[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EBVH9A0AS32XXWWZN2C5XZ":3,"skill-same:01M7EBVH9A0AS32XXWWZN2C5XZ":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},"01M7EBVH9A0AS32XXWWZN2C5XZ","clearml",null,"Route ClearML Python SDK tasks across experiment tracking, data\u002Fversioned storage, remote execution CLIs, automation pipelines, HPO, schedulers, routers, and services.","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\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: clearml\ndescription: \"Route ClearML Python SDK tasks across experiment tracking,\n  data\u002Fversioned storage, remote execution CLIs, automation pipelines, HPO,\n  schedulers, routers, and services.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# ClearML Repo Skill\n\nUse this skill when a user asks how to use, configure, script, or troubleshoot the ClearML Python SDK. ClearML is an experiment tracking, data management, remote execution, automation, and MLOps SDK exposed through Python APIs and command-line tools.\n\nThis root skill is a router. Read the focused sub-skill that matches the user's workflow, then use the linked references and scripts inside that sub-skill.\n\n## Fast Routing\n\n| User task | Read |\n| --- | --- |\n| Add ClearML to a training or evaluation script; log metrics, plots, artifacts, configs, models, or offline sessions | `sub-skills\u002Fexperiment-tracking\u002FSKILL.md` |\n| Create, sync, version, retrieve, or troubleshoot datasets, storage URIs, `clearml-data`, `Dataset`, `StorageManager`, or HyperDataset\u002FDataView | `sub-skills\u002Fdata-storage\u002FSKILL.md` |\n| Configure ClearML, build `clearml-task` commands, launch code on agents, clone\u002Fenqueue tasks, import offline sessions, or debug queues | `sub-skills\u002Fremote-execution-cli\u002FSKILL.md` |\n| Build pipelines, HPO jobs, schedulers, triggers, controller tasks, or validate `clearml-param-search` JSON | `sub-skills\u002Fautomation-pipelines\u002FSKILL.md` |\n| Use HTTP routers, local proxies, endpoint telemetry, service tasks, or optional `clearml[router]` dependencies | `sub-skills\u002Frouters-services\u002FSKILL.md` |\n\n## Package Entry Points\n\nClearML exposes these common imports:\n\n```python\nfrom clearml import Task, TaskTypes, Logger, Dataset, StorageManager\nfrom clearml import InputModel, OutputModel, Model\nfrom clearml import PipelineController, PipelineDecorator\nfrom clearml.automation import HyperParameterOptimizer, TaskScheduler, TriggerScheduler\n```\n\nThe package installs these user-facing CLIs:\n\n- `clearml-init` for writing a local ClearML configuration file.\n- `clearml-debug` for diagnostic configuration and token checks.\n- `clearml-task` for creating or launching remote tasks on `clearml-agent` queues.\n- `clearml-data` for dataset creation, sync, upload, finalize, verify, list, and retrieval.\n- `clearml-param-search` for command-line hyperparameter search over a task or script.\n\n## Installation And Optional Extras\n\nUse the base package for tracking, datasets, CLIs, storage manager basics, and automation APIs:\n\n```bash\npip install clearml\n```\n\nInstall optional extras only for the workflow that needs them:\n\n- `clearml[s3]` for S3 object storage integration.\n- `clearml[gs]` for Google Cloud Storage integration.\n- `clearml[azure]` for Azure Blob Storage integration.\n- `clearml[router]` for HTTP router\u002Fproxy support through FastAPI, Uvicorn, and HTTPX.\n\nUse `scripts\u002Fclearml_environment_check.py` for a read-only import, CLI, optional-extra, and credential-signal check. The script reports only whether secrets\u002Fconfiguration signals are present; it must not print secret values.\n\n## Configuration And Credentials\n\nMost live ClearML workflows need:\n\n- A reachable ClearML server or hosted workspace.\n- Credentials from `clearml-init`, a ClearML configuration file, or environment variables such as `CLEARML_API_HOST`, `CLEARML_API_ACCESS_KEY`, and `CLEARML_API_SECRET_KEY`.\n- A `clearml-agent` polling the selected queue for remote execution, pipeline steps, HPO jobs, services, and schedulers.\n- Storage credentials or configured provider defaults when using S3, Google Cloud Storage, Azure, or shared filesystem destinations.\n\nFor code that must run without credentials or network access, use the experiment-tracking sub-skill's offline mode pattern and later import the offline session when a server is available.\n\n## Safety Defaults For Agents\n\n- Prefer generating code, command plans, validation output, and checklists before running live ClearML operations.\n- Do not run commands that create tasks, upload data, enqueue jobs, deploy routers, or start services unless the user explicitly wants side effects against a ClearML server.\n- Do not echo API keys, secret keys, tokens, or credential file contents.\n- Treat examples that require external datasets, queues, GPU frameworks, cloud credentials, or a running ClearML server as evidence, not as safe smoke tests.\n- Use bundled scripts in this skill tree rather than relying on the original repository checkout.\n\n## Root References\n\n- `references\u002Fpackage-overview.md` summarizes ClearML imports, CLIs, optional extras, configuration, and workflow selection.\n- `references\u002Ftroubleshooting.md` covers cross-cutting install\u002Fimport, credentials, server, queue, storage, optional extras, and privacy failures.\n- `references\u002Frepo-provenance.md` records the source snapshot and evidence paths used to create this skill.\n- `references\u002Frepo-routing-metadata.json` is structured metadata consumed by the managed repo-skills-router import process.\n","# ClearML Repo Skill\n\nUse this skill when a user asks how to use, configure, script, or troubleshoot the ClearML Python SDK. ClearML is an experiment tracking, data management, remote execution, automation, and MLOps SDK exposed through Python APIs and command-line tools.