[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75MC7MC9QQE3VB05R2F9XKH":3,"skill-same:01M75MC7MC9QQE3VB05R2F9XKH":70},{"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":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M75MC7MC9QQE3VB05R2F9XKH","Workflow Orchestrator",null,"Coordinates multi-skill execution pipelines (e.g., research → plan → build → test)","Razaib-khan\u002FForgeWeave","Razaib-khan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160170334?v=4","01M75M7QPJVP3N29AZVG6RN6R7","Razaib Khan","01M75M7QQS6KEPD0W2ZB99ENKK",1,"MIT","https:\u002F\u002Fgithub.com\u002FRazaib-khan\u002FForgeWeave\u002Fblob\u002Fmain\u002Fsrc\u002Fforgeweave\u002Ftemplates\u002Fgemini\u002F.gemini\u002Fskills\u002Fworkflow-orchestrator\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nskill_id: workflow-orchestrator\nname: Workflow Orchestrator\nversion: 1.0.0\ndescription: Coordinates multi-skill execution pipelines (e.g., research → plan → build → test)\nauthor: ForgeWeave Core\ntui_compatibility:\n  - opencode\n  - claude\n  - gemini\n  - qwen\ntags:\n  - orchestration\n  - pipeline\n  - workflow\n---\n\n# Workflow Orchestrator\n\n## Purpose\n\nCoordinate the execution of multiple skills in sequence or parallel to achieve a complex goal. Handles dependency resolution, data passing between skills, error recovery, and progress reporting. The top-level orchestrator that makes multi-step agentic workflows reliable.\n\n## When to Use\n\n- A complex goal requires 3+ skills in sequence (e.g., research → plan → build → test)\n- Multiple independent subtasks can run in parallel\n- A pipeline needs retry logic or error recovery\n- The user wants a multi-step workflow executed end-to-end\n\n## When Not to Use\n\n- Only one skill is needed — invoke it directly\n- The steps are manual and need user approval at each stage\n- The workflow is a simple linear script — use a script instead\n\n## Inputs\n\n| Input | Type | Required | Description |\n|---|---|---|---|\n| `goal` | string | Yes | The overall objective |\n| `pipeline_definition` | array | No | Explicit skill order if known (auto-generated if omitted) |\n| `fallback_strategy` | enum | No (default: stop) | stop, retry, skip |\n\n## Expected Outputs\n\n| Output | Description |\n|---|---|\n| Pipeline result | The output of the final skill |\n| Execution trace | What ran, in what order, what each produced |\n| Status report | Success, failures, and retries |\n\n## Exact Workflow Steps\n\n1. Accept the goal from the user or from a command\n2. Decompose the goal into ordered skills using `planner` skill\n3. Identify dependencies between skills (blocking, parallel, sequential)\n4. Execute skills in dependency order:\n   - Parallel skills run concurrently\n   - Sequential skills run in order, passing outputs\n5. After each skill, validate output using `validation-engine`\n6. On failure: retry, skip, or stop based on fallback strategy\n7. Report results to user with execution trace\n\n## Required Checks\n\n- [ ] All skills in the pipeline are available\n- [ ] Dependency order is correct (no cycles)\n- [ ] Each skill's output is valid before passing to next\n- [ ] Fallback strategy is defined for every pipeline step\n\n## Failure Modes\n\n| Failure Condition | Response |\n|---|---|\n| Required skill not available | Report missing skill and suggest alternatives |\n| Pipeline step fails after retries | Report failure with partial results |\n| Circular dependency detected | Restructure to eliminate the cycle |\n\n## Examples\n\n### Example: Feature development pipeline\n1. planner → decompose: code design, implement, test, document\n2. architecture-designer → design module structure\n3. code-builder → implement (depends on architecture-designer)\n4. test-generator → create tests (parallel with docs)\n5. validation-engine → validate all outputs\n6. Report results\n\n## References\n\n| Reference | Path |\n|---|---|\n| Planner skill | `..