[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7977D8PDECT6BQSKGWAFXY0":3,"skill-same:01M7977D8PDECT6BQSKGWAFXY0":66},{"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},"01M7977D8PDECT6BQSKGWAFXY0","evaluation",null,"Guide VLA-Adapter LIBERO and CALVIN evaluation, command generation, outputs, prerequisites, metrics, and benchmark cautions.","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\u002Fvla-adapter\u002Fsub-skills\u002Fevaluation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: evaluation\ndescription: \"Guide VLA-Adapter LIBERO and CALVIN evaluation, command\n  generation, outputs, prerequisites, metrics, and benchmark cautions.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Evaluation (external-checkout adapter)\n\nThis sub-skill renders plans for native LIBERO\u002FCALVIN evaluators in a separate\ncheckout. It contains only documentation and a command renderer: it does not\ncontain `experiments\u002Frobot\u002F` or `vla-scripts\u002F`, does not run an evaluation, and\nis not a self-contained benchmark runtime.\n\nSet the absolute source root and enter it before any native workflow:\n\n```bash\nexport VLA_ADAPTER_REPO_ROOT=\u002Fabs\u002Fpath\u002Fto\u002FVLA-Adapter\ncd \"$VLA_ADAPTER_REPO_ROOT\"\npython -m pip install -e \"$VLA_ADAPTER_REPO_ROOT\"\n```\n\nNative entrypoints are `experiments\u002Frobot\u002Flibero\u002Frun_libero_eval.py` and\n`vla-scripts\u002Fevaluate_calvin.py`. The bundled builder only prints commands\nbeginning with `cd \u003Cabsolute-repo-root> &&`; it never imports the model or\nlaunches a rollout. External prerequisites are CUDA-capable PyTorch, the base\nVLA-Adapter package, a complete compatible checkpoint, the selected LIBERO or\nCALVIN checkout and assets\u002Fdata\u002Fconfig layout, and a working EGL\u002FOpenGL\u002FMuJoCo\nor pybullet renderer. Video runs may additionally require imageio\u002Fffmpeg.\n\n## Read first\n\n- Read [references\u002Fevaluation-workflows.md](references\u002Fevaluation-workflows.md) for checkpoint-to-command workflows, expected outputs, and benchmark-specific runtime behavior.\n- Read [references\u002Fbenchmarks.md](references\u002Fbenchmarks.md) for suite names, checkpoint names, default evaluation volumes, and published LIBERO\u002FCALVIN metrics.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for dependency, renderer, checkpoint, unnormalization-key, log, and video failures.\n- Run `python \"$VLA_ADAPTER_SKILL_ROOT\u002Fsub-skills\u002Fevaluation\u002Fscripts\u002Fbuild_eval_command.py\" --repo-root \"$VLA_ADAPTER_REPO_ROOT\" --help` to inspect the non-executing command renderer.\n\n## Operating route\n\n1. Identify the benchmark: use LIBERO for `libero_spatial`, `libero_object`, `libero_goal`, or `libero_10`; use CALVIN for `calvin_abc`.\n2. Confirm the checkpoint family and suite match. Prefer the Pro checkpoints for published reproduction unless the user explicitly asks for the original release or a custom checkpoint.\n3. Confirm downstream prerequisites before launching: CUDA-capable PyTorch, the base VLA-Adapter package dependencies, the external benchmark stack, benchmark assets, and the checkpoint files.\n4. Generate the command with the bundled builder, then review the resulting `CUDA_VISIBLE_DEVICES=... python ...` invocation before execution.\n5. Capture stdout\u002Fstderr into an `eval_logs\u002F` file for long runs. LIBERO also writes internal text logs and rollout videos; CALVIN writes evaluation result files and per-subtask videos.\n6. Interpret only full-volume runs against published metrics: LIBERO defaults to 500 episodes per suite, while CALVIN reports average successful sequence length across 1,000 five-instruction sequences.\n\n## Critical cautions\n\n- LIBERO evaluation depends on the repository's image preprocessing: both third-person and wrist camera images are rotated 180 degrees before policy input.\n- LIBERO\u002FOpenVLA action execution normalizes the gripper action to `[-1, +1]`, binarizes it, then inverts the OpenVLA gripper sign for environment execution.\n- CALVIN reports average sequence length, not a single binary episode success rate; also inspect chain success rates for 1 through 5 consecutive instructions.\n- External LIBERO and CALVIN stacks were not part of the base package import surface. Treat them as downstream prerequisites, not guaranteed installed dependencies.\n","# Evaluation (external-checkout adapter)\n\nThis sub-skill renders plans for native LIBERO\u002FCALVIN evaluators in a separate\ncheckout. It contains only documentation and a command renderer: it does not\ncontain `experiments\u002Frobot\u002F` or `vla-scripts\u002F`, does not run an evaluation, and\nis not a self-contained benchmark runtime.