[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6P59PCEQF5XFDVMMYAZJTSA":3,"skill-same:01M6P59PCEQF5XFDVMMYAZJTSA":94},{"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":72,"commitSha":73,"skillDirectory":74,"forksCount":75,"repositoryHtmlUrl":76,"repositoryHomepageUrl":6,"ownerHtmlUrl":77,"ownerBlogUrl":78,"ownerDescription":6,"updatedAt":79,"install":80,"resources":93},"01M6P59PCEQF5XFDVMMYAZJTSA","workflow-router",null,"Routes user goals to the appropriate specialist agent workflow with resource allocation confirmation. Use when: the user wants to start a task but has not specified a workflow, asks 'how should I approach this?', or needs orchestration across research → plan → build → fix stages.","DojoGenesis\u002Fgateway","DojoGenesis","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F273886418?v=4","01M6P54RXMD3TZ2082Z3Z4JMQP","Cruz Morales (TresPies)","01M6P54S269YR0ZZZ96WGQM439",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fagent-orchestration\u002Fskills\u002Fworkflow-router\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","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],"workflow","router","workflow router","which","orchestration","sure","agent-orchestration","resource allocation","false","classify","across","route","goal","fix","confirmation","plan","how","Meta","orchestrate","tasks","2026-11-10 10:12:30",false,"---\nname: workflow-router\nmodel: sonnet\ndescription: \"Routes user goals to the appropriate specialist agent workflow with resource allocation confirmation. Use when: the user wants to start a task but has not specified a workflow, asks 'how should I approach this?', or needs orchestration across research → plan → build → fix stages.\"\ncategory: agent-orchestration\ntriggers:\n  - \"how should I approach this\"\n  - \"route this to the right workflow\"\n  - \"orchestrate across research plan build fix\"\n  - \"start a task but not sure which workflow\"\ntier: 1\nagents:\n  - \"primary\"\ntool_dependencies:\n  - \"meta_skill\"\n  - \"file_system\"\n\ninputs:\n  - name: goal\n    type: string\n    description: User's stated goal or task description — the router will classify and route it\n    required: false\noutputs:\n  - name: routed_workflow\n    type: string\n    description: Confirmation of the agent(s) dispatched and their assigned tasks, with handoff paths\n---\n\n# Workflow Router\n\nRoutes user goals to the appropriate specialist agent workflow with explicit resource allocation and confirmation before dispatch.\n\n## Description\n\nClassifies an incoming goal into one of four categories (Research, Plan, Build, Fix), maps it to the appropriate specialist agent(s), confirms resource allocation with the user, and dispatches. Handles the Fix workflow as a two-stage process (investigate first, then implement). Preserves context across agent handoffs using shared handoff documents. This skill is the entry point for multi-agent orchestration when the user knows what they want to accomplish but not which agent or workflow to use.\n\n## When to Use\n\n- User wants to start a non-trivial task without specifying a workflow\n- User asks \"how should I approach this?\" or \"what's the best way to tackle X?\"\n- A task requires multiple sequential agents (Research → Plan → Build)\n- You need explicit resource allocation agreement before spawning agents\n\n## Workflow\n\n### Step 1: Classify the Goal\n\nIf the goal is not provided or is ambiguous, ask:\n\n```\nWhat's your primary goal for this task?\n\n- Research — Understand\u002Fexplore something (unfamiliar code, libraries, concepts)\n- Plan — Design\u002Farchitect a solution (implementation plans, problem decomposition)\n- Build — Implement\u002Fcode something (new features, components, implementation from a plan)\n- Fix — Debug\u002Ffix an issue (investigate and resolve bugs, failing tests)\n```\n\nIf intent is clear from context (e.g., \"this test is failing\" → Fix), infer without asking.