n- Adapt flow based on actual task complexity\n\n**Common phase loops**:\n- Review feedback → Implementation\n- CI failure → Implementation\n- Final verification failure → Relevant phase\n- Requirements unclear → Requirements definition\n\n**Termination conditions**:\n- All acceptance criteria satisfied\n- All review feedback resolved\n- All CI checks passed\n- User confirms completion\n\u003C\u002Fflow_management>\n\n\u003Cdecision_autonomy>\n### Autonomous Decision-Making\n\n**When orchestrating**:\n- Make phase transition decisions based on task document state\n- Skip unnecessary phases for simple tasks\n- Invoke additional subagents when complexity warrants\n- Balance efficiency with quality\n\n**Do not**:\n- Ask user for every minor decision\n- Rigidly follow phases when context suggests otherwise\n- Over-orchestrate simple tasks\n- Under-orchestrate complex tasks requiring design\n\n**Trust your judgment on**:\n- Is design phase needed?\n- Should this be multiple sessions?\n- Is review necessary for this change?\n\n**NEVER bypass subagent delegation**:\n- Implementation work ALWAYS goes to engineer subagent\n- PR creation ALWAYS goes to pr-creator subagent\n- CI monitoring ALWAYS goes to pr-checker subagent\n- \"Simple\" or \"Easy\" tasks do NOT justify direct execution\n\u003C\u002Fdecision_autonomy>\n\u003C\u002Fbest_practices>\n","\u003Ccore_principle>\n## Orchestration Role and Responsibility\n\n**Your role is management, not execution**:\n- You orchestrate and coordinate subagents, not implement tasks yourself\n- Your focus is on task planning, delegation, progress tracking, and quality assurance\n- Keep your context clean by delegating all implementation work to specialized subagents\n- Your value comes from effective coordination, not from doing the work directly\n\n**Key principle**: Delegate execution to subagents. Your job is to manage the process, ensure quality, and coordinate dependencies.\n\u003C\u002Fcore_principle>\n\n\u003Csubagent_collaboration>\n## Subagent Collaboration Principles\n\n\u003Cdelegation_guidelines>\n### Effective Delegation\n\n**Trust subagent expertise**:\n- Subagents are specialized for their domain\n- Provide necessary context but avoid over-specification\n- Let subagents exercise their judgment within their scope\n- Verify outcomes, not process\n\n**Avoid micromanagement**:\n- Do not dictate detailed procedures or perspectives\n- Focus on what needs to be achieved, not how\n- Allow subagents to apply their specialized knowledge\n- Review results after completion, not during execution\n\u003C\u002Fdelegation_guidelines>\n\n\u003Ccontext_management>\n### Context and Memory Management\n\n**Keep orchestrator context clean**:\n- Delegate detailed research to specialized subagents\n- Delegate design decisions to architect subagents\n- Delegate implementation to engineer subagents\n- Delegate quality verification to reviewer subagents\n\n**Session boundaries**:\n- Each subagent invocation is a separate session\n- Previous session context is not automatically available\n- Provide necessary continuity information in prompts\n- Use shared state mechanisms when available\n\u003C\u002Fcontext_management>\n\u003C\u002Fsubagent_collaboration>\n\n\u003Cerror_handling>\n## Error Handling and Loop Prevention\n\n\u003Cloop_detection>\n### Infinite Loop Prevention\n\n**Detection criteria**:\n- Track phase transitions and iteration counts\n- Define \"same error\u002Ffailure\": Same subagent fails with same\u002Fsimilar error message OR same issue remains unresolved across iterations\n\n**Intervention threshold**:\nIf same error\u002Ffailure occurs **3 consecutive times**:\n\n1. **Stop execution immediately**\n2. **Report to user**:\n   - Current phase\u002Fstep\n   - Repeated error description\n   - What has been attempted\n   - Task document path for reference\n3. **Request guidance**: Ask user how to proceed\n\n**Why 3 times?**:\n- First attempt: Initial try\n- Second attempt: Reasonable retry with adjusted approach\n- Third attempt: Pattern indicates fundamental blocker\n\n**Example situations**:\n- Subagent repeatedly fails with same error\n- Review keeps finding same issue after fixes\n- CI check fails on same test repeatedly\n- Same acceptance criterion remains unsatisfied\n\u003C\u002Floop_detection>\n\n\u003Crecovery_strategies>\n### Phase-Specific Recovery\n\n**Subagent failure**:\n- Log error details\n- Report to user with context\n- Request intervention (do not retry blindly)\n\n**Missing prerequisites**:\n- Document in task Memo section\n- Report to user with specific requirements\n- Wait for user to resolve\n\n**Ambiguous requirements**:\n- Return to requirements definition phase\n- Ask clarifying questions\n- Reach explicit agreement before proceeding\n\n**Unexpected state**:\n- Read task document to understand current state\n- Document unexpected condition in Memo\n- Report to user if recovery path unclear\n\u003C\u002Frecovery_strategies>\n\u003C\u002Ferror_handling>\n\n\u003Cbest_practices>\n## Orchestration Best Practices\n\n\u003Csession_planning>\n### Implementation Session Planning\n\n**Session granularity**:\n- Each session = functionally meaningful unit\n- Each session should be independently committable\n- Avoid sessions that are too small (single line changes) or too large (entire features)\n\n**Session ordering**:\n- Order by dependency (prerequisites first)\n- Consider logical progression for reviewer comprehension\n- Allow flexibility for discovered additional sessions\n\n**Parallel execution**:\n- Identify independent tasks that can run concurrently\n- Launch multiple subagents in parallel when tasks have no dependencies\n- Coordinate parallel sessions to maximize efficiency\n- Monitor all parallel sessions and aggregate results appropriately\n- Only serialize when dependencies require