[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Z5ADG3DHW5VCSTFQSX9EN":3,"skill-same:01M78Z5ADG3DHW5VCSTFQSX9EN":75},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M78Z5ADG3DHW5VCSTFQSX9EN","sdk-client",null,"Use LeptonAI's Python SDK Client and v2 API resource\u002Fmodel objects safely from scripts and notebooks.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fleptonai\u002Fsub-skills\u002Fsdk-client\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sdk-client\ndescription: \"Use LeptonAI's Python SDK Client and v2 API resource\u002Fmodel objects\n  safely from scripts and notebooks.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# sdk-client\n\nUse this sub-skill when the task is to call a deployed Lepton endpoint from Python, inspect endpoint OpenAPI-derived methods, or build SDK scripts\u002Fnotebooks with `leptonai.api.v2` resource objects and Pydantic models.\n\n## Route here for\n\n- `Client(workspace_or_url, deployment=None, token=None, stream=None, chunk_size=None, timeout=None, no_check=False, http2=True)` endpoint-call code.\n- `local(port)`, `Client.local(port)`, `current()`, and `Client.current()` usage.\n- Dynamic `PathTree` behavior for OpenAPI paths exposed as Python attributes.\n- `APIClient(...)` workspace API resource objects and their method surfaces.\n- `APIResourse.safe_json(...)` model serialization and v2 Pydantic spec construction.\n- Pure parsing helpers `make_mounts_from_strings(...)` and `make_env_vars_from_strings(...)`.\n\n## Route elsewhere\n\n- Workspace login, workspace record maintenance, token refresh, or auth setup: use the `workspace-and-auth` route.\n- Shell-first workload recipes such as endpoint\u002Fjob\u002Fpod\u002FRay\u002Ffinetune create\u002Flist\u002Fupdate\u002Fdelete: use the `workload-management` route.\n- Storage, secrets, ingress, or canary routing plans: use the storage\u002Fingress route even when SDK model helpers appear in the plan.\n\n## Safety rule\n\nCreating a `Client(...)` for a real URL or workspace endpoint performs network checks and tries to fetch `openapi.json`. `APIClient` resource methods perform authenticated workspace API requests. Do not run live or credentialed cloud calls unless the user has explicitly authorized the operation and supplied an appropriate workspace context. The bundled scripts in this sub-skill are designed to avoid network calls.\n\n## Quick starts\n\n### Inspect the installed SDK without network calls\n\n```bash\npython scripts\u002Fsdk_introspection.py\npython scripts\u002Fclient_path_tree_demo.py\n```\n\nThe first script prints the installed package version, important signatures, and `APIClient` resource method surfaces without constructing a live workspace client. The second script demonstrates `PathTree` and `local(...)` behavior with fake callables only.\n\n### Call a deployed endpoint from Python\n\n```python\nimport os\nfrom leptonai.client import Client, local\n\n# Local endpoint URL plan; constructing the client contacts the local service.\nc = Client(local(port=8080), timeout=60, no_check=True)\nprint(list(c.paths()))\n\n# Workspace endpoint URL plan; pass an auth token explicitly if the endpoint is private.\nremote = Client(\n    \"workspace-id\",\n    \"endpoint-name\",\n    token=os.environ.get(\"LEPTON_WORKSPACE_TOKEN\"),\n    timeout=None,\n)\n# OpenAPI path \u002Frun becomes remote.run(...)\nresult = remote.run(inputs=\"hello\")\n```\n\nFor dynamic path rules, streaming return behavior, and failure modes, read [client-api.md](references\u002Fclient-api.md).\n\n### Build v2 specs without cloud calls\n\n```python\nfrom leptonai.api.v2.api_resource import APIResourse\nfrom leptonai.api.v2.spec_utils import make_env_vars_from_strings, make_mounts_from_strings\nfrom leptonai.api.v2.types.common import Metadata\nfrom leptonai.api.v2.types.deployment import LeptonDeployment, LeptonDeploymentUserSpec\n\nspec = LeptonDeployment(\n    metadata=Metadata(name=\"example\"),\n    spec=LeptonDeploymentUserSpec(\n        envs=make_env_vars_from_strings([\"MODE=test\"], [\"API_SECRET\"]),\n        mounts=make_mounts_from_strings([\"\u002Fdata:\u002Fmnt\u002Fdata:node-local\"]),\n    ),\n)\npayload = APIResourse.safe_json(APIResourse.