[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796TRNKVH0PJCWPJZXVFJA6":3,"skill-same:01M796TRNKVH0PJCWPJZXVFJA6":74},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M796TRNKVH0PJCWPJZXVFJA6","export-and-speed",null,"Routes Ultra-Fast-Lane-Detection TorchScript export, synthetic speed checks, and deployment benchmarking workflows.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fultra-fast-lane-detection\u002Fsub-skills\u002Fexport-and-speed\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: export-and-speed\ndescription: \"Routes Ultra-Fast-Lane-Detection TorchScript export, synthetic\n  speed checks, and deployment benchmarking workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# export-and-speed\n\nUse this sub-skill when a task is about exporting a lane model for deployment, timing its throughput, or understanding the C++\u002FLibTorch demo path.\n\n## Read this when\n\n- You need to export a checkpoint to TorchScript.\n- You need a quick synthetic speed benchmark.\n- You need to explain the C++\u002FLibTorch deployment example.\n- You need to reason about `cls_dim`, anchors, device choice, or half precision for export and timing.\n\n## What this sub-skill owns\n\n- TorchScript export commands and model input shape.\n- Synthetic throughput timing.\n- Deployment caveats for the C++ demo.\n- Speed-related checkpoint, device, and dimension assumptions.\n\n## What it does not own\n\n- Training command construction: see `training`.\n- Dataset layout and conversion: see `data-and-config`.\n- Accuracy evaluation and demo metrics: see `evaluation-and-visualization`.\n\n## Start here\n\n- Read `references\u002Fexport-workflows.md` for the export and benchmark flow.\n- Read `references\u002Fspeed-and-deployment.md` for the LibTorch\u002FOpenCV notes and practical timing caveats.\n- Read `references\u002Fapi-reference.md` for the verified model signature and dimension assumptions.\n- Read `references\u002Ftroubleshooting.md` for hardcoded path, checkpoint, and device issues.\n- Run `scripts\u002Fexport_torchscript.py` when you need a portable TorchScript file.\n- Run `scripts\u002Fbenchmark_synthetic.py` when you need a configurable synthetic timing check.\n\n## Typical flow\n\n1. Decide whether the user wants a CPU or CUDA export\u002Fbenchmark path.\n2. Confirm the checkpoint file and model dimensions.\n3. Export or benchmark using a helper that accepts explicit paths and device options.\n4. If the user wants C++ deployment, read the deployment caveats before building anything.\n\n## Caution points\n\n- The source `export.py` has a hardcoded checkpoint path and CUDA map_location.\n- The source speed scripts are demos, not robust command-line tools.\n- The C++ example hardcodes LibTorch and OpenCV paths.\n- `cls_dim` must match the chosen dataset family and backbone setup.\n\n## Reference and script links\n\n- `references\u002Fexport-workflows.md` for export patterns and safe invocation advice.\n- `references\u002Fspeed-and-deployment.md` for deployment and benchmark caveats.\n- `references\u002Fapi-reference.md` for the verified signature notes.\n- `references\u002Ftroubleshooting.md` for export and timing failures.\n- `scripts\u002Fexport_torchscript.py` for a parameterized export helper.\n- `scripts\u002Fbenchmark_synthetic.py` for a configurable speed helper.\n","# export-and-speed\n\nUse this sub-skill when a task is about exporting a lane model for deployment, timing its throughput, or understanding the C++\u002FLibTorch demo path.\n\n## Read this when\n\n- You need to export a checkpoint to TorchScript.\n- You need a quick synthetic speed benchmark.\n- You need to explain the C++\u002FLibTorch deployment example.\n- You need to reason about `cls_dim`, anchors, device choice, or half precision for export and timing.\n\n## What this sub-skill owns\n\n- TorchScript export commands and model input shape.\n- Synthetic throughput timing.\n- Deployment caveats for the C++ demo.\n- Speed-related checkpoint, device, and dimension assumptions.\n\n## What it does not own\n\n- Training command construction: see `training`.\n- Dataset layout and conversion: see `data-and-config`.\n- Accuracy evaluation and demo metrics: see `evaluation-and-visualization`.\n\n## Start here\n\n- Read `references\u002Fexport-workflows.md` for the export and benchmark flow.\n- Read `references\u002Fspeed-and-deployment.md` for the LibTorch\u002FOpenCV notes and practical timing caveats.\n- Read `references\u002Fapi-reference.md` for the verified model signature and dimension assumptions.\n- Read `references\u002Ftroubleshooting.md` for hardcoded path, checkpoint, and device issues.\n- Run `scripts\u002Fexport_torchscript.py` when you need a portable TorchScript file.\n- Run `scripts\u002Fbenchmark_synthetic.py` when you need a configurable synthetic timing check.\n\n## Typical flow\n\n1. Decide whether the user wants a CPU or CUDA export\u002Fbenchmark path.\n2. Confirm the checkpoint file and model dimensions.\n3. Export or benchmark using a helper that accepts explicit paths and device options.\n4. If the user wants C++ deployment, read the deployment caveats before building anything.\n\n## Caution points\n\n- The source `export.py` has a hardcoded checkpoint path and CUDA map_location.\n- The source speed scripts are demos, not robust command-line tools.\n- The C++ example hardcodes LibTorch and OpenCV paths.\n- `cls_dim` must match the chosen dataset family and backbone setup.\n\n## Reference and script links\n\n- `references\u002Fexport-workflows.md` for export patterns and safe invocation advice.\n- `references\u002Fspeed-and-deployment.md` for deployment and benchmark caveats.\n- `references\u002Fapi-reference.md` for the verified signature notes.\n- `references\u002Ftroubleshooting.md` for export and timing failures.\n- `scripts\u002Fexport_torchscript.py` for a parameterized export helper.\n- `scripts\u002Fbenchmark_synthetic.py` for a configurable speed helper.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fultra-fast-lane-detection\u002Fsub-skills\u002Fexport-and-speed",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill export-and-speed",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill export-and-speed",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill export-and-speed","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fultra-fast-lane-detection\u002Fsub-skills\u002Fexport-and-speed\u002FSKILL.md",[46,52,56,60,64,70],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",1255,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fultra-fast-lane-detection\u002Fsub-skills\u002Fexport-and-speed\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fexport-workflows.md",1508,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fultra-fast-lane-detection\u002Fsub-skills\u002Fexport-and-speed\u002Freferences\u002Fexport-workflows.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fspeed-and-deployment.md",1254,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fultra-fast-lane-detection\u002Fsub-skills\u002Fexport-and-speed\u002Freferences\u002Fspeed-and-deployment.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",2295,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fultra-fast-lane-detection\u002Fsub-skills\u002Fexport-and-speed\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fbenchmark_synthetic.py","SCRIPT","脚本",2709,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fultra-fast-lane-detection\u002Fsub-skills\u002Fexport-and-speed\u002Fscripts\u002Fbenchmark_synthetic.py",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fexport_torchscript.py",3109,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fultra-fast-lane-detection\u002Fsub-skills\u002Fexport-and-speed\u002Fscripts\u002Fexport_torchscript.py",[75,83,90,97,104,111],{"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":79,"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.","Apache-2.0","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":79,"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":79,"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":79,"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":79,"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":79,"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",[],[]]