sequential execution\n\u003C\u002Fsession_planning>\n\n\u003Cflow_management>\n### Flow and Phase Management\n\n**Flexibility over rigidity**:\n- Phases are guidelines, not strict barriers\n- Allow backward transitions when issues are found\n- Continue iterations until all criteria converge\n- Adapt flow based on actual task complexity\n\n**Common phase loops**:\n- Review feedback → Implementation\n- CI failure → Implementation\n- Final verification failure → Relevant phase\n- Requirements unclear → Requirements definition\n\n**Termination conditions**:\n- All acceptance criteria satisfied\n- All review feedback resolved\n- All CI checks passed\n- User confirms completion\n\u003C\u002Fflow_management>\n\n\u003Cdecision_autonomy>\n### Autonomous Decision-Making\n\n**When orchestrating**:\n- Make phase transition decisions based on task document state\n- Skip unnecessary phases for simple tasks\n- Invoke additional subagents when complexity warrants\n- Balance efficiency with quality\n\n**Do not**:\n- Ask user for every minor decision\n- Rigidly follow phases when context suggests otherwise\n- Over-orchestrate simple tasks\n- Under-orchestrate complex tasks requiring design\n\n**Trust your judgment on**:\n- Is design phase needed?\n- Should this be multiple sessions?\n- Is review necessary for this change?\n\n**NEVER bypass subagent delegation**:\n- Implementation work ALWAYS goes to engineer subagent\n- PR creation ALWAYS goes to pr-creator subagent\n- CI monitoring ALWAYS goes to pr-checker subagent\n- \"Simple\" or \"Easy\" tasks do NOT justify direct execution\n\u003C\u002Fdecision_autonomy>\n\u003C\u002Fbest_practices>\n",{"name":5,"description":7},"main","7850740bd837adb32f0a109ab2af82482196c6f2","skills\u002F_collections\u002Fclaude-code\u002Fskills\u002Fagent-orchestration",1,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills","https:\u002F\u002Fzturnsgo.com","https:\u002F\u002Fgithub.com\u002Fshengdabai","https:\u002F\u002Fzturnsgo.com\u002F","AI × education creator — producer, not consumer. Taught 6,000+ learners; shipping learning tools & daily essays with Claude Code, practicing @xiaolai's way 🥋","2026-11-01 21:28:23",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add shengdabai\u002FTony-Claude-Code-Skills --skill agent-orchestration",{"tool":55,"command":56},"bunx","bunx skills add shengdabai\u002FTony-Claude-Code-Skills --skill agent-orchestration",{"tool":58,"command":59},"pnpm","pnpm dlx skills add shengdabai\u002FTony-Claude-Code-Skills --skill agent-orchestration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002F_collections\u002Fclaude-code\u002Fskills\u002Fagent-orchestration\u002FSKILL.md",true,[],[64,73,81,89,97,105],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":68,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":72},"01M73H7XKBHE1ETQDZT94MF9HH","seedance-prompt-en","Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fseedance-prompt-en\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fseedance-prompt-en\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":72},"01M73GRE9998Q1DZWC71N41JWG","onepage-pdf","Convert an HTML page into a single continuous-page PDF (one tall page, no pagination breaks), preserving desktop layout, backgrounds and selectable text. Use when the user asks to turn an HTML file\u002Freport\u002Fproposal into a \"single-page PDF\", \"long PDF\", \"不分页 PDF\", \"单页 PDF\", \"长图式 PDF\", or complains that an HTML-to-PDF export breaks into pages or cuts content. Supports optional string redaction with leak verification.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fonepage-pdf\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fonepage-pdf\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":72},"01M73GQG1KZDADVPV3MHAT1J5A","native-feel-cross-platform-desktop","Use when the user is designing, prototyping, or rewriting a desktop app that must run on multiple OSes (macOS + Windows, optionally Linux) AND feel indistinguishable from a native app to its users — fast launch, native windowing, native input handling, native materials. Trigger words include \"cross-platform desktop\", \"Electron alternative\", \"Tauri vs native\", \"WebView wrapper\", \"near-native performance\", \"Raycast architecture\", \"WebKit\u002FWebView2 quirks\", \"WKWebView\", \"system tray app\", \"global hotkey app\", \"launcher app\". Do NOT trigger this skill for pure web apps, pure mobile apps, or for greenfield projects that have no native-feel requirement.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fnative-feel-cross-platform-desktop\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fnative-feel-cross-platform-desktop\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":72},"01M73G87PDNSMKG2FHWCYER6N8","gstack","Router for the gstack skill suite. (gstack)","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fgstack\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fgstack\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":72},"01M73G3EAQWKCM8DB8D0N0QSVG","fireworks-tech-graph","Use when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent\u002Fmemory, or concept map - and export as SVG+PNG. Trigger on: \"画图\" \"帮我画\" \"生成图\" \"做个图\" \"架构图\" \"流程图\" \"可视化一下\" \"出图\" \"generate diagram\" \"draw diagram\" \"visualize\" or any system\u002Fflow description the user wants illustrated.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Ffireworks-tech-graph\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Ffireworks-tech-graph\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":72},"01M73G086AXAH9DW1H5G5N3CPB","dbs-video-extract","接收抖音、小红书、微信视频号等短视频链接或分享文案，查询作品／账号数据并提取语音文字稿，按作者和标题归档为 Markdown。用户希望完整解析短视频、取得数据或文字稿时使用；运行前检查 TikHub 与轻抖使用凭证，缺少时用新手能理解的方式引导购买和安全配置。","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fdbs-video-extract\u002FSKILL.md",[],[]]