[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F6B2QGHMMVE16VGKWJFCJS":3,"skill-same:01M7F6B2QGHMMVE16VGKWJFCJS":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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7F6B2QGHMMVE16VGKWJFCJS","pipelines",null,"Routes UltraRAG pipeline build, run, and recipe workflows, including YAML orchestration and the Python API wrappers.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fultra-rag\u002Fsub-skills\u002Fpipelines\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: pipelines\ndescription: \"Routes UltraRAG pipeline build, run, and recipe workflows,\n  including YAML orchestration and the Python API wrappers.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Pipelines\n\nUse this sub-skill when the task is about running, building, or authoring an\nUltraRAG pipeline.\n\n## Typical triggers\n\n- `ultrarag build`, `ultrarag run`, or `ultrarag show`\n- `ToolCall` \u002F `PipelineCall` usage from Python\n- `pipeline.yaml`, `servers:`, `pipeline:`, `loop:`, `branch:`\n- Demo or experiment files under `examples\u002Fdemos\u002F` or `examples\u002Fexperiments\u002F`\n- Questions about how a pipeline step consumes or produces variables\n- Requests to reproduce or adapt a named example such as `RAG`, `LLM`,\n  `LightResearch`, `AgentCPM-Report`, `webnote`, `search_o1`, `search_r1`,\n  `rankcot`, `ircot`, `visrag`, or `sayhello`\n\n## What this sub-skill covers\n\n- CLI build\u002Frun\u002Fshow entry points.\n- `ToolCall` and `PipelineCall` from the Python API.\n- Pipeline structure, variable resolution, step remapping, branch\u002Floop logic,\n  and generated `parameter\u002F` and `server\u002F` artifacts.\n- Example workflows that combine benchmark data, retriever, generation, prompt,\n  custom, memory, router, evaluation, and corpus steps.\n- Safe smoke checks that prove the orchestration layer still works.\n\n## What stays elsewhere\n\n- Individual MCP server signatures and backend-specific configuration belong in\n  `sub-skills\u002Fservers\u002F`.\n- Flask UI, chat sessions, knowledge-base storage, and case study belong in\n  `sub-skills\u002Fui-and-storage\u002F`.\n\n## Start here\n\n- Read `references\u002Fpipeline-dsl.md` for the verified YAML syntax, data-flow\n  rules, and build\u002Frun behavior.\n- Read `references\u002Fworkflows.md` for a map of example families and the best\n  starting point for each one.\n- Read `references\u002Ftroubleshooting.md` when a pipeline build, parameter merge,\n  or execution step fails.\n- Run `scripts\u002Fsmoke_sayhello_pipeline.py` for a minimal end-to-end smoke check.\n\n## Common user questions this sub-skill should answer\n\n- How do I build a pipeline from YAML?\n- How do I run a pipeline with a custom parameter file?\n- How do I express a loop or branch?\n- Why did a step remap or variable lookup fail?\n- Which example pipeline is closest to my task?\n- How do I get a small smoke test working before a larger RAG workflow?\n\n## Practical workflow\n\n1. Identify the example family that matches the request.\n2. Check whether the task is only orchestration, or whether it also needs a\n   specific server backend or UI route.\n3. Use the DSL reference to confirm the step shape and variable names.\n4. Use the smoke script or a minimal example to validate the plan.\n\n## Helpful commands\n\nUse the bundled smoke helper instead of relying on a source example file:\n\n```bash\npython sub-skills\u002Fpipelines\u002Fscripts\u002Fsmoke_sayhello_pipeline.py --repo-root \u003Ccheckout>\nultrarag show ui\nultrarag show case --config_path \u003Cmemory-case.json>\n```\n\nIf the task is about a named experiment or demo, use the distilled family map in\n`references\u002Fworkflows.md` before guessing the pipeline structure.\n","# Pipelines\n\nUse this sub-skill when the task is about running, building, or authoring an\nUltraRAG pipeline.\n\n## Typical triggers\n\n- `ultrarag build`, `ultrarag run`, or `ultrarag show`\n- `ToolCall` \u002F `PipelineCall` usage from Python\n- `pipeline.yaml`, `servers:`, `pipeline:`, `loop:`, `branch:`\n- Demo or experiment files under `examples\u002Fdemos\u002F` or `examples\u002Fexperiments\u002F`\n- Questions about how a pipeline step consumes or produces variables\n- Requests to reproduce or adapt a named example such as `RAG`, `LLM`,\n  `LightResearch`, `AgentCPM-Report`, `webnote`, `search_o1`, `search_r1`,\n  `rankcot`, `ircot`, `visrag`, or `sayhello`\n\n## What this sub-skill covers\n\n- CLI build\u002Frun\u002Fshow entry points.\n- `ToolCall` and `PipelineCall` from the Python API.\n- Pipeline structure, variable resolution, step remapping, branch\u002Floop logic,\n  and generated `parameter\u002F` and `server\u002F` artifacts.\n- Example workflows that combine benchmark data, retriever, generation, prompt,\n  custom, memory, router, evaluation, and corpus steps.\n- Safe smoke checks that prove the orchestration layer still works.\n\n## What stays elsewhere\n\n- Individual MCP server signatures and backend-specific configuration belong in\n  `sub-skills\u002Fservers\u002F`.\n- Flask UI, chat sessions, knowledge-base storage, and case study belong in\n  `sub-skills\u002Fui-and-storage\u002F`.\n\n## Start here\n\n- Read `references\u002Fpipeline-dsl.md` for the verified YAML syntax, data-flow\n  rules, and build\u002Frun behavior.\n- Read `references\u002Fworkflows.md` for a map of example families and the best\n  starting point for each one.\n- Read `references\u002Ftroubleshooting.md` when a pipeline build, parameter merge,\n  or execution step fails.\n- Run `scripts\u002Fsmoke_sayhello_pipeline.py` for a minimal end-to-end smoke check.\n\n## Common user questions this sub-skill should answer\n\n- How do I build a pipeline from YAML?\n- How do I run a pipeline with a custom parameter file?\n- How do I express a loop or branch?\n- Why did a step remap or variable lookup fail?\n- Which example pipeline is closest to my task?\n- How do I get a small smoke test working before a larger RAG workflow?\n\n## Practical workflow\n\n1. Identify the example family that matches the request.\n2. Check whether the task is only orchestration, or whether it also needs a\n   specific server backend or UI route.\n3. Use the DSL reference to confirm the step shape and variable names.\n4. Use the smoke script or a minimal example to validate the plan.\n\n## Helpful commands\n\nUse the bundled smoke helper instead of relying on a source example file:\n\n```bash\npython sub-skills\u002Fpipelines\u002Fscripts\u002Fsmoke_sayhello_pipeline.py --repo-root \u003Ccheckout>\nultrarag show ui\nultrarag show case --config_path \u003Cmemory-case.json>\n```\n\nIf the task is about a named experiment or demo, use the distilled family map in\n`references\u002Fworkflows.md` before guessing the pipeline structure.\n",{"name":5,"license":24,"metadata":25,"description":7,"disable-model-invocation":27},"Apache 2.0",{"disco-role":26},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fultra-rag\u002Fsub-skills\u002Fpipelines",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":27},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill pipelines",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill pipelines",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill pipelines","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fultra-rag\u002Fsub-skills\u002Fpipelines\u002FSKILL.md",[49,55,59],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fpipeline-dsl.md","REFERENCE","参考文档",2890,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fultra-rag\u002Fsub-skills\u002Fpipelines\u002Freferences\u002Fpipeline-dsl.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Ftroubleshooting.md",2576,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fultra-rag\u002Fsub-skills\u002Fpipelines\u002Freferences\u002Ftroubleshooting.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fworkflows.md",3442,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fultra-rag\u002Fsub-skills\u002Fpipelines\u002Freferences\u002Fworkflows.md",[64,72,77,84,91,98],{"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":68,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":73,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]