[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78VAYKS5PACWRR4PQFV64KC":3,"skill-same:01M78VAYKS5PACWRR4PQFV64KC":66},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M78VAYKS5PACWRR4PQFV64KC","sdk-automation",null,"Automate CVAT with the Python SDK, high-level repositories, authentication helpers, and safe task\u002Fproject data scripts.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcvat\u002Fsub-skills\u002Fsdk-automation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sdk-automation\ndescription: \"Automate CVAT with the Python SDK, high-level repositories,\n  authentication helpers, and safe task\u002Fproject data scripts.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# CVAT SDK automation\n\nUse this sub-skill when a task needs Python code against a CVAT server: login with a Personal Access Token or password, reuse CLI profiles, create\u002Flist\u002Fupdate\u002Fdelete tasks or projects, upload local\u002Fremote\u002Fshared data, import\u002Fexport annotations or datasets, download frames\u002Fpreviews\u002Fbackups, use organization context, or fall back to generated low-level REST API wrappers.\n\n## Route first\n\n- Read `references\u002Fapi-reference.md` for confirmed public classes, signatures, defaults, auth\u002Fprofile helpers, and repository\u002Fentity relationships.\n- Read `references\u002Fworkflows.md` for copyable SDK patterns for task\u002Fproject creation, frame download, import\u002Fexport, backups, profile-compatible scripts, and low-level API fallback.\n- Read `references\u002Ftroubleshooting.md` when imports, authentication, server compatibility, background requests, SSL, organization context, or cache\u002Ffilesystem behavior fail.\n- Run or adapt `scripts\u002Fsdk_task_smoke_template.py` for a safe import\u002Fsignature smoke by default, or for an explicit authenticated list\u002Fdownload workflow when the user supplies server credentials.\n\n## Use SDK instead of CLI when\n\n- The user needs branching logic, error handling, Python data structures, or integration into an ML pipeline.\n- A workflow needs `Client`, `Task`, `Project`, `Job`, `Organization`, `Issue`, or generated API model objects.\n- The task must compose CVAT calls with local data processing, model inference, or dataset conversion.\n- Repeated background operations should use `wait_for_completion()` rather than shell polling.\n\nUse `..\u002Fcli-automation\u002FSKILL.md` for terminal-only commands, `..\u002Fdataset-ops\u002FSKILL.md` for format and PyTorch dataset choices, `..\u002Fauto-annotation\u002FSKILL.md` for AA function protocols, and `..\u002Fdeployment-admin\u002FSKILL.md` for starting or administering a CVAT service.\n\n## Minimal install and import checks\n\n```bash\npip install cvat-sdk\npython - \u003C\u003C'PY'\nfrom cvat_sdk import make_client, Client, Config\nfrom cvat_sdk.core.proxies.tasks import ResourceType\nprint(Client, Config, [str(x) for x in ResourceType])\nPY\n```\n\nUse extras only when needed:\n\n```bash\npip install \"cvat-sdk[masks]\"     # mask encode\u002Fdecode helpers needing NumPy\npip install \"cvat-sdk[pytorch]\"   # PyTorch dataset adapter and built-in torchvision AA functions\n```\n\n## Safe authentication defaults\n\n- Prefer PAT authentication (`access_token=`) or CLI-compatible profiles rather than hard-coded passwords.\n- If using password auth, pass it as a secret runtime value, not in code committed to a repository.\n- Include the scheme in the server URL (`http:\u002F\u002F` or `https:\u002F\u002F`); SDK defaults and compatibility checks are stricter in recent releases.\n- Set `organization_slug` or use `organization_context(slug)` when the workflow must operate inside an organization workspace.\n- Treat `config.allow_unsupported_server=True` warnings seriously: SDK\u002Fserver minor versions should normally match or be adjacent.\n\n## Core pattern\n\n```python\nfrom cvat_sdk import make_client, models\nfrom cvat_sdk.core.proxies.tasks import ResourceType\n\nwith make_client(\"https:\u002F\u002Fcvat.example.com\", access_token=token) as client:\n    client.organization_slug = \"team-slug\"  # omit for personal workspace\n    task = client.tasks.create_from_data(\n        spec=models.TaskWriteRequest(\n            name=\"demo\",\n            labels=[{\"name\": \"car\", \"type\": \"rectangle\"}],\n        ),\n        resource_type=ResourceType.LOCAL,\n        resources=[\"image1.jpg\", \"image2.jpg\"],\n    )\n    print(task.id, task.size)\n```\n\nKeep scripts explicit about side effects: creating tasks\u002Fprojects, importing annotations, deleting resources, and downloading frames all mutate or read server state and need user-approved credentials\u002Fserver targets.\n","# CVAT SDK automation\n\nUse this sub-skill when a task needs Python code against a CVAT server: login with a Personal Access Token or password, reuse CLI profiles, create\u002Flist\u002Fupdate\u002Fdelete tasks or projects, upload local\u002Fremote\u002Fshared data, import\u002Fexport annotations or datasets, download frames\u002Fpreviews\u002Fbackups, use organization context, or fall back to generated low-level REST API wrappers.