[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78SSH1DMEYAVZ7R3ZA74JS1":3,"skill-same:01M78SSH1DMEYAVZ7R3ZA74JS1":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},"01M78SSH1DMEYAVZ7R3ZA74JS1","motion-retargeting",null,"Prepare SMPL and AMASS assets, fit ASAP humanoid shapes and motions, validate robot motion assets, and visualize retargeted motion in MuJoCo.","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\u002Fasap\u002Fsub-skills\u002Fmotion-retargeting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: motion-retargeting\ndescription: \"Prepare SMPL and AMASS assets, fit ASAP humanoid shapes and\n  motions, validate robot motion assets, and visualize retargeted motion in\n  MuJoCo.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# motion-retargeting\n\nUse this sub-skill when an ASAP task is about turning SMPL or AMASS motion into robot motion `.pkl` files, checking robot XML\u002Fmotion config assets, fitting a humanoid shape, retargeting motion, or visualizing retargeted motion with MuJoCo.\n\nRun ASAP retargeting entry points from the repository checkout root. Run bundled validation helpers from the generated ASAP skill root with `--repo-root \u003Casap-checkout>`. If the request is about policy training, checkpoint evaluation, or deployment\u002Fcontrol rather than motion file preparation, route to the sibling skills instead.\n\n## When to use this sub-skill\n\n- Prepare SMPL model files under `humanoidverse\u002Fdata\u002Fsmpl\u002F`.\n- Prepare AMASS-style `.npz` motion files for the ASAP retargeting scripts.\n- Check `robot.motion` config fields, MuJoCo XML, URDF, and mesh layout for a robot such as `g1\u002Fg1_29dof_anneal_23dof`.\n- Run `fit_