\n\n### Step 2: Check for Existing Plans\n\n```bash\nls thoughts\u002Fshared\u002Fplans\u002F*.md 2>\u002Fdev\u002Fnull || ls docs\u002Fplans\u002F*.md 2>\u002Fdev\u002Fnull\n```\n\n- **Build goal:** Ask if implementing an existing plan; load it to avoid duplication\n- **Plan goal:** Surface existing plans to prevent redundant work\n- **Research \u002F Fix:** Proceed without plan check\n\n### Step 3: Confirm Resource Allocation\n\nPresent options and confirm before spawning:\n\n```\nHow would you like to allocate resources?\n\n- Conservative — 1-2 agents, sequential (minimal context, simple tasks)\n- Balanced (recommended) — appropriate agents for the task, some parallelism\n- Aggressive — max parallel agents (time-critical tasks)\n- Auto — system decides based on complexity\n```\n\nDefault to **Balanced** for unspecified or Auto selection.\n\n### Step 4: Map Goal to Agent\n\n| Goal | Primary Agent Type | Description |\n|------|-------------------|-------------|\n| Research | general-purpose (research mode) | Multi-source research using web and documentation tools |\n| Plan | Plan | Create phased implementation plans with architectural trade-offs |\n| Build | general-purpose (implementation mode) | Coding tasks, feature implementation, component creation |\n| Fix | general-purpose (debug mode) → then implementation | Investigate first, implement fix after diagnosis |\n\n**Fix workflow (two stages):**\n1. Spawn debug agent to investigate: produce diagnosis and recommended fix\n2. If fix requires code changes, spawn implementation agent with the diagnosis as context\n\n### Step 5: Show Execution Summary and Confirm\n\n```\n## Execution Summary\n\nGoal: [Research \u002F Plan \u002F Build \u002F Fix]\nResource Allocation: [Conservative \u002F Balanced \u002F Aggressive]\nAgent(s) to dispatch: [agent descriptions]\n\nWhat will happen:\n- [Brief description of each agent's task]\n- [Expected output \u002F deliverable and where it will be written]\n\nProceed? [Yes \u002F Adjust settings]\n```\n\nWait for confirmation before dispatching. If \"Adjust settings\", return to the relevant step.\n\n### Step 6: Dispatch Agents\n\n#### Research\n\n```\nDispatch: general-purpose agent (research mode)\n\nPrompt:\n  Research: [topic]\n  Scope: [what to investigate — libraries, APIs, patterns, concepts]\n  Output: Write findings to research\u002F[topic-slug].md and summarize key points\n```\n\n#### Plan\n\n```\nDispatch: Plan agent\n\nPrompt:\n  Create implementation plan for: [feature\u002Ftask]\n  Context: [relevant codebase context, constraints, goals]\n  Output: Save plan to docs\u002Fplans\u002F[plan-slug].md with phased breakdown and trade-offs\n```\n\n#### Build\n\nIf a plan exists, summarize risks before dispatching:\n- Identify any HIGH severity blockers (missing dependencies, ambiguous interfaces)\n- Surface them to the user before proceeding\n\n```\nDispatch: general-purpose agent (implementation mode)\n\nPrompt:\n  Implement: [task]\n  Plan: [path to plan, if applicable]\n  Constraints: [language, framework, test requirements]\n  Output: Working implementation with tests passing; write handoff to handoffs\u002F[session]\u002F\n```\n\n#### Fix (two stages)\n\n```\nStage 1 — Dispatch: general-purpose agent (debug mode)\n\nPrompt:\n  Investigate: [issue description]\n  Symptoms: [what's failing, error messages, test output]\n  Output: Diagnosis document with root cause and recommended fix path\n\nStage 2 — (after diagnosis) Dispatch: general-purpose agent (implementation mode)\n\nPrompt:\n  Fix: [issue as diagnosed]\n  Diagnosis: [diagnosis document path]\n  Output: Working fix with tests passing\n```\n\n## Handoff Preservation\n\nEach dispatched agent should write a handoff before completing:\n```\nhandoffs\u002F{session-id}\u002F{agent-type}-{timestamp}.md\n```\n\nThe handoff captures: what was accomplished, what was found, decisions made, open questions, and what the next agent needs to know.