\n\nSet the absolute source root and enter it before any native workflow:\n\n```bash\nexport VLA_ADAPTER_REPO_ROOT=\u002Fabs\u002Fpath\u002Fto\u002FVLA-Adapter\ncd \"$VLA_ADAPTER_REPO_ROOT\"\npython -m pip install -e \"$VLA_ADAPTER_REPO_ROOT\"\n```\n\nNative entrypoints are `experiments\u002Frobot\u002Flibero\u002Frun_libero_eval.py` and\n`vla-scripts\u002Fevaluate_calvin.py`. The bundled builder only prints commands\nbeginning with `cd \u003Cabsolute-repo-root> &&`; it never imports the model or\nlaunches a rollout. External prerequisites are CUDA-capable PyTorch, the base\nVLA-Adapter package, a complete compatible checkpoint, the selected LIBERO or\nCALVIN checkout and assets\u002Fdata\u002Fconfig layout, and a working EGL\u002FOpenGL\u002FMuJoCo\nor pybullet renderer. Video runs may additionally require imageio\u002Fffmpeg.\n\n## Read first\n\n- Read [references\u002Fevaluation-workflows.md](references\u002Fevaluation-workflows.md) for checkpoint-to-command workflows, expected outputs, and benchmark-specific runtime behavior.\n- Read [references\u002Fbenchmarks.md](references\u002Fbenchmarks.md) for suite names, checkpoint names, default evaluation volumes, and published LIBERO\u002FCALVIN metrics.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for dependency, renderer, checkpoint, unnormalization-key, log, and video failures.\n- Run `python \"$VLA_ADAPTER_SKILL_ROOT\u002Fsub-skills\u002Fevaluation\u002Fscripts\u002Fbuild_eval_command.py\" --repo-root \"$VLA_ADAPTER_REPO_ROOT\" --help` to inspect the non-executing command renderer.\n\n## Operating route\n\n1. Identify the benchmark: use LIBERO for `libero_spatial`, `libero_object`, `libero_goal`, or `libero_10`; use CALVIN for `calvin_abc`.\n2. Confirm the checkpoint family and suite match. Prefer the Pro checkpoints for published reproduction unless the user explicitly asks for the original release or a custom checkpoint.\n3. Confirm downstream prerequisites before launching: CUDA-capable PyTorch, the base VLA-Adapter package dependencies, the external benchmark stack, benchmark assets, and the checkpoint files.\n4. Generate the command with the bundled builder, then review the resulting `CUDA_VISIBLE_DEVICES=... python ...` invocation before execution.\n5. Capture stdout\u002Fstderr into an `eval_logs\u002F` file for long runs. LIBERO also writes internal text logs and rollout videos; CALVIN writes evaluation result files and per-subtask videos.\n6. Interpret only full-volume runs against published metrics: LIBERO defaults to 500 episodes per suite, while CALVIN reports average successful sequence length across 1,000 five-instruction sequences.\n\n## Critical cautions\n\n- LIBERO evaluation depends on the repository's image preprocessing: both third-person and wrist camera images are rotated 180 degrees before policy input.\n- LIBERO\u002FOpenVLA action execution normalizes the gripper action to `[-1, +1]`, binarizes it, then inverts the OpenVLA gripper sign for environment execution.\n- CALVIN reports average sequence length, not a single binary episode success rate; also inspect chain success rates for 1 through 5 consecutive instructions.\n- External LIBERO and CALVIN stacks were not part of the base package import surface. Treat them as downstream prerequisites, not guaranteed installed dependencies.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fvla-adapter\u002Fsub-skills\u002Fevaluation",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 evaluation",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill evaluation",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill evaluation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvla-adapter\u002Fsub-skills\u002Fevaluation\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fbenchmarks.md","REFERENCE","参考文档",5456,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvla-adapter\u002Fsub-skills\u002Fevaluation\u002Freferences\u002Fbenchmarks.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fevaluation-workflows.md",11307,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvla-adapter\u002Fsub-skills\u002Fevaluation\u002Freferences\u002Fevaluation-workflows.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",6384,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvla-adapter\u002Fsub-skills\u002Fevaluation\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fbuild_eval_command.py","SCRIPT","脚本",9129,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvla-adapter\u002Fsub-skills\u002Fevaluation\u002Fscripts\u002Fbuild_eval_command.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"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.","Apache-2.0","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":71,"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":71,"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":71,"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":71,"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":71,"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",[],[]]