\u002Fplanner\u002FSKILL.md` |\n| Validation Engine skill | `..\u002Fvalidation-engine\u002FSKILL.md` |\n| Command Executor skill | `..\u002Fcommand-executor\u002FSKILL.md` |\n","# Workflow Orchestrator\n\n## Purpose\n\nCoordinate the execution of multiple skills in sequence or parallel to achieve a complex goal. Handles dependency resolution, data passing between skills, error recovery, and progress reporting. The top-level orchestrator that makes multi-step agentic workflows reliable.\n\n## When to Use\n\n- A complex goal requires 3+ skills in sequence (e.g., research → plan → build → test)\n- Multiple independent subtasks can run in parallel\n- A pipeline needs retry logic or error recovery\n- The user wants a multi-step workflow executed end-to-end\n\n## When Not to Use\n\n- Only one skill is needed — invoke it directly\n- The steps are manual and need user approval at each stage\n- The workflow is a simple linear script — use a script instead\n\n## Inputs\n\n| Input | Type | Required | Description |\n|---|---|---|---|\n| `goal` | string | Yes | The overall objective |\n| `pipeline_definition` | array | No | Explicit skill order if known (auto-generated if omitted) |\n| `fallback_strategy` | enum | No (default: stop) | stop, retry, skip |\n\n## Expected Outputs\n\n| Output | Description |\n|---|---|\n| Pipeline result | The output of the final skill |\n| Execution trace | What ran, in what order, what each produced |\n| Status report | Success, failures, and retries |\n\n## Exact Workflow Steps\n\n1. Accept the goal from the user or from a command\n2. Decompose the goal into ordered skills using `planner` skill\n3. Identify dependencies between skills (blocking, parallel, sequential)\n4. Execute skills in dependency order:\n   - Parallel skills run concurrently\n   - Sequential skills run in order, passing outputs\n5. After each skill, validate output using `validation-engine`\n6. On failure: retry, skip, or stop based on fallback strategy\n7. Report results to user with execution trace\n\n## Required Checks\n\n- [ ] All skills in the pipeline are available\n- [ ] Dependency order is correct (no cycles)\n- [ ] Each skill's output is valid before passing to next\n- [ ] Fallback strategy is defined for every pipeline step\n\n## Failure Modes\n\n| Failure Condition | Response |\n|---|---|\n| Required skill not available | Report missing skill and suggest alternatives |\n| Pipeline step fails after retries | Report failure with partial results |\n| Circular dependency detected | Restructure to eliminate the cycle |\n\n## Examples\n\n### Example: Feature development pipeline\n1. planner → decompose: code design, implement, test, document\n2. architecture-designer → design module structure\n3. code-builder → implement (depends on architecture-designer)\n4. test-generator → create tests (parallel with docs)\n5. validation-engine → validate all outputs\n6. Report results\n\n## References\n\n| Reference | Path |\n|---|---|\n| Planner skill | `..\u002Fplanner\u002FSKILL.md` |\n| Validation Engine skill | `..\u002Fvalidation-engine\u002FSKILL.md` |\n| Command Executor skill | `..