[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GW7ABM2F529N0JEEP6WRMH":3,"skill-same:01M6GW7ABM2F529N0JEEP6WRMH":62},{"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":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":37,"install":38,"resources":51},"01M6GW7ABM2F529N0JEEP6WRMH","new-arnold-pipeline-template",null,"Scaffold a new Arnold native-first pipeline package from the _template skeleton.","peteromallet\u002FArnold","peteromallet","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4647941?v=4","01M6GW770S4CG20MPXS5PZWNF8","POM","01M6GW774TYWCS83WGXD72E15V",98,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Farnold_pipelines\u002F_template\u002FSKILL.md",[],[19,20,21,22,23,24,25],"pipeline","template","new arnold pipeline template","scaffold","package","first","native","2026-11-10 10:12:30",false,"---\nname: new-arnold-pipeline-template\ndescription: Scaffold a new Arnold native-first pipeline package from the _template skeleton.\n---\n\n# New Arnold Pipeline Template\n\nCopy `arnold_pipelines\u002F_template\u002F` to a new package under `arnold_pipelines\u002F`,\nrename it (remove the leading underscore), and replace the skeleton native\ndeclarations with real pipeline logic.\n\nThis template is **native-first**. Every package built from it uses\n`@pipeline`, `@phase`, `@decision`, `parallel`, `compile_pipeline`, and\n`project_graph` to declare a native program and project it into a\n`Pipeline` shell that the runtime executes directly.\n\n## Contract\n\n- `build_pipeline() -> arnold.pipeline.Pipeline` returning a projected\n  shell with a **non-null** `native_program`.\n- Module-level metadata: `name`, `description`, `driver`, `entrypoint`,\n  `arnold_api_version`, `capabilities`.\n- `driver` must be `(\"native\", \"\u003Ckind>\")` (e.g. `(\"native\", \"project+validate\")`).\n- `supported_modes` must include `\"native\"` (e.g. `(\"native\",)`).\n- Optional: `default_profile`, `recommended_profiles`.\n\nNew packages must be native-first. Do **not** add `_legacy.py`, graph\nfallback builders, compatibility namespaces, shim packages, or temporary\nwrapper modules for new work — those patterns are explicitly disallowed.\n\n## Dispatch Substrate, Not Final Composition\n\nThe `native_program` attached to the projected `Pipeline` is a **dispatch\nsubstrate**. It describes how the runtime lowers and executes pipeline\ntopology, but it does **not** define the final visible compositional\nsemantics (panel synthesis, join delegation, parallel merge strategy,\nsubpipeline ownership, or Capsule projection). Those compositional\nconcerns are deferred to later Megaplan layers above the dispatch\nboundary.\n\nPackage authors should treat `native_program` as the execution-level\ncontract: a non-null program proves the package is native-runnable, but\nthe exact shape of how composition is rendered for end users, agents, or\nCapsules is not finalised at this layer.\n\n## Example\n\n```python\nfrom arnold.pipeline import Pipeline, StepResult, compile_pipeline, phase, pipeline, project_graph\n\n\n@phase(name=\"draft\")\ndef draft(ctx: object) -> StepResult:\n    return StepResult(outputs={\"draft\": \"TODO\"}, next=\"publish\")\n\n\n@phase(name=\"publish\")\ndef publish(ctx: object) -> StepResult:\n    return StepResult(outputs={\"final_artifact\": \"TODO\"}, next=\"halt\")\n\n\n@pipeline(name=\"my-pipeline\", description=\"draft → publish\")\ndef my_pipeline_native(ctx: object) -> Any:\n    state = yield draft(ctx)\n    state = yield publish(ctx)\n    return state\n\n\ndef build_pipeline() -> Pipeline:\n    native = compile_pipeline(my_pipeline_native)\n    return project_graph(native, key_mode=\"phase\")\n```\n\nThe returned `Pipeline` carries a non-null `native_program`. The runtime\nuses that program directly; the projected shell is for discovery and\nvalidation, not for hand-authored graph construction.\n\n## Validation\n\n- Validate import: `arnold_pipelines.my_pipeline:build_pipeline`\n- Contract: `build_pipeline()` returns `arnold.pipeline.Pipeline`\n  with a non-null `native_program`.\n- Metadata: `driver` starts with `\"native\"`; `supported_modes` contains\n  `\"native\"`.\n\nRun through the Arnold native checker:\n\n```bash\narnold pipelines check --module arnold_pipelines.my_pipeline:build_pipeline\n```\n","# New Arnold Pipeline Template\n\nCopy `arnold_pipelines\u002F_template\u002F` to a new package under `arnold_pipelines\u002F`,\nrename it (remove the leading underscore), and replace the skeleton native\ndeclarations with real pipeline logic.\n\nThis template is **native-first**. Every package built from it uses\n`@pipeline`, `@phase`, `@decision`, `parallel`, `compile_pipeline`, and\n`project_graph` to declare a native program and project it into a\n`Pipeline` shell that the runtime executes directly.\n\n## Contract\n\n- `build_pipeline() -> arnold.pipeline.Pipeline` returning a projected\n  shell with a **non-null** `native_program`.\n- Module-level metadata: `name`, `description`, `driver`, `entrypoint`,\n  `arnold_api_version`, `capabilities`.\n- `driver` must be `(\"native\", \"\u003Ckind>\")` (e.g. `(\"native\", \"project+validate\")`).\n- `supported_modes` must include `\"native\"` (e.g. `(\"native\",)`).\n- Optional: `default_profile`, `recommended_profiles`.\n\nNew packages must be native-first. Do **not** add `_legacy.py`, graph\nfallback builders, compatibility namespaces, shim packages, or temporary\nwrapper modules for new work — those patterns are explicitly disallowed.\n\n## Dispatch Substrate, Not Final Composition\n\nThe `native_program` attached to the projected `Pipeline` is a **dispatch\nsubstrate**. It describes how the runtime lowers and executes pipeline\ntopology, but it does **not** define the final visible compositional\nsemantics (panel synthesis, join delegation, parallel merge strategy,\nsubpipeline ownership, or Capsule projection). Those compositional\nconcerns are deferred to later Megaplan layers above the dispatch\nboundary.\n\nPackage authors should treat `native_program` as the execution-level\ncontract: a non-null program proves the package is native-runnable, but\nthe exact shape of how composition is rendered for end users, agents, or\nCapsules is not finalised at this layer.\n\n## Example\n\n```python\nfrom arnold.pipeline import Pipeline, StepResult, compile_pipeline, phase, pipeline, project_graph\n\n\n@phase(name=\"draft\")\ndef draft(ctx: object) -> StepResult:\n    return StepResult(outputs={\"draft\": \"TODO\"}, next=\"publish\")\n\n\n@phase(name=\"publish\")\ndef publish(ctx: object) -> StepResult:\n    return StepResult(outputs={\"final_artifact\": \"TODO\"}, next=\"halt\")\n\n\n@pipeline(name=\"my-pipeline\", description=\"draft → publish\")\ndef my_pipeline_native(ctx: object) -> Any:\n    state = yield draft(ctx)\n    state = yield publish(ctx)\n    return state\n\n\ndef build_pipeline() -> Pipeline:\n    native = compile_pipeline(my_pipeline_native)\n    return project_graph(native, key_mode=\"phase\")\n```\n\nThe returned `Pipeline` carries a non-null `native_program`. The runtime\nuses that program directly; the projected shell is for discovery and\nvalidation, not for hand-authored graph construction.\n\n## Validation\n\n- Validate import: `arnold_pipelines.my_pipeline:build_pipeline`\n- Contract: `build_pipeline()` returns `arnold.pipeline.Pipeline`\n  with a non-null `native_program`.\n- Metadata: `driver` starts with `\"native\"`; `supported_modes` contains\n  `\"native\"`.\n\nRun through the Arnold native checker:\n\n```bash\narnold pipelines check --module arnold_pipelines.my_pipeline:build_pipeline\n```\n",{"name":5,"description":7},"main","4815916805531030f062fc1c10bcc9f9cd10a40f","arnold_pipelines\u002F_template",7,"https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold","https:\u002F\u002Fgithub.com\u002Fpeteromallet","2026-10-27 21:10:27",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add peteromallet\u002FArnold --skill new-arnold-pipeline-template",{"tool":44,"command":45},"bunx","bunx skills add peteromallet\u002FArnold --skill new-arnold-pipeline-template",{"tool":47,"command":48},"pnpm","pnpm dlx skills add peteromallet\u002FArnold --skill new-arnold-pipeline-template","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Farnold_pipelines\u002F_template\u002FSKILL.md",true,[52,58],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"__init__.py","SCRIPT","脚本",3085,"https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Farnold_pipelines\u002F_template\u002F__init__.py",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"pipelines.py",5919,"https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Farnold_pipelines\u002F_template\u002Fpipelines.py",[63,72,78,84,90,106],{"skillNo":64,"name":65,"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":66,"categories":67,"keywords":68,"publishedAt":26},"01M6GWC4WCKXPTH05M6D84CPC6","live_supervisor","https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Fexamples\u002Fworkflow_authoring\u002Fshipped\u002Flive_supervisor\u002FSKILL.md",[],[69,70,71],"live supervisor","live","supervisor",{"skillNo":73,"name":74,"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":75,"categories":76,"keywords":77,"publishedAt":26},"01M6GWC25QW59XZMZF5A8QB1R2","jokes","https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Fexamples\u002Fworkflow_authoring\u002Fshipped\u002Fjokes\u002FSKILL.md",[],[74],{"skillNo":79,"name":80,"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":81,"categories":82,"keywords":83,"publishedAt":26},"01M6GWBZ01NNK2NMGC4GSNK5EN","creative","https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Fexamples\u002Fworkflow_authoring\u002Fshipped\u002Fcreative\u002FSKILL.md",[],[80],{"skillNo":85,"name":86,"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":87,"categories":88,"keywords":89,"publishedAt":26},"01M6GWBX6DPACH6GV2MD07Z1Q9","hello","https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Fexamples\u002Fworkflow_authoring\u002Fhello\u002FSKILL.md",[],[86],{"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":26},"01M6GWBRWZSK3C7459P1H2X2HZ","vibecomfy-executor","Arnold pipeline that classifies a user query, optionally researches via Hivemind\u002FBanodoco, optionally edits a ComfyUI workflow, and always emits a final reply.","https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Fdocs\u002Farchive\u002Fm5\u002Fpipelines\u002Fvibecomfy_executor\u002FSKILL.md",[],[97,98,99,100,101,102,103,104,19,105],"vibecomfy executor","executor","comfyui","via","query","reply","hivemind","user","workflow",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":122,"publishedAt":26},"01M6GWBPM62R2V1X5P81WWX1C3","simplify-writing","Fan out DeepSeek Pro critics and a Kimi editor to iteratively simplify a piece of writing.","https:\u002F\u002Fgithub.com\u002Fpeteromallet\u002FArnold\u002Fblob\u002Fmain\u002Fdocs\u002Farchive\u002Fm5\u002Fpipelines\u002Fsimplify_writing\u002Fskills\u002Fsimplify-writing\u002FSKILL.md",[112,117],{"categoryNo":113,"categoryName":114,"taxonomyType":115,"taxonomyTypeDesc":116},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":118,"categoryName":119,"taxonomyType":120,"taxonomyTypeDesc":121},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[123,124,125,126,127,128,129],"simplify","simplify writing","writing","pro","deepseek","kimi","editor"]