__new__(APIResourse), spec)\n```\n\nFor resource surfaces, serialization caveats, and spec helpers, read [api-resources.md](references\u002Fapi-resources.md) and [specs-and-models.md](references\u002Fspecs-and-models.md).\n\n## Troubleshooting index\n\n- OpenAPI path not found, invalid identifier, or confusing attribute name: [troubleshooting.md](references\u002Ftroubleshooting.md#openapi-path-or-attribute-not-found).\n- `current()` says no current workspace: [troubleshooting.md](references\u002Ftroubleshooting.md#current-has-no-workspace).\n- 401\u002F403\u002Fauth token required: [troubleshooting.md](references\u002Ftroubleshooting.md#authtoken-needed).\n- Pydantic v1\u002Fv2 model or validator issues: [troubleshooting.md](references\u002Ftroubleshooting.md#pydantic-v1v2-compatibility).\n- `safe_json` dropped `None` unexpectedly or rejected a dict: [troubleshooting.md](references\u002Ftroubleshooting.md#safe_json-and-explicit-null-values).\n- Mount\u002Fenv parsing errors: [troubleshooting.md](references\u002Ftroubleshooting.md#mountenv-validation-errors).\n","# sdk-client\n\nUse this sub-skill when the task is to call a deployed Lepton endpoint from Python, inspect endpoint OpenAPI-derived methods, or build SDK scripts\u002Fnotebooks with `leptonai.api.v2` resource objects and Pydantic models.\n\n## Route here for\n\n- `Client(workspace_or_url, deployment=None, token=None, stream=None, chunk_size=None, timeout=None, no_check=False, http2=True)` endpoint-call code.\n- `local(port)`, `Client.local(port)`, `current()`, and `Client.current()` usage.\n- Dynamic `PathTree` behavior for OpenAPI paths exposed as Python attributes.\n- `APIClient(...)` workspace API resource objects and their method surfaces.\n- `APIResourse.safe_json(...)` model serialization and v2 Pydantic spec construction.\n- Pure parsing helpers `make_mounts_from_strings(...)` and `make_env_vars_from_strings(...)`.\n\n## Route elsewhere\n\n- Workspace login, workspace record maintenance, token refresh, or auth setup: use the `workspace-and-auth` route.\n- Shell-first workload recipes such as endpoint\u002Fjob\u002Fpod\u002FRay\u002Ffinetune create\u002Flist\u002Fupdate\u002Fdelete: use the `workload-management` route.\n- Storage, secrets, ingress, or canary routing plans: use the storage\u002Fingress route even when SDK model helpers appear in the plan.\n\n## Safety rule\n\nCreating a `Client(...)` for a real URL or workspace endpoint performs network checks and tries to fetch `openapi.json`. `APIClient` resource methods perform authenticated workspace API requests. Do not run live or credentialed cloud calls unless the user has explicitly authorized the operation and supplied an appropriate workspace context. The bundled scripts in this sub-skill are designed to avoid network calls.\n\n## Quick starts\n\n### Inspect the installed SDK without network calls\n\n```bash\npython scripts\u002Fsdk_introspection.py\npython scripts\u002Fclient_path_tree_demo.py\n```\n\nThe first script prints the installed package version, important signatures, and `APIClient` resource method surfaces without constructing a live workspace client. The second script demonstrates `PathTree` and `local(...)` behavior with fake callables only.\n\n### Call a deployed endpoint from Python\n\n```python\nimport os\nfrom leptonai.client import Client, local\n\n# Local endpoint URL plan; constructing the client contacts the local service.\nc = Client(local(port=8080), timeout=60, no_check=True)\nprint(list(c.paths()))\n\n# Workspace endpoint URL plan; pass an auth token explicitly if the endpoint is private.