[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796EBKKFW7BJRPWAQTB5MTY":3,"skill-same:01M796EBKKFW7BJRPWAQTB5MTY":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},"01M796EBKKFW7BJRPWAQTB5MTY","core-api",null,"Use TorchMetrics core APIs for import checks, metric lifecycle, custom Metric state, device\u002FDDP behavior, persistence, and Lightning logging.","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\u002Ftorchmetrics\u002Fsub-skills\u002Fcore-api\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: core-api\ndescription: \"Use TorchMetrics core APIs for import checks, metric lifecycle,\n  custom Metric state, device\u002FDDP behavior, persistence, and Lightning logging.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# TorchMetrics Core API\n\nUse this sub-skill when a task is about the TorchMetrics base API rather than a specific metric family: choosing functional versus module metrics, accumulating batches, writing a custom `Metric`, moving metrics across devices, synchronizing distributed state, saving metric state, or logging metrics from PyTorch Lightning.\n\n## Route map\n\n- Read [references\u002Fcore-api.md](references\u002Fcore-api.md) when you need import sanity checks, functional-vs-module selection, `update`\u002F`compute`\u002F`forward`\u002F`reset` semantics, `MetricCollection`, device\u002Fdtype rules, or state persistence.\n- Read [references\u002Fcustom-metrics-lightning-ddp.md](references\u002Fcustom-metrics-lightning-ddp.md) when implementing `Metric` subclasses with `add_state`, list states, `dist_reduce_fx`, cache behavior, DDP controls, or Lightning `self.log`\u002F`self.log_dict` patterns.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when you see install\u002Fimport errors, unexpected keyword arguments, stale computed values, device mismatches, unregistered metrics, Lightning logging failures, or DDP synchronization surprises.\n- Run [scripts\u002Fcore_metric_smoke.py](scripts\u002Fcore_metric_smoke.py) to verify that the installed package can instantiate and execute `Accuracy`, `MeanSquaredError`, `MetricCollection`, and a small custom list-state metric without downloads.\n\n## Quick usage policy\n\n1. Use functional metrics for one-shot tensor-in\u002Ftensor-out calculations that do not need accumulation, object registration, state persistence, or built-in distributed synchronization.\n2. Use module metrics for training\u002Fevaluation loops, multi-batch accumulation, Lightning logging, `MetricCollection`, device moves, or DDP-aware synchronization.\n3. Register module metrics as `nn.Module` children: direct attributes, `nn.ModuleList`, `nn.ModuleDict`, or `MetricCollection`; do not hide metrics inside plain Python containers.\n4. Keep separate metric instances for train\u002Fvalidation\u002Ftest and for each dataloader whose state must not mix.\n5. Route detailed domain metric catalogs to sibling domain sub-skills; route wrappers and plotting to `collections-wrappers-plotting`; route metrics that may download models to `model-based-metrics`.\n","# TorchMetrics Core API\n\nUse this sub-skill when a task is about the TorchMetrics base API rather than a specific metric family: choosing functional versus module metrics, accumulating batches, writing a custom `Metric`, moving metrics across devices, synchronizing distributed state, saving metric state, or logging metrics from PyTorch Lightning.\n\n## Route map\n\n- Read [references\u002Fcore-api.md](references\u002Fcore-api.md) when you need import sanity checks, functional-vs-module selection, `update`\u002F`compute`\u002F`forward`\u002F`reset` semantics, `MetricCollection`, device\u002Fdtype rules, or state persistence.\n- Read [references\u002Fcustom-metrics-lightning-ddp.md](references\u002Fcustom-metrics-lightning-ddp.md) when implementing `Metric` subclasses with `add_state`, list states, `dist_reduce_fx`, cache behavior, DDP controls, or Lightning `self.log`\u002F`self.log_dict` patterns.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when you see install\u002Fimport errors, unexpected keyword arguments, stale computed values, device mismatches, unregistered metrics, Lightning logging failures, or DDP synchronization surprises.\n- Run [scripts\u002Fcore_metric_smoke.py](scripts\u002Fcore_metric_smoke.py) to verify that the installed package can instantiate and execute `Accuracy`, `MeanSquaredError`, `MetricCollection`, and a small custom list-state metric without downloads.\n\n## Quick usage policy\n\n1. Use functional metrics for one-shot tensor-in\u002Ftensor-out calculations that do not need accumulation, object registration, state persistence, or built-in distributed synchronization.\n2. Use module metrics for training\u002Fevaluation loops, multi-batch accumulation, Lightning logging, `MetricCollection`, device moves, or DDP-aware synchronization.\n3. Register module metrics as `nn.Module` children: direct attributes, `nn.ModuleList`, `nn.ModuleDict`, or `MetricCollection`; do not hide metrics inside plain Python containers.\n4. Keep separate metric instances for train\u002Fvalidation\u002Ftest and for each dataloader whose state must not mix.\n5. Route detailed domain metric catalogs to sibling domain sub-skills; route wrappers and plotting to `collections-wrappers-plotting`; route metrics that may download models to `model-based-metrics`.\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\u002Ftorchmetrics\u002Fsub-skills\u002Fcore-api",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 core-api",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill core-api",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill core-api","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftorchmetrics\u002Fsub-skills\u002Fcore-api\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcore-api.md","REFERENCE","参考文档",9181,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftorchmetrics\u002Fsub-skills\u002Fcore-api\u002Freferences\u002Fcore-api.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fcustom-metrics-lightning-ddp.md",10563,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftorchmetrics\u002Fsub-skills\u002Fcore-api\u002Freferences\u002Fcustom-metrics-lightning-ddp.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",6821,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftorchmetrics\u002Fsub-skills\u002Fcore-api\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcore_metric_smoke.py","SCRIPT","脚本",7447,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftorchmetrics\u002Fsub-skills\u002Fcore-api\u002Fscripts\u002Fcore_metric_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",[],[]]