[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7962AR1EHPR61HTF71QCHNJ":3,"skill-same:01M7962AR1EHPR61HTF71QCHNJ":83},{"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},"01M7962AR1EHPR61HTF71QCHNJ","serving-and-clients",null,"Use this sub-skill to build TensorFlow Serving PredictRequest payloads, run the Python gRPC dense and sparse clients, benchmark the minimal model, or reason about the legacy HTTP and non-Python client surfaces.","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\u002Ftensorflow-template-application\u002Fsub-skills\u002Fserving-and-clients\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"serving-and-clients\"\ndescription: \"Use this sub-skill to build TensorFlow Serving PredictRequest\n  payloads, run the Python gRPC dense and sparse clients, benchmark the minimal\n  model, or reason about the legacy HTTP and non-Python client surfaces.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Serving and Clients\n\nUse this route when a user asks how to send predictions to an exported model,\nwhy a serving request fails, which model name or port to use, or how the repo's\nlegacy client examples map to dense and sparse tensors.\n\n## Read first\n\n- [references\u002Fpython-grpc-client.md](references\u002Fpython-grpc-client.md) for the dense and sparse `PredictRequest` contract, tensor names, dtypes, and shape rules.\n- [references\u002Fminimal-benchmark.md](references\u002Fminimal-benchmark.md) for the safe minimal-model latency and QPS helper.\n- [references\u002Fhttp-service.md](references\u002Fhttp-service.md) for the legacy Django checkpoint-backed wrapper and its failure modes.\n- [references\u002Falternate-clients.md](references\u002Falternate-clients.md) when the question is about Java, Go, C++, Android, iOS, or Spark clients.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when the user reports a timeout, connection refusal, model mismatch, or shape error.\n\n## What this sub-skill owns\n\n- Python gRPC dense and sparse serving payloads.\n- Model name, version, port, and signature behavior for serving calls.\n- The safe dry-run path that prints request tensors without contacting a server.\n- The minimal model benchmark helper for local latency and live gRPC checks.\n- The legacy HTTP cancer prediction wrapper as a checkpoint-backed pattern.\n- Alternate clients as reference-only surfaces that need external toolchains.\n\n## Use these bundled helpers\n\n- Run [scripts\u002Fpredict_dense.py](scripts\u002Fpredict_dense.py) to inspect or send the dense serving payload.\n- Run [scripts\u002Fpredict_sparse.py](scripts\u002Fpredict_sparse.py) to inspect or send the sparse serving payload.\n- Run [scripts\u002Fbenchmark_minimal_model.py](scripts\u002Fbenchmark_minimal_model.py) for the minimal model's local or gRPC benchmark modes.\n\n## Route boundaries\n\n- If the user needs data conversion, TFRecords, or fixture creation, route that to the data-preparation sub-skill.\n- If the user needs training, checkpointing, SavedModel export, or TensorBoard, route that to the training-and-export sub-skill.\n- If the user wants Java, Go, C++, Android, or iOS build instructions, keep those as reference-only and do not promise a runnable helper in this environment.\n- If the user wants to modify the exported model itself, stay within the serving contract and do not drift into training logic.\n\n## Common questions this route should answer\n\n- Which `model_name`, `model_version`, and `port` values should match the server?\n- What are the dense and sparse input tensor names, dtypes, and shapes?\n- When should `signature_name` be set or omitted?\n- How do I tell a connection refusal from a request-shape mismatch?\n- Why does the legacy HTTP wrapper exit when the checkpoint is missing?\n\n## Working style\n\n1. Use the dry-run mode first when the user only needs to validate request shape or payload construction.\n2. Use the live gRPC path only when a server is already running and the model export is known.\n3. Prefer the dense or sparse reference that matches the user's tensor layout rather than guessing from the serving port alone.\n4. For non-Python clients, answer from the bundled reference pages and call out external toolchain needs clearly.\n\n## Notes\n\n- The dense and sparse helpers normalize request tensors before sending them.\n- The bundled benchmark helper separates a local NumPy check from the live serving call so the user can reason about minimal-model behavior without a server.\n- This sub-skill intentionally does not bundle native Java, Go, C++, Android, or iOS build systems.\n","# Serving and Clients\n\nUse this route when a user asks how to send predictions to an exported model,\nwhy a serving request fails, which model name or port to use, or how the repo's\nlegacy client examples map to dense and sparse tensors.\n\n## Read first\n\n- [references\u002Fpython-grpc-client.md](references\u002Fpython-grpc-client.md) for the dense and sparse `PredictRequest` contract, tensor names, dtypes, and shape rules.\n- [references\u002Fminimal-benchmark.md](references\u002Fminimal-benchmark.md) for the safe minimal-model latency and QPS helper.\n- [references\u002Fhttp-service.md](references\u002Fhttp-service.md) for the legacy Django checkpoint-backed wrapper and its failure modes.\n- [references\u002Falternate-clients.md](references\u002Falternate-clients.md) when the question is about Java, Go, C++, Android, iOS, or Spark clients.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when the user reports a timeout, connection refusal, model mismatch, or shape error.