[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EBVMAJ3KWFWZQ7N2K5JKVG":3,"skill-same:01M7EBVMAJ3KWFWZQ7N2K5JKVG":67},{"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},"01M7EBVMAJ3KWFWZQ7N2K5JKVG","automation-pipelines",null,"Build and debug ClearML automation workflows with PipelineController, PipelineDecorator, HPO, schedulers, triggers, and clearml-param-search.","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\u002F03-逆向工程\u002Fclearml\u002Fsub-skills\u002Fautomation-pipelines\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: automation-pipelines\ndescription: \"Build and debug ClearML automation workflows with\n  PipelineController, PipelineDecorator, HPO, schedulers, triggers, and\n  clearml-param-search.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# ClearML Automation Pipelines\n\nUse this sub-skill when an agent needs to create or troubleshoot ClearML automation workflows: pipeline DAGs, decorated function pipelines, hyperparameter search, recurring schedules, event triggers, and automation controller\u002Fservice tasks.\n\n## Read First\n\n- [API reference](references\u002Fapi-reference.md) lists the verified automation classes, important signatures, search-space classes, scheduler\u002Ftrigger calls, and decision notes.\n- [Workflow recipes](references\u002Fworkflows.md) shows function pipelines, task pipelines, local debugging, HPO, scheduler, and trigger patterns.\n- [HPO CLI reference](references\u002Fhpo-cli-reference.md) explains `clearml-param-search` flags and JSON payloads, plus offline validation with [hpo_search_space_check.py](scripts\u002Fhpo_search_space_check.py).\n- [Troubleshooting](references\u002Ftroubleshooting.md) covers parent references, parameter overrides, queues\u002Fagents, caching, objective metric matching, JSON errors, and recurring time validation.\n- [Pipeline skeleton generator](scripts\u002Fpipeline_skeleton.py) writes minimal `PipelineDecorator` or `PipelineController` starter files without contacting a ClearML server.\n\n## Route Boundaries\n\n- Use this sub-skill for `PipelineController`, `PipelineDecorator`, `HyperParameterOptimizer`, `TaskScheduler`, `TriggerScheduler`, and the `clearml-param-search` CLI.\n- For logging inside step code with `Task.init`, `Logger.report_scalar`, text, images, tables, or artifacts, route to `..\u002Fexperiment-tracking\u002FSKILL.md`.\n- For `Dataset`, `StorageManager`, dataset lineage, or object storage assets passed through pipelines, route to `..\u002Fdata-storage\u002FSKILL.md`.\n- For direct `clearml-task` packaging, enqueueing, or command-line task launches outside HPO\u002Fpipeline orchestration, route to `..\u002Fremote-execution-cli\u002FSKILL.md`.\n- For HTTP routers, `Task.get_http_router()`, web services, or endpoint deployment, route to `..\u002Frouters-services\u002FSKILL.md`.\n\n## Automation Decision Path\n\n1. Choose `PipelineDecorator` when the user has ordinary Python functions and wants pipeline steps created from function calls.\n2. Choose `PipelineController.add_function_step()` when the user wants explicit DAG nodes from Python functions, named return artifacts, parameter references, callbacks, retries, or queue overrides.\n3. Choose `PipelineController.add_step()` when the user already has ClearML Tasks to clone and connect into a DAG.\n4. Choose `HyperParameterOptimizer` or `clearml-param-search` when the user has a base task\u002Fscript and wants to clone it across parameter ranges using an objective scalar.\n5. Choose `TaskScheduler` for recurring cron-like launches and `TriggerScheduler` for model, dataset, or task events.\n\n## Safety And Execution Notes\n\n- Draft pipeline\u002FHPO\u002Fscheduler code without running it unless the user explicitly has a configured ClearML server, credentials, queues, and safe execution target.\n- Prefer local debugging paths first: `PipelineDecorator.debug_pipeline()`, `PipelineDecorator.run_locally()`, `PipelineController.start_locally()`, or HPO `--local` where appropriate.\n- Treat remote queue names as deployment choices: pipeline controller defaults to a `services` queue, while step execution and HPO jobs usually need worker queues.\n- Keep pipeline step imports inside the step function when they are required remotely; ClearML can infer per-step packages from imports used in function steps.\n","# ClearML Automation Pipelines\n\nUse this sub-skill when an agent needs to create or troubleshoot ClearML automation workflows: pipeline DAGs, decorated function pipelines, hyperparameter search, recurring schedules, event triggers, and automation controller\u002Fservice tasks.\n\n## Read First\n\n- [API reference](references\u002Fapi-reference.md) lists the verified automation classes, important signatures, search-space classes, scheduler\u002Ftrigger calls, and decision notes.\n- [Workflow recipes](references\u002Fworkflows.md) shows function pipelines, task pipelines, local debugging, HPO, scheduler, and trigger patterns.