\n\nThis root skill is a router. Read the focused sub-skill that matches the user's workflow, then use the linked references and scripts inside that sub-skill.\n\n## Fast Routing\n\n| User task | Read |\n| --- | --- |\n| Add ClearML to a training or evaluation script; log metrics, plots, artifacts, configs, models, or offline sessions | `sub-skills\u002Fexperiment-tracking\u002FSKILL.md` |\n| Create, sync, version, retrieve, or troubleshoot datasets, storage URIs, `clearml-data`, `Dataset`, `StorageManager`, or HyperDataset\u002FDataView | `sub-skills\u002Fdata-storage\u002FSKILL.md` |\n| Configure ClearML, build `clearml-task` commands, launch code on agents, clone\u002Fenqueue tasks, import offline sessions, or debug queues | `sub-skills\u002Fremote-execution-cli\u002FSKILL.md` |\n| Build pipelines, HPO jobs, schedulers, triggers, controller tasks, or validate `clearml-param-search` JSON | `sub-skills\u002Fautomation-pipelines\u002FSKILL.md` |\n| Use HTTP routers, local proxies, endpoint telemetry, service tasks, or optional `clearml[router]` dependencies | `sub-skills\u002Frouters-services\u002FSKILL.md` |\n\n## Package Entry Points\n\nClearML exposes these common imports:\n\n```python\nfrom clearml import Task, TaskTypes, Logger, Dataset, StorageManager\nfrom clearml import InputModel, OutputModel, Model\nfrom clearml import PipelineController, PipelineDecorator\nfrom clearml.automation import HyperParameterOptimizer, TaskScheduler, TriggerScheduler\n```\n\nThe package installs these user-facing CLIs:\n\n- `clearml-init` for writing a local ClearML configuration file.\n- `clearml-debug` for diagnostic configuration and token checks.\n- `clearml-task` for creating or launching remote tasks on `clearml-agent` queues.\n- `clearml-data` for dataset creation, sync, upload, finalize, verify, list, and retrieval.\n- `clearml-param-search` for command-line hyperparameter search over a task or script.\n\n## Installation And Optional Extras\n\nUse the base package for tracking, datasets, CLIs, storage manager basics, and automation APIs:\n\n```bash\npip install clearml\n```\n\nInstall optional extras only for the workflow that needs them:\n\n- `clearml[s3]` for S3 object storage integration.\n- `clearml[gs]` for Google Cloud Storage integration.\n- `clearml[azure]` for Azure Blob Storage integration.\n- `clearml[router]` for HTTP router\u002Fproxy support through FastAPI, Uvicorn, and HTTPX.\n\nUse `scripts\u002Fclearml_environment_check.py` for a read-only import, CLI, optional-extra, and credential-signal check. The script reports only whether secrets\u002Fconfiguration signals are present; it must not print secret values.\n\n## Configuration And Credentials\n\nMost live ClearML workflows need:\n\n- A reachable ClearML server or hosted workspace.\n- Credentials from `clearml-init`, a ClearML configuration file, or environment variables such as `CLEARML_API_HOST`, `CLEARML_API_ACCESS_KEY`, and `CLEARML_API_SECRET_KEY`.\n- A `clearml-agent` polling the selected queue for remote execution, pipeline steps, HPO jobs, services, and schedulers.\n- Storage credentials or configured provider defaults when using S3, Google Cloud Storage, Azure, or shared filesystem destinations.\n\nFor code that must run without credentials or network access, use the experiment-tracking sub-skill's offline mode pattern and later import the offline session when a server is available.\n\n## Safety Defaults For Agents\n\n- Prefer generating code, command plans, validation output, and checklists before running live ClearML operations.\n- Do not run commands that create tasks, upload data, enqueue jobs, deploy routers, or start services unless the user explicitly wants side effects against a ClearML server.\n- Do not echo API keys, secret keys, tokens, or credential file contents.\n- Treat examples that require external datasets, queues, GPU frameworks, cloud credentials, or a running ClearML server as evidence, not as safe smoke tests.\n- Use bundled scripts in this skill tree rather than relying on the original repository checkout.\n\n## Root References\n\n- `references\u002Fpackage-overview.md` summarizes ClearML imports, CLIs, optional extras, configuration, and workflow selection.\n- `references\u002Ftroubleshooting.md` covers cross-cutting install\u002Fimport, credentials, server, queue, storage, optional extras, and privacy failures.\n- `references\u002Frepo-provenance.md` records the source snapshot and evidence paths used to create this skill.\n- `references\u002Frepo-routing-metadata.json` is structured metadata consumed by the managed repo-skills-router import process.\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",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 clearml",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill clearml",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill clearml","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\u002FSKILL.md",[49,55,59,63],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fpackage-overview.md","REFERENCE","参考文档",3668,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fclearml\u002Freferences\u002Fpackage-overview.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Frepo-provenance.md",1486,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fclearml\u002Freferences\u002Frepo-provenance.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Frepo-routing-metadata.json",457,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fclearml\u002Freferences\u002Frepo-routing-metadata.json",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Ftroubleshooting.md",3758,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fclearml\u002Freferences\u002Ftroubleshooting.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",[],[]]