\n\n## Output\n\nA confirmation message showing:\n- Which agent(s) were dispatched\n- Their assigned prompts\n- Expected output locations\n- Status after dispatch completes\n","# Workflow Router\n\nRoutes user goals to the appropriate specialist agent workflow with explicit resource allocation and confirmation before dispatch.\n\n## Description\n\nClassifies an incoming goal into one of four categories (Research, Plan, Build, Fix), maps it to the appropriate specialist agent(s), confirms resource allocation with the user, and dispatches. Handles the Fix workflow as a two-stage process (investigate first, then implement). Preserves context across agent handoffs using shared handoff documents. This skill is the entry point for multi-agent orchestration when the user knows what they want to accomplish but not which agent or workflow to use.\n\n## When to Use\n\n- User wants to start a non-trivial task without specifying a workflow\n- User asks \"how should I approach this?\" or \"what's the best way to tackle X?\"\n- A task requires multiple sequential agents (Research → Plan → Build)\n- You need explicit resource allocation agreement before spawning agents\n\n## Workflow\n\n### Step 1: Classify the Goal\n\nIf the goal is not provided or is ambiguous, ask:\n\n```\nWhat's your primary goal for this task?\n\n- Research — Understand\u002Fexplore something (unfamiliar code, libraries, concepts)\n- Plan — Design\u002Farchitect a solution (implementation plans, problem decomposition)\n- Build — Implement\u002Fcode something (new features, components, implementation from a plan)\n- Fix — Debug\u002Ffix an issue (investigate and resolve bugs, failing tests)\n```\n\nIf intent is clear from context (e.g., \"this test is failing\" → Fix), infer without asking.\n\n### Step 2: Check for Existing Plans\n\n```bash\nls thoughts\u002Fshared\u002Fplans\u002F*.md 2>\u002Fdev\u002Fnull || ls docs\u002Fplans\u002F*.md 2>\u002Fdev\u002Fnull\n```\n\n- **Build goal:** Ask if implementing an existing plan; load it to avoid duplication\n- **Plan goal:** Surface existing plans to prevent redundant work\n- **Research \u002F Fix:** Proceed without plan check\n\n### Step 3: Confirm Resource Allocation\n\nPresent options and confirm before spawning:\n\n```\nHow would you like to allocate resources?\n\n- Conservative — 1-2 agents, sequential (minimal context, simple tasks)\n- Balanced (recommended) — appropriate agents for the task, some parallelism\n- Aggressive — max parallel agents (time-critical tasks)\n- Auto — system decides based on complexity\n```\n\nDefault to **Balanced** for unspecified or Auto selection.\n\n### Step 4: Map Goal to Agent\n\n| Goal | Primary Agent Type | Description |\n|------|-------------------|-------------|\n| Research | general-purpose (research mode) | Multi-source research using web and documentation tools |\n| Plan | Plan | Create phased implementation plans with architectural trade-offs |\n| Build | general-purpose (implementation mode) | Coding tasks, feature implementation, component creation |\n| Fix | general-purpose (debug mode) → then implementation | Investigate first, implement fix after diagnosis |\n\n**Fix workflow (two stages):**\n1. Spawn debug agent to investigate: produce diagnosis and recommended fix\n2. If fix requires code changes, spawn implementation agent with the diagnosis as context\n\n### Step 5: Show Execution Summary and Confirm\n\n```\n## Execution Summary\n\nGoal: [Research \u002F Plan \u002F Build \u002F Fix]\nResource Allocation: [Conservative \u002F Balanced \u002F Aggressive]\nAgent(s) to dispatch: [agent descriptions]\n\nWhat will happen:\n- [Brief description of each agent's task]\n- [Expected output \u002F deliverable and where it will be written]\n\nProceed? [Yes \u002F Adjust settings]\n```\n\nWait for confirmation before dispatching. If \"Adjust settings\", return to the relevant step.