\u002Fcommand-executor\u002FSKILL.md` |\n",{"name":5,"tags":24,"author":28,"version":29,"skill_id":30,"description":7,"tui_compatibility":31},[25,26,27],"orchestration","pipeline","workflow","ForgeWeave Core","1.0.0","workflow-orchestrator",[32,33,34,35],"opencode","claude","gemini","qwen","main","93f2582acd699b8d3917b2b61fdd2178b69f921c","src\u002Fforgeweave\u002Ftemplates\u002Fgemini\u002F.gemini\u002Fskills\u002Fworkflow-orchestrator",0,"https:\u002F\u002Fgithub.com\u002FRazaib-khan\u002FForgeWeave","https:\u002F\u002Fgithub.com\u002FRazaib-khan","Web dev & AI explorer | Building, breaking, learning | Long-term mindset","2026-06-22 22:46:11",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add Razaib-khan\u002FForgeWeave --skill \"Workflow Orchestrator\"",{"tool":50,"command":51},"bunx","bunx skills add Razaib-khan\u002FForgeWeave --skill \"Workflow Orchestrator\"",{"tool":53,"command":54},"pnpm","pnpm dlx skills add Razaib-khan\u002FForgeWeave --skill \"Workflow Orchestrator\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRazaib-khan\u002FForgeWeave\u002Fblob\u002Fmain\u002Fsrc\u002Fforgeweave\u002Ftemplates\u002Fgemini\u002F.gemini\u002Fskills\u002Fworkflow-orchestrator\u002FSKILL.md",true,[58,64],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Forchestration-patterns.md","REFERENCE","参考文档",828,"https:\u002F\u002Fgithub.com\u002FRazaib-khan\u002FForgeWeave\u002Fblob\u002Fmain\u002Fsrc\u002Fforgeweave\u002Ftemplates\u002Fgemini\u002F.gemini\u002Fskills\u002Fworkflow-orchestrator\u002Freferences\u002Forchestration-patterns.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fexecute_pipeline.py","SCRIPT","脚本",2979,"https:\u002F\u002Fgithub.com\u002FRazaib-khan\u002FForgeWeave\u002Fblob\u002Fmain\u002Fsrc\u002Fforgeweave\u002Ftemplates\u002Fgemini\u002F.gemini\u002Fskills\u002Fworkflow-orchestrator\u002Fscripts\u002Fexecute_pipeline.py",[71,76,83,90,97,104],{"skillNo":72,"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":73,"categories":74,"keywords":75,"publishedAt":19},"01M75MEJ4J1S2ZERWSM5ZBKRTE","https:\u002F\u002Fgithub.com\u002FRazaib-khan\u002FForgeWeave\u002Fblob\u002Fmain\u002Fsrc\u002Fforgeweave\u002Ftemplates\u002Fqwen\u002F.qwen\u002Fskills\u002Fworkflow-orchestrator\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M75MEEZQ0V89BABKZF5XQ3MW","Web Research","Browser-driven or scraping-based skill for real-time internet extraction using Playwright and HTTP-based fetching","https:\u002F\u002Fgithub.com\u002FRazaib-khan\u002FForgeWeave\u002Fblob\u002Fmain\u002Fsrc\u002Fforgeweave\u002Ftemplates\u002Fqwen\u002F.qwen\u002Fskills\u002Fweb-research\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M75MECJV3NEN6GY89ZT7NWFA","Validation Engine","Checks outputs from other skills for consistency, correctness, and adherence to AGENTS.md rules","https:\u002F\u002Fgithub.com\u002FRazaib-khan\u002FForgeWeave\u002Fblob\u002Fmain\u002Fsrc\u002Fforgeweave\u002Ftemplates\u002Fqwen\u002F.qwen\u002Fskills\u002Fvalidation-engine\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M75MEAAXKRA9HJWWQH0MMBGY","Tool Selector","Determines which tools, APIs, MCP actions, or system capabilities are required for a given task","https:\u002F\u002Fgithub.com\u002FRazaib-khan\u002FForgeWeave\u002Fblob\u002Fmain\u002Fsrc\u002Fforgeweave\u002Ftemplates\u002Fqwen\u002F.qwen\u002Fskills\u002Ftool-selector\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":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M75ME7JAXQG26T1NEB3VNDM6","Test Generator","Creates test plans and test cases (unit, integration, edge cases) based on existing or planned code","https:\u002F\u002Fgithub.com\u002FRazaib-khan\u002FForgeWeave\u002Fblob\u002Fmain\u002Fsrc\u002Fforgeweave\u002Ftemplates\u002Fqwen\u002F.qwen\u002Fskills\u002Ftest-generator\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M75ME52949X3D8JQSYAWGDRB","Skill Generator","Meta-skill that creates new SKILL.md files from research outputs and patterns discovered in execution","https:\u002F\u002Fgithub.com\u002FRazaib-khan\u002FForgeWeave\u002Fblob\u002Fmain\u002Fsrc\u002Fforgeweave\u002Ftemplates\u002Fqwen\u002F.qwen\u002Fskills\u002Fskill-generator\u002FSKILL.md",[],[]]