\n- [HPO CLI reference](references\u002Fhpo-cli-reference.md) explains `clearml-param-search` flags and JSON payloads, plus offline validation with [hpo_search_space_check.py](scripts\u002Fhpo_search_space_check.py).\n- [Troubleshooting](references\u002Ftroubleshooting.md) covers parent references, parameter overrides, queues\u002Fagents, caching, objective metric matching, JSON errors, and recurring time validation.\n- [Pipeline skeleton generator](scripts\u002Fpipeline_skeleton.py) writes minimal `PipelineDecorator` or `PipelineController` starter files without contacting a ClearML server.\n\n## Route Boundaries\n\n- Use this sub-skill for `PipelineController`, `PipelineDecorator`, `HyperParameterOptimizer`, `TaskScheduler`, `TriggerScheduler`, and the `clearml-param-search` CLI.\n- For logging inside step code with `Task.init`, `Logger.report_scalar`, text, images, tables, or artifacts, route to `..\u002Fexperiment-tracking\u002FSKILL.md`.\n- For `Dataset`, `StorageManager`, dataset lineage, or object storage assets passed through pipelines, route to `..\u002Fdata-storage\u002FSKILL.md`.\n- For direct `clearml-task` packaging, enqueueing, or command-line task launches outside HPO\u002Fpipeline orchestration, route to `..\u002Fremote-execution-cli\u002FSKILL.md`.\n- For HTTP routers, `Task.get_http_router()`, web services, or endpoint deployment, route to `..\u002Frouters-services\u002FSKILL.md`.\n\n## Automation Decision Path\n\n1. Choose `PipelineDecorator` when the user has ordinary Python functions and wants pipeline steps created from function calls.\n2. Choose `PipelineController.add_function_step()` when the user wants explicit DAG nodes from Python functions, named return artifacts, parameter references, callbacks, retries, or queue overrides.\n3. Choose `PipelineController.add_step()` when the user already has ClearML Tasks to clone and connect into a DAG.\n4. Choose `HyperParameterOptimizer` or `clearml-param-search` when the user has a base task\u002Fscript and wants to clone it across parameter ranges using an objective scalar.\n5. Choose `TaskScheduler` for recurring cron-like launches and `TriggerScheduler` for model, dataset, or task events.\n\n## Safety And Execution Notes\n\n- Draft pipeline\u002FHPO\u002Fscheduler code without running it unless the user explicitly has a configured ClearML server, credentials, queues, and safe execution target.\n- Prefer local debugging paths first: `PipelineDecorator.debug_pipeline()`, `PipelineDecorator.run_locally()`, `PipelineController.start_locally()`, or HPO `--local` where appropriate.\n- Treat remote queue names as deployment choices: pipeline controller defaults to a `services` queue, while step execution and HPO jobs usually need worker queues.\n- Keep pipeline step imports inside the step function when they are required remotely; ClearML can infer per-step packages from imports used in function steps.\n",{"name":5,"license":24,"metadata":25,"description":7,"disable-model-invocation":27},"Apache 2.0",{"disco-role":26},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","03-逆向工程\u002Fclearml\u002Fsub-skills\u002Fautomation-pipelines",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 automation-pipelines",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill automation-pipelines",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill automation-pipelines","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fclearml\u002Fsub-skills\u002Fautomation-pipelines\u002FSKILL.md",[49,55,59,63],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fapi-reference.md","REFERENCE","参考文档",18415,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fclearml\u002Fsub-skills\u002Fautomation-pipelines\u002Freferences\u002Fapi-reference.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fhpo-cli-reference.md",6592,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fclearml\u002Fsub-skills\u002Fautomation-pipelines\u002Freferences\u002Fhpo-cli-reference.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Ftroubleshooting.md",9741,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fclearml\u002Fsub-skills\u002Fautomation-pipelines\u002Freferences\u002Ftroubleshooting.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fworkflows.md",13290,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fclearml\u002Fsub-skills\u002Fautomation-pipelines\u002Freferences\u002Fworkflows.md",[68,77,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":76},"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",[],[],"2026-11-16 10:05:34",{"skillNo":78,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":76},"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":76},"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":76},"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":76},"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":76},"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",[],[]]