\n\n### Step 6: Dispatch Agents\n\n#### Research\n\n```\nDispatch: general-purpose agent (research mode)\n\nPrompt:\n  Research: [topic]\n  Scope: [what to investigate — libraries, APIs, patterns, concepts]\n  Output: Write findings to research\u002F[topic-slug].md and summarize key points\n```\n\n#### Plan\n\n```\nDispatch: Plan agent\n\nPrompt:\n  Create implementation plan for: [feature\u002Ftask]\n  Context: [relevant codebase context, constraints, goals]\n  Output: Save plan to docs\u002Fplans\u002F[plan-slug].md with phased breakdown and trade-offs\n```\n\n#### Build\n\nIf a plan exists, summarize risks before dispatching:\n- Identify any HIGH severity blockers (missing dependencies, ambiguous interfaces)\n- Surface them to the user before proceeding\n\n```\nDispatch: general-purpose agent (implementation mode)\n\nPrompt:\n  Implement: [task]\n  Plan: [path to plan, if applicable]\n  Constraints: [language, framework, test requirements]\n  Output: Working implementation with tests passing; write handoff to handoffs\u002F[session]\u002F\n```\n\n#### Fix (two stages)\n\n```\nStage 1 — Dispatch: general-purpose agent (debug mode)\n\nPrompt:\n  Investigate: [issue description]\n  Symptoms: [what's failing, error messages, test output]\n  Output: Diagnosis document with root cause and recommended fix path\n\nStage 2 — (after diagnosis) Dispatch: general-purpose agent (implementation mode)\n\nPrompt:\n  Fix: [issue as diagnosed]\n  Diagnosis: [diagnosis document path]\n  Output: Working fix with tests passing\n```\n\n## Handoff Preservation\n\nEach dispatched agent should write a handoff before completing:\n```\nhandoffs\u002F{session-id}\u002F{agent-type}-{timestamp}.md\n```\n\nThe handoff captures: what was accomplished, what was found, decisions made, open questions, and what the next agent needs to know.\n\n## Output\n\nA confirmation message showing:\n- Which agent(s) were dispatched\n- Their assigned prompts\n- Expected output locations\n- Status after dispatch completes\n",{"name":5,"tier":52,"model":53,"agents":54,"inputs":56,"outputs":60,"category":33,"triggers":64,"description":7,"tool_dependencies":69},1,"sonnet",[55],"primary",[57],{"name":39,"type":58,"required":48,"description":59},"string","User's stated goal or task description — the router will classify and route it",[61],{"name":62,"type":58,"description":63},"routed_workflow","Confirmation of the agent(s) dispatched and their assigned tasks, with handoff paths",[65,66,67,68],"how should I approach this","route this to the right workflow","orchestrate across research plan build fix","start a task but not sure which workflow",[70,71],"meta_skill","file_system","main","ff07df5fd8f75762c2a131e6e26d297e8ae403ee","plugins\u002Fagent-orchestration\u002Fskills\u002Fworkflow-router",0,"https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway","https:\u002F\u002Fgithub.com\u002FDojoGenesis","dojogenesis.com","2026-10-25 22:59:58",{"source":8,"skillName":5,"commands":81,"prompt":91,"zipAvailable":92},[82,85,88],{"tool":83,"command":84},"npx","npx skills add DojoGenesis\u002Fgateway --skill workflow-router",{"tool":86,"command":87},"bunx","bunx skills add DojoGenesis\u002Fgateway --skill workflow-router",{"tool":89,"command":90},"pnpm","pnpm dlx skills add DojoGenesis\u002Fgateway --skill workflow-router","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fagent-orchestration\u002Fskills\u002Fworkflow-router\u002FSKILL.md",true,[],[95,114,125,133,173,198],{"skillNo":96,"name":97,"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":98,"categories":99,"keywords":103,"publishedAt":47},"01M6P6J0WYSD1MTGA3ZX6MGGZ5","kata-test-echo","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fserver\u002Ftestdata\u002Fkata\u002Fskills\u002Fkata-test-echo\u002FSKILL.md",[100],{"categoryNo":101,"categoryName":102,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[104,105,106,107,108,109,110,111,112,113],"kata test echo","Echo","test","json","v1","output","input","structured","contracts","schema",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":121,"publishedAt":47},"01M6P6HQJNGG4WPZW0DEWMAY2N","kata-plain","An ordinary prose skill; not