[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78WRTYGZG2YVD70C65YAJGS":3,"skill-same:01M78WRTYGZG2YVD70C65YAJGS":67},{"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},"01M78WRTYGZG2YVD70C65YAJGS","module-computation",null,"Compute evaluate metrics, comparisons, and measurements with direct or streaming inputs; combine modules; configure cache\u002Fdistributed runs; save results; and debug input validation.","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\u002Fevaluate\u002Fsub-skills\u002Fmodule-computation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: module-computation\ndescription: \"Compute evaluate metrics, comparisons, and measurements with\n  direct or streaming inputs; combine modules; configure cache\u002Fdistributed runs;\n  save results; and debug input validation.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Module Computation\n\nUse this sub-skill when a user has already selected or loaded an `evaluate` module and needs to run it correctly. Route module discovery, Hub\u002Flocal loading, revisions, and `evaluate.load(...)` decisions to `..\u002Fmodule-loading\u002F`. Route evaluator pipeline orchestration around datasets\u002Fmodels\u002Fpipelines to `..\u002Fevaluator-pipelines\u002F`. Route authoring or sharing new modules to `..\u002Fhub-and-cli\u002F`.\n\n## Start Here\n\n1. Inspect the loaded module before computing: check `module.features`, `module.inputs_description`, `module.module_type`, and `module.info` so input names and shapes match the module contract.\n2. Choose a computation style:\n   - Direct: `module.compute(predictions=[...], references=[...], **module_kwargs)` for all inputs at once.\n   - Streaming examples: call `module.add(prediction=..., reference=...)` repeatedly, then `module.compute()`.\n   - Streaming batches: call `module.add_batch(predictions=[...], references=[...])` for each batch, then `module.compute()`.\n3. For non-standard modules, use the input names shown in `features`, such as `inputs=` and `targets=`, instead of assuming `predictions`\u002F`references`.\n4. For multiple modules, use `evaluate.combine(...)`; pass `force_prefix=True` or a name-to-module dict when output keys may collide.\n5. For distributed runs, set the same `cache_dir`, `num_process`, and `experiment_id` on every worker, a unique `process_id` per worker, and read the result only from `process_id == 0`.\n6. Save finished result dictionaries with `evaluate.save(path_or_file, **result, **metadata)` when the user needs a JSON record.\n\n## Core References\n\n- `references\u002Fcomputation-workflows.md`: direct compute, streaming, combined evaluations, distributed\u002Fcache patterns, result saving, and integration examples.\n- `references\u002Fapi-reference.md`: signatures, accepted inputs, result shapes, and constructor\u002Fsettings table for computation APIs.\n- `references\u002Ftroubleshooting.md`: validation, shape, cache, distributed, casting, and combined-key failure modes.\n- `scripts\u002Fcompute_smoke.py`: safe smoke helper for tiny computations against a named module or local module path.\n\n## Fast Patterns\n\n```python\nimport evaluate\n\nmetric = evaluate.load(\"accuracy\")\nresult = metric.compute(predictions=[0, 1, 1, 0], references=[0, 1, 0, 1])\n```\n\n```python\nmetric = evaluate.load(\"accuracy\")\nfor predictions, references in [([0, 1], [0, 1]), ([1, 0], [0, 1])]:\n    metric.add_batch(predictions=predictions, references=references)\nresult = metric.compute()\n```\n\n```python\ncombined = evaluate.combine({\"acc\": \"accuracy\", \"f1_binary\": \"f1\"}, force_prefix=True)\nresult = combined.compute(predictions=[0, 1, 0], references=[0, 1, 1])\n```\n\n## Guardrails\n\n- `compute`, `add`, and `add_batch` are keyword-oriented for `EvaluationModule`; do not rely on positional calls for normal modules.\n- `features` describes one example; `add_batch` and `compute` usually receive lists, arrays, or tensors of those examples.\n- `add` takes singular aliases (`prediction`, `reference`) for standard modules; use custom feature names directly for non-standard modules.\n- `compute()` returns `None` on non-zero distributed processes; only process `0` returns the final result dict.\n- `keep_in_memory=True` is single-process only; do not combine it with `num_process > 1`.\n- `evaluate.save` records metadata including interpreter information in the JSON output; avoid publishing sensitive local paths from saved files without review.\n\n","# Module Computation\n\nUse this sub-skill when a user has already selected or loaded an `evaluate` module and needs to run it correctly. Route module discovery, Hub\u002Flocal loading, revisions, and `evaluate.load(...)