\n\n## Route first\n\n- Read `references\u002Fapi-reference.md` for confirmed public classes, signatures, defaults, auth\u002Fprofile helpers, and repository\u002Fentity relationships.\n- Read `references\u002Fworkflows.md` for copyable SDK patterns for task\u002Fproject creation, frame download, import\u002Fexport, backups, profile-compatible scripts, and low-level API fallback.\n- Read `references\u002Ftroubleshooting.md` when imports, authentication, server compatibility, background requests, SSL, organization context, or cache\u002Ffilesystem behavior fail.\n- Run or adapt `scripts\u002Fsdk_task_smoke_template.py` for a safe import\u002Fsignature smoke by default, or for an explicit authenticated list\u002Fdownload workflow when the user supplies server credentials.\n\n## Use SDK instead of CLI when\n\n- The user needs branching logic, error handling, Python data structures, or integration into an ML pipeline.\n- A workflow needs `Client`, `Task`, `Project`, `Job`, `Organization`, `Issue`, or generated API model objects.\n- The task must compose CVAT calls with local data processing, model inference, or dataset conversion.\n- Repeated background operations should use `wait_for_completion()` rather than shell polling.\n\nUse `..\u002Fcli-automation\u002FSKILL.md` for terminal-only commands, `..\u002Fdataset-ops\u002FSKILL.md` for format and PyTorch dataset choices, `..\u002Fauto-annotation\u002FSKILL.md` for AA function protocols, and `..\u002Fdeployment-admin\u002FSKILL.md` for starting or administering a CVAT service.\n\n## Minimal install and import checks\n\n```bash\npip install cvat-sdk\npython - \u003C\u003C'PY'\nfrom cvat_sdk import make_client, Client, Config\nfrom cvat_sdk.core.proxies.tasks import ResourceType\nprint(Client, Config, [str(x) for x in ResourceType])\nPY\n```\n\nUse extras only when needed:\n\n```bash\npip install \"cvat-sdk[masks]\"     # mask encode\u002Fdecode helpers needing NumPy\npip install \"cvat-sdk[pytorch]\"   # PyTorch dataset adapter and built-in torchvision AA functions\n```\n\n## Safe authentication defaults\n\n- Prefer PAT authentication (`access_token=`) or CLI-compatible profiles rather than hard-coded passwords.\n- If using password auth, pass it as a secret runtime value, not in code committed to a repository.\n- Include the scheme in the server URL (`http:\u002F\u002F` or `https:\u002F\u002F`); SDK defaults and compatibility checks are stricter in recent releases.\n- Set `organization_slug` or use `organization_context(slug)` when the workflow must operate inside an organization workspace.\n- Treat `config.allow_unsupported_server=True` warnings seriously: SDK\u002Fserver minor versions should normally match or be adjacent.\n\n## Core pattern\n\n```python\nfrom cvat_sdk import make_client, models\nfrom cvat_sdk.core.proxies.tasks import ResourceType\n\nwith make_client(\"https:\u002F\u002Fcvat.example.com\", access_token=token) as client:\n    client.organization_slug = \"team-slug\"  # omit for personal workspace\n    task = client.tasks.create_from_data(\n        spec=models.TaskWriteRequest(\n            name=\"demo\",\n            labels=[{\"name\": \"car\", \"type\": \"rectangle\"}],\n        ),\n        resource_type=ResourceType.LOCAL,\n        resources=[\"image1.jpg\", \"image2.jpg\"],\n    )\n    print(task.id, task.size)\n```\n\nKeep scripts explicit about side effects: creating tasks\u002Fprojects, importing annotations, deleting resources, and downloading frames all mutate or read server state and need user-approved credentials\u002Fserver targets.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fcvat\u002Fsub-skills\u002Fsdk-automation",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill sdk-automation",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill sdk-automation",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill sdk-automation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcvat\u002Fsub-skills\u002Fsdk-automation\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",8428,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcvat\u002Fsub-skills\u002Fsdk-automation\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",4081,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcvat\u002Fsub-skills\u002Fsdk-automation\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",5376,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcvat\u002Fsub-skills\u002Fsdk-automation\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fsdk_task_smoke_template.py","SCRIPT","脚本",3692,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcvat\u002Fsub-skills\u002Fsdk-automation\u002Fscripts\u002Fsdk_task_smoke_template.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]