dispatchable.","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fserver\u002Ftestdata\u002Fkata\u002Fskills\u002Fkata-plain\u002FSKILL.md",[120],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[122,123,124],"kata plain","prose skill","prose",{"skillNo":126,"name":127,"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":128,"categories":129,"keywords":130,"publishedAt":47},"01M6P6HH6Y7K8K6606MF7VZ1HB","kata-broken","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fserver\u002Ftestdata\u002Fkata\u002Fskills\u002Fkata-broken\u002FSKILL.md",[],[131,132,111,112,105,113,107,106,110,108,109],"kata broken","broken",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":153,"publishedAt":47},"01M6P6GW520QJ03A6K7Y5PWJ52","voice-before-structure","Read the project's design language and philosophy before writing structural artifacts. Ground manifests, READMEs, and descriptions in the project's voice, not boilerplate. Use when creating manifests or READMEs for established projects, writing ecosystem-level documentation, building plugin descriptions or marketplace metadata, or authoring metadata that carries a project's identity. Trigger phrases: 'write the manifest', 'create a README', 'describe this plugin', 'ground yourself in the philosophy', 'ecosystem-level work'.","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fwisdom-garden\u002Fskills\u002Fvoice-before-structure\u002FSKILL.md",[139,142,145,150],{"categoryNo":140,"categoryName":141,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":143,"categoryName":144,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":146,"categoryName":147,"taxonomyType":148,"taxonomyTypeDesc":149},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",{"categoryNo":151,"categoryName":152,"taxonomyType":148,"taxonomyTypeDesc":149},"01JBSEEDCAT000000000000036","内容创作者",[154,155,156,157,158,35,159,160,161,162,163,164,165,166,167,168,169,170,171,172],"voice before structure","structure","voice","manifests","ecosystem","authoring","structural","project","artifact","philosophy","design","writing","identity","documentation","create","projects","work","read","write",{"skillNo":174,"name":175,"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":180,"publishedAt":47},"01M6P6GMNA4HJ4D5RRM3BQZ73M","system-prompt-archaeology","Produces a named ADA disposition preset (YAML) and a layered behavioral analysis (structural decomposition + evidence-cited classifications) from a system prompt. Use when: \"analyze this system prompt\", \"extract disposition from prompt\", \"reverse-engineer agent behavior\", \"what patterns does this prompt use\", \"build a preset from this prompt\".","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fwisdom-garden\u002Fskills\u002Fsystem-prompt-archaeology\u002FSKILL.md",[179],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[181,182,183,184,185,36,160,186,187,188,189,190,191,192,193,194,195,53,196,197],"system prompt archaeology","system prompt","prompt","system","behavioral","decomposition","wisdom","patterns","engineer","decompose","evidence","ada","analyze","analysis","STRING","true","reverse",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":205,"publishedAt":47},"01M6P6G2D70T9R00HX6K154X5Y","session-lifecycle-automation","Designs and configures all three loops of solo-operator session automation — session bookends, background maintenance agents, and a delegation flywheel. Use when setting up a new workspace, recovering from the 44% zero-artifact session leak, or preparing to scale delegation across multiple concurrent agents.","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fwisdom-garden\u002Fskills\u002Fsession-lifecycle-automation\u002FSKILL.md",[204],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[206,207,208,209,210,211,212,213,214,215,216,217,218,162,219,37,220,221,222,223],"automation","session lifecycle automation","session lifecycle","lifecycle","session","markdown","configure","directory","config","delegation","audit","SET","files","solo","scheduled","loops","up","template"]