` decisions to `..\u002Fmodule-loading\u002F`. Route evaluator pipeline orchestration around datasets\u002Fmodels\u002Fpipelines to `..\u002Fevaluator-pipelines\u002F`. Route authoring or sharing new modules to `..\u002Fhub-and-cli\u002F`.\n\n## Start Here\n\n1. Inspect the loaded module before computing: check `module.features`, `module.inputs_description`, `module.module_type`, and `module.info` so input names and shapes match the module contract.\n2. Choose a computation style:\n   - Direct: `module.compute(predictions=[...], references=[...], **module_kwargs)` for all inputs at once.\n   - Streaming examples: call `module.add(prediction=..., reference=...)` repeatedly, then `module.compute()`.\n   - Streaming batches: call `module.add_batch(predictions=[...], references=[...])` for each batch, then `module.compute()`.\n3. For non-standard modules, use the input names shown in `features`, such as `inputs=` and `targets=`, instead of assuming `predictions`\u002F`references`.\n4. For multiple modules, use `evaluate.combine(...)`; pass `force_prefix=True` or a name-to-module dict when output keys may collide.\n5. For distributed runs, set the same `cache_dir`, `num_process`, and `experiment_id` on every worker, a unique `process_id` per worker, and read the result only from `process_id == 0`.\n6. Save finished result dictionaries with `evaluate.save(path_or_file, **result, **metadata)` when the user needs a JSON record.\n\n## Core References\n\n- `references\u002Fcomputation-workflows.md`: direct compute, streaming, combined evaluations, distributed\u002Fcache patterns, result saving, and integration examples.\n- `references\u002Fapi-reference.md`: signatures, accepted inputs, result shapes, and constructor\u002Fsettings table for computation APIs.\n- `references\u002Ftroubleshooting.md`: validation, shape, cache, distributed, casting, and combined-key failure modes.\n- `scripts\u002Fcompute_smoke.py`: safe smoke helper for tiny computations against a named module or local module path.\n\n## Fast Patterns\n\n```python\nimport evaluate\n\nmetric = evaluate.load(\"accuracy\")\nresult = metric.compute(predictions=[0, 1, 1, 0], references=[0, 1, 0, 1])\n```\n\n```python\nmetric = evaluate.load(\"accuracy\")\nfor predictions, references in [([0, 1], [0, 1]), ([1, 0], [0, 1])]:\n    metric.add_batch(predictions=predictions, references=references)\nresult = metric.compute()\n```\n\n```python\ncombined = evaluate.combine({\"acc\": \"accuracy\", \"f1_binary\": \"f1\"}, force_prefix=True)\nresult = combined.compute(predictions=[0, 1, 0], references=[0, 1, 1])\n```\n\n## Guardrails\n\n- `compute`, `add`, and `add_batch` are keyword-oriented for `EvaluationModule`; do not rely on positional calls for normal modules.\n- `features` describes one example; `add_batch` and `compute` usually receive lists, arrays, or tensors of those examples.\n- `add` takes singular aliases (`prediction`, `reference`) for standard modules; use custom feature names directly for non-standard modules.\n- `compute()` returns `None` on non-zero distributed processes; only process `0` returns the final result dict.\n- `keep_in_memory=True` is single-process only; do not combine it with `num_process > 1`.\n- `evaluate.save` records metadata including interpreter information in the JSON output; avoid publishing sensitive local paths from saved files without review.\n\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\u002Fevaluate\u002Fsub-skills\u002Fmodule-computation",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 module-computation",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill module-computation",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill module-computation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fevaluate\u002Fsub-skills\u002Fmodule-computation\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",5951,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fevaluate\u002Fsub-skills\u002Fmodule-computation\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fcomputation-workflows.md",5931,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fevaluate\u002Fsub-skills\u002Fmodule-computation\u002Freferences\u002Fcomputation-workflows.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",4878,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fevaluate\u002Fsub-skills\u002Fmodule-computation\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcompute_smoke.py","SCRIPT","脚本",3449,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fevaluate\u002Fsub-skills\u002Fmodule-computation\u002Fscripts\u002Fcompute_smoke.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]