\n\n## What this sub-skill owns\n\n- Python gRPC dense and sparse serving payloads.\n- Model name, version, port, and signature behavior for serving calls.\n- The safe dry-run path that prints request tensors without contacting a server.\n- The minimal model benchmark helper for local latency and live gRPC checks.\n- The legacy HTTP cancer prediction wrapper as a checkpoint-backed pattern.\n- Alternate clients as reference-only surfaces that need external toolchains.\n\n## Use these bundled helpers\n\n- Run [scripts\u002Fpredict_dense.py](scripts\u002Fpredict_dense.py) to inspect or send the dense serving payload.\n- Run [scripts\u002Fpredict_sparse.py](scripts\u002Fpredict_sparse.py) to inspect or send the sparse serving payload.\n- Run [scripts\u002Fbenchmark_minimal_model.py](scripts\u002Fbenchmark_minimal_model.py) for the minimal model's local or gRPC benchmark modes.\n\n## Route boundaries\n\n- If the user needs data conversion, TFRecords, or fixture creation, route that to the data-preparation sub-skill.\n- If the user needs training, checkpointing, SavedModel export, or TensorBoard, route that to the training-and-export sub-skill.\n- If the user wants Java, Go, C++, Android, or iOS build instructions, keep those as reference-only and do not promise a runnable helper in this environment.\n- If the user wants to modify the exported model itself, stay within the serving contract and do not drift into training logic.\n\n## Common questions this route should answer\n\n- Which `model_name`, `model_version`, and `port` values should match the server?\n- What are the dense and sparse input tensor names, dtypes, and shapes?\n- When should `signature_name` be set or omitted?\n- How do I tell a connection refusal from a request-shape mismatch?\n- Why does the legacy HTTP wrapper exit when the checkpoint is missing?\n\n## Working style\n\n1. Use the dry-run mode first when the user only needs to validate request shape or payload construction.\n2. Use the live gRPC path only when a server is already running and the model export is known.\n3. Prefer the dense or sparse reference that matches the user's tensor layout rather than guessing from the serving port alone.\n4. For non-Python clients, answer from the bundled reference pages and call out external toolchain needs clearly.\n\n## Notes\n\n- The dense and sparse helpers normalize request tensors before sending them.\n- The bundled benchmark helper separates a local NumPy check from the live serving call so the user can reason about minimal-model behavior without a server.\n- This sub-skill intentionally does not bundle native Java, Go, C++, Android, or iOS build systems.\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\u002Ftensorflow-template-application\u002Fsub-skills\u002Fserving-and-clients",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 serving-and-clients",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill serving-and-clients",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill serving-and-clients","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorflow-template-application\u002Fsub-skills\u002Fserving-and-clients\u002FSKILL.md",[47,53,57,61,65,69,75,79],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Falternate-clients.md","REFERENCE","参考文档",3616,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorflow-template-application\u002Fsub-skills\u002Fserving-and-clients\u002Freferences\u002Falternate-clients.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fhttp-service.md",2184,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorflow-template-application\u002Fsub-skills\u002Fserving-and-clients\u002Freferences\u002Fhttp-service.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fminimal-benchmark.md",3510,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorflow-template-application\u002Fsub-skills\u002Fserving-and-clients\u002Freferences\u002Fminimal-benchmark.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fpython-grpc-client.md",3634,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorflow-template-application\u002Fsub-skills\u002Fserving-and-clients\u002Freferences\u002Fpython-grpc-client.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ftroubleshooting.md",3692,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorflow-template-application\u002Fsub-skills\u002Fserving-and-clients\u002Freferences\u002Ftroubleshooting.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fbenchmark_minimal_model.py","SCRIPT","脚本",5815,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorflow-template-application\u002Fsub-skills\u002Fserving-and-clients\u002Fscripts\u002Fbenchmark_minimal_model.py",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Fpredict_dense.py",5166,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorflow-template-application\u002Fsub-skills\u002Fserving-and-clients\u002Fscripts\u002Fpredict_dense.py",{"path":80,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":81,"sourceHtmlUrl":82},"scripts\u002Fpredict_sparse.py",7071,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorflow-template-application\u002Fsub-skills\u002Fserving-and-clients\u002Fscripts\u002Fpredict_sparse.py",[84,91,98,105,112,119],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"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":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"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":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"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",[],[]]