\nremote = Client(\n    \"workspace-id\",\n    \"endpoint-name\",\n    token=os.environ.get(\"LEPTON_WORKSPACE_TOKEN\"),\n    timeout=None,\n)\n# OpenAPI path \u002Frun becomes remote.run(...)\nresult = remote.run(inputs=\"hello\")\n```\n\nFor dynamic path rules, streaming return behavior, and failure modes, read [client-api.md](references\u002Fclient-api.md).\n\n### Build v2 specs without cloud calls\n\n```python\nfrom leptonai.api.v2.api_resource import APIResourse\nfrom leptonai.api.v2.spec_utils import make_env_vars_from_strings, make_mounts_from_strings\nfrom leptonai.api.v2.types.common import Metadata\nfrom leptonai.api.v2.types.deployment import LeptonDeployment, LeptonDeploymentUserSpec\n\nspec = LeptonDeployment(\n    metadata=Metadata(name=\"example\"),\n    spec=LeptonDeploymentUserSpec(\n        envs=make_env_vars_from_strings([\"MODE=test\"], [\"API_SECRET\"]),\n        mounts=make_mounts_from_strings([\"\u002Fdata:\u002Fmnt\u002Fdata:node-local\"]),\n    ),\n)\npayload = APIResourse.safe_json(APIResourse.__new__(APIResourse), spec)\n```\n\nFor resource surfaces, serialization caveats, and spec helpers, read [api-resources.md](references\u002Fapi-resources.md) and [specs-and-models.md](references\u002Fspecs-and-models.md).\n\n## Troubleshooting index\n\n- OpenAPI path not found, invalid identifier, or confusing attribute name: [troubleshooting.md](references\u002Ftroubleshooting.md#openapi-path-or-attribute-not-found).\n- `current()` says no current workspace: [troubleshooting.md](references\u002Ftroubleshooting.md#current-has-no-workspace).\n- 401\u002F403\u002Fauth token required: [troubleshooting.md](references\u002Ftroubleshooting.md#authtoken-needed).\n- Pydantic v1\u002Fv2 model or validator issues: [troubleshooting.md](references\u002Ftroubleshooting.md#pydantic-v1v2-compatibility).\n- `safe_json` dropped `None` unexpectedly or rejected a dict: [troubleshooting.md](references\u002Ftroubleshooting.md#safe_json-and-explicit-null-values).\n- Mount\u002Fenv parsing errors: [troubleshooting.md](references\u002Ftroubleshooting.md#mountenv-validation-errors).\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fleptonai\u002Fsub-skills\u002Fsdk-client",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill sdk-client",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill sdk-client",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill sdk-client","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fleptonai\u002Fsub-skills\u002Fsdk-client\u002FSKILL.md",[47,53,57,61,65,71],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-resources.md","REFERENCE","参考文档",7865,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fleptonai\u002Fsub-skills\u002Fsdk-client\u002Freferences\u002Fapi-resources.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fclient-api.md",7244,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fleptonai\u002Fsub-skills\u002Fsdk-client\u002Freferences\u002Fclient-api.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fspecs-and-models.md",6745,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fleptonai\u002Fsub-skills\u002Fsdk-client\u002Freferences\u002Fspecs-and-models.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",8104,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fleptonai\u002Fsub-skills\u002Fsdk-client\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fclient_path_tree_demo.py","SCRIPT","脚本",3271,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fleptonai\u002Fsub-skills\u002Fsdk-client\u002Fscripts\u002Fclient_path_tree_demo.py",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fsdk_introspection.py",5657,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fleptonai\u002Fsub-skills\u002Fsdk-client\u002Fscripts\u002Fsdk_introspection.py",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]