[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78ZATDFJBZYVBJVMTKETDJV":3,"skill-same:01M78ZATDFJBZYVBJVMTKETDJV":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},"01M78ZATDFJBZYVBJVMTKETDJV","benchmark-cli",null,"Use LimiX benchmark-style classification and regression CLI commands with safe local dataset and checkpoint handling.","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\u002Flimi-x\u002Fsub-skills\u002Fbenchmark-cli\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: benchmark-cli\ndescription: \"Use LimiX benchmark-style classification and regression CLI\n  commands with safe local dataset and checkpoint handling.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# benchmark-cli\n\nUse this sub-skill when a task asks for LimiX benchmark-style CLI inference over one or more local tabular dataset folders, result CSV collection, or dataset-layout validation before running the classification\u002Fregression benchmark scripts.\n\n## Start here\n\n1. Validate the dataset root before model inference:\n   ```bash\n   python sub-skills\u002Fbenchmark-cli\u002Fscripts\u002Fvalidate_dataset_layout.py DATASET_ROOT --task classification\n   python sub-skills\u002Fbenchmark-cli\u002Fscripts\u002Fvalidate_dataset_layout.py DATASET_ROOT --task regression\n   ```\n2. Prefer local inputs: pass both `--data_dir` and `--model_path`. Omitting either can trigger network downloads into `.\u002Fcache`.\n3. Choose an explicit config JSON path instead of relying on missing default config filenames.\n4. Treat full checkpoint CLI inference as GPU\u002FCUDA-sensitive: the benchmark scripts guard on CUDA availability before they process workloads, and full LimiX checkpoint inference needs a local LimiX checkpoint. Do not claim a benchmark CLI was run unless it actually completed.\n\n## Reference map\n\n- `references\u002Fcli-reference.md`: flag meanings, safe local command templates, DDP launch shapes, output files, and metrics.\n- `references\u002Fdataset-layout.md`: expected dataset-folder schema, target-column placement, train\u002Ftest behavior, dtype\u002Fcategory handling, and validator usage.\n- `references\u002Ftroubleshooting.md`: GPU guard, auto-download\u002Fnetwork failures, class-count and row-count skips, data-shape errors, DDP notes, and result-path confusion.\n\n## Routing boundaries\n\n- For direct `LimiXPredictor` Python API usage, route to `..\u002Fpredictor-inference\u002FSKILL.md`.\n- For inference config schema details, config generation, or preprocessing-pipeline edits, route to `..\u002Fconfiguration-preprocessing\u002FSKILL.md`.\n- For retrieval tuning\u002Fsearch-space semantics beyond the CLI flag surface, route to `..\u002Fretrieval-optimization\u002FSKILL.md`.\n- Do not run heavyweight benchmark CLIs as a validation shortcut. Use the bundled dataset validator and provide command recipes unless the user explicitly authorizes full inference with local data, a local checkpoint, and a ready CUDA\u002FGPU environment.\n","# benchmark-cli\n\nUse this sub-skill when a task asks for LimiX benchmark-style CLI inference over one or more local tabular dataset folders, result CSV collection, or dataset-layout validation before running the classification\u002Fregression benchmark scripts.\n\n## Start here\n\n1. Validate the dataset root before model inference:\n   ```bash\n   python sub-skills\u002Fbenchmark-cli\u002Fscripts\u002Fvalidate_dataset_layout.py DATASET_ROOT --task classification\n   python sub-skills\u002Fbenchmark-cli\u002Fscripts\u002Fvalidate_dataset_layout.py DATASET_ROOT --task regression\n   ```\n2. Prefer local inputs: pass both `--data_dir` and `--model_path`. Omitting either can trigger network downloads into `.\u002Fcache`.\n3. Choose an explicit config JSON path instead of relying on missing default config filenames.\n4. Treat full checkpoint CLI inference as GPU\u002FCUDA-sensitive: the benchmark scripts guard on CUDA availability before they process workloads, and full LimiX checkpoint inference needs a local LimiX checkpoint. Do not claim a benchmark CLI was run unless it actually completed.\n\n## Reference map\n\n- `references\u002Fcli-reference.md`: flag meanings, safe local command templates, DDP launch shapes, output files, and metrics.\n- `references\u002Fdataset-layout.md`: expected dataset-folder schema, target-column placement, train\u002Ftest behavior, dtype\u002Fcategory handling, and validator usage.\n- `references\u002Ftroubleshooting.md`: GPU guard, auto-download\u002Fnetwork failures, class-count and row-count skips, data-shape errors, DDP notes, and result-path confusion.\n\n## Routing boundaries\n\n- For direct `LimiXPredictor` Python API usage, route to `..\u002Fpredictor-inference\u002FSKILL.md`.\n- For inference config schema details, config generation, or preprocessing-pipeline edits, route to `..\u002Fconfiguration-preprocessing\u002FSKILL.md`.\n- For retrieval tuning\u002Fsearch-space semantics beyond the CLI flag surface, route to `..\u002Fretrieval-optimization\u002FSKILL.md`.\n- Do not run heavyweight benchmark CLIs as a validation shortcut. Use the bundled dataset validator and provide command recipes unless the user explicitly authorizes full inference with local data, a local checkpoint, and a ready CUDA\u002FGPU environment.\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\u002Flimi-x\u002Fsub-skills\u002Fbenchmark-cli",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 benchmark-cli",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill benchmark-cli",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill benchmark-cli","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flimi-x\u002Fsub-skills\u002Fbenchmark-cli\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcli-reference.md","REFERENCE","参考文档",8843,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flimi-x\u002Fsub-skills\u002Fbenchmark-cli\u002Freferences\u002Fcli-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fdataset-layout.md",4770,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flimi-x\u002Fsub-skills\u002Fbenchmark-cli\u002Freferences\u002Fdataset-layout.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",7489,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flimi-x\u002Fsub-skills\u002Fbenchmark-cli\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fvalidate_dataset_layout.py","SCRIPT","脚本",16420,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flimi-x\u002Fsub-skills\u002Fbenchmark-cli\u002Fscripts\u002Fvalidate_dataset_layout.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",[],[]]