[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78SFDHPP4SWEG2M8XA3WJFF":3,"skill-same:01M78SFDHPP4SWEG2M8XA3WJFF":75},{"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},"01M78SFDHPP4SWEG2M8XA3WJFF","alpasim",null,"Use AlpaSim repository guidance for autonomous-driving simulation setup, Hydra wizard runs, runtime services, ego drivers and plugins, ASL evaluation, controller\u002Fphysics\u002Ftraffic components, gRPC contracts, and operational troubleshooting.","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\u002Falpasim\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: alpasim\ndescription: \"Use AlpaSim repository guidance for autonomous-driving simulation\n  setup, Hydra wizard runs, runtime services, ego drivers and plugins, ASL\n  evaluation, controller\u002Fphysics\u002Ftraffic components, gRPC contracts, and\n  operational troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# AlpaSim\n\nAlpaSim is a modular, data-driven autonomous-driving simulator. It orchestrates\nrenderer, driver, controller, physics, traffic, runtime, and evaluation\nservices through gRPC. Use this root as a router; read only the focused\nsub-skill needed for the task.\n\n## Route by intent\n\n- **Prepare or run a simulation, compose Hydra overrides, select scenes,\n  Docker\u002FSlurm deployment, tune GPUs\u002Ftiming, or inspect telemetry:** read\n  [simulation-wizard](sub-skills\u002Fsimulation-wizard\u002FSKILL.md).\n- **Understand the event loop, service lifecycle, addresses, daemon mode,\n  replay, timing validation, renderer caches, or video-model chunking:** read\n  [runtime-services](sub-skills\u002Fruntime-services\u002FSKILL.md).\n- **Select or adapt an ego policy, manual\u002Fexternal driver, model input\u002Foutput,\n  camera rectification, or plugin entry points\u002Fconfig discovery:** read\n  [drivers-and-plugins](sub-skills\u002Fdrivers-and-plugins\u002FSKILL.md).\n- **Inspect ASL logs, extract frames, evaluate\u002Faggregate\u002Fre-evaluate runs,\n  interpret metrics\u002Fvideos, or use trajectory\u002Fgeometry utilities:** read\n  [evaluation-and-logs](sub-skills\u002Fevaluation-and-logs\u002FSKILL.md).\n- **Choose MPC, inspect vehicle state, run ground physics, understand CATK\n  traffic sessions\u002Fhandover, or classify CUDA\u002FPyG\u002FWarp requirements:** read\n  [control-physics-traffic](sub-skills\u002Fcontrol-physics-traffic\u002FSKILL.md).\n- **Change protobufs, compile generated stubs, use gRPC clients, inspect\n  package entry points, or review safe developer\u002Ftool workflows:** read\n  [grpc-and-developer-tools](sub-skills\u002Fgrpc-and-developer-tools\u002FSKILL.md).\n\nCross-cutting details are in [troubleshooting](references\u002Ftroubleshooting.md),\n[package and backend notes](references\u002Fpackage-and-backend-overview.md), and\n[coordinate frames](references\u002Fcoordinate-frames.md). Run the read-only\n[environment checker](scripts\u002Fcheck_env.py) before optional backend work; the\nstructured [routing metadata](references\u002Frepo-routing-metadata.json) is consumed\nby the specialized repo-skill importer. Check [repository provenance](references\u002Frepo-provenance.md) before treating this\ngraph as current for another checkout.\n\n## Installation orientation\n\nAlpaSim is a `uv` workspace. The root project intentionally has no default\nruntime dependencies; install only the workspace extra for the chosen workflow:\n\n```bash\nuv sync --extra wizard                 # wizard and its transitive core\nuv sync --extra all                    # all core packages, no optional plugin\nuv sync --extra all --extra transfuser # core plus the public Transfuser plugin\n```\n\nUse Python 3.11 for the core packages. `alpasim_driver` currently requires\nPython 3.12, so use a compatible environment for driver\u002Fmodel inspection. A\nfull simulation additionally requires Docker Compose, NVIDIA Container\nToolkit\u002FCUDA, scene artifacts, and often Hugging Face access; a package import\nis not proof that those services or assets work.\n\nAfter changing `.proto` definitions, compile stubs from the gRPC package with\n`uv run compile-protos`; use the developer-tools route for the safe bundled\ncompiler and clean\u002Fbuild distinctions. Verify a selected environment with:\n\n```bash\npython -c \"import alpasim_grpc, alpasim_utils, alpasim_runtime, alpasim_wizard\"\npython -c \"from alpasim_grpc.v0 import runtime_pb2, runtime_pb2_grpc\"\n```\n\n## Operating boundaries\n\n- Keep `HF_TOKEN`, external endpoints, private paths, model weights, scene\n  caches, and scheduler credentials out of prompts, generated YAML, logs, and\n  skill content. Treat gated scene\u002Fmodel downloads as user-authorized actions.\n- Start with config generation and a one-scene\u002Fone-rollout plan. Prefer\n  `wizard.run_method=NONE` or a read-only checker before containers, network\n  services, GPU inference, or scheduler submission.\n- Preserve resolved run files and the first causal service error. A rollout is\n  successful only when its `_complete` marker and expected evaluation outputs\n  exist; an ASL file alone is not completion.\n- Do not use CPU imports to claim CUDA renderer, Warp, CATK\u002FPyG, or model\n  inference coverage. The optional backend notes preserve those limits.\n- Keep coordinate-frame names explicit: `local`, `rig`, `aabb`, `ecef`, and the\n  estimated\u002Fnoised frame are not interchangeable. Read the coordinate reference\n  before changing transforms or service messages.\n\n## Verification entry points\n\nThe generated graph is intended to support focused, reproducible checks rather\nthan a default full simulation. Use the verification artifacts outside this\nruntime tree when reviewing coverage. Safe native candidates include wizard\nconfig\u002Fdispatch, runtime validation\u002Freplay, controller, evaluation\u002FASL,\nutilities, plugin registry, and protobuf compilation tests. Full Docker,\nNuRec\u002FFlashDreams, gated HF assets, model inference, CATK compiled extensions,\nSlurm submission, and large benchmarks remain explicitly conditional.\n","# AlpaSim\n\nAlpaSim is a modular, data-driven autonomous-driving simulator. It orchestrates\nrenderer, driver, controller, physics, traffic, runtime, and evaluation\nservices through gRPC. Use this root as a router; read only the focused\nsub-skill needed for the task.\n\n## Route by intent\n\n- **Prepare or run a simulation, compose Hydra overrides, select scenes,\n  Docker\u002FSlurm deployment, tune GPUs\u002Ftiming, or inspect telemetry:** read\n  [simulation-wizard](sub-skills\u002Fsimulation-wizard\u002FSKILL.md).\n- **Understand the event loop, service lifecycle, addresses, daemon mode,\n  replay, timing validation, renderer caches, or video-model chunking:** read\n  [runtime-services](sub-skills\u002Fruntime-services\u002FSKILL.md).\n- **Select or adapt an ego policy, manual\u002Fexternal driver, model input\u002Foutput,\n  camera rectification, or plugin entry points\u002Fconfig discovery:** read\n  [drivers-and-plugins](sub-skills\u002Fdrivers-and-plugins\u002FSKILL.md).\n- **Inspect ASL logs, extract frames, evaluate\u002Faggregate\u002Fre-evaluate runs,\n  interpret metrics\u002Fvideos, or use trajectory\u002Fgeometry utilities:** read\n  [evaluation-and-logs](sub-skills\u002Fevaluation-and-logs\u002FSKILL.md).\n- **Choose MPC, inspect vehicle state, run ground physics, understand CATK\n  traffic sessions\u002Fhandover, or classify CUDA\u002FPyG\u002FWarp requirements:** read\n  [control-physics-traffic](sub-skills\u002Fcontrol-physics-traffic\u002FSKILL.md).\n- **Change protobufs, compile generated stubs, use gRPC clients, inspect\n  package entry points, or review safe developer\u002Ftool workflows:** read\n  [grpc-and-developer-tools](sub-skills\u002Fgrpc-and-developer-tools\u002FSKILL.md).\n\nCross-cutting details are in [troubleshooting](references\u002Ftroubleshooting.md),\n[package and backend notes](references\u002Fpackage-and-backend-overview.md), and\n[coordinate frames](references\u002Fcoordinate-frames.md). Run the read-only\n[environment checker](scripts\u002Fcheck_env.py) before optional backend work; the\nstructured [routing metadata](references\u002Frepo-routing-metadata.json) is consumed\nby the specialized repo-skill importer. Check [repository provenance](references\u002Frepo-provenance.md) before treating this\ngraph as current for another checkout.\n\n## Installation orientation\n\nAlpaSim is a `uv` workspace. The root project intentionally has no default\nruntime dependencies; install only the workspace extra for the chosen workflow:\n\n```bash\nuv sync --extra wizard                 # wizard and its transitive core\nuv sync --extra all                    # all core packages, no optional plugin\nuv sync --extra all --extra transfuser # core plus the public Transfuser plugin\n```\n\nUse Python 3.11 for the core packages. `alpasim_driver` currently requires\nPython 3.12, so use a compatible environment for driver\u002Fmodel inspection. A\nfull simulation additionally requires Docker Compose, NVIDIA Container\nToolkit\u002FCUDA, scene artifacts, and often Hugging Face access; a package import\nis not proof that those services or assets work.\n\nAfter changing `.proto` definitions, compile stubs from the gRPC package with\n`uv run compile-protos`; use the developer-tools route for the safe bundled\ncompiler and clean\u002Fbuild distinctions. Verify a selected environment with:\n\n```bash\npython -c \"import alpasim_grpc, alpasim_utils, alpasim_runtime, alpasim_wizard\"\npython -c \"from alpasim_grpc.v0 import runtime_pb2, runtime_pb2_grpc\"\n```\n\n## Operating boundaries\n\n- Keep `HF_TOKEN`, external endpoints, private paths, model weights, scene\n  caches, and scheduler credentials out of prompts, generated YAML, logs, and\n  skill content. Treat gated scene\u002Fmodel downloads as user-authorized actions.\n- Start with config generation and a one-scene\u002Fone-rollout plan. Prefer\n  `wizard.run_method=NONE` or a read-only checker before containers, network\n  services, GPU inference, or scheduler submission.\n- Preserve resolved run files and the first causal service error. A rollout is\n  successful only when its `_complete` marker and expected evaluation outputs\n  exist; an ASL file alone is not completion.\n- Do not use CPU imports to claim CUDA renderer, Warp, CATK\u002FPyG, or model\n  inference coverage. The optional backend notes preserve those limits.\n- Keep coordinate-frame names explicit: `local`, `rig`, `aabb`, `ecef`, and the\n  estimated\u002Fnoised frame are not interchangeable. Read the coordinate reference\n  before changing transforms or service messages.\n\n## Verification entry points\n\nThe generated graph is intended to support focused, reproducible checks rather\nthan a default full simulation. Use the verification artifacts outside this\nruntime tree when reviewing coverage. Safe native candidates include wizard\nconfig\u002Fdispatch, runtime validation\u002Freplay, controller, evaluation\u002FASL,\nutilities, plugin registry, and protobuf compilation tests. Full Docker,\nNuRec\u002FFlashDreams, gated HF assets, model inference, CATK compiled extensions,\nSlurm submission, and large benchmarks remain explicitly conditional.\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\u002Falpasim",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 alpasim",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill alpasim",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill alpasim","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falpasim\u002FSKILL.md",[47,53,57,61,65,69],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcoordinate-frames.md","REFERENCE","参考文档",1822,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falpasim\u002Freferences\u002Fcoordinate-frames.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fpackage-and-backend-overview.md",3412,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falpasim\u002Freferences\u002Fpackage-and-backend-overview.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-provenance.md",2954,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falpasim\u002Freferences\u002Frepo-provenance.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Frepo-routing-metadata.json",428,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falpasim\u002Freferences\u002Frepo-routing-metadata.json",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ftroubleshooting.md",3987,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falpasim\u002Freferences\u002Ftroubleshooting.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fcheck_env.py","SCRIPT","脚本",3371,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falpasim\u002Fscripts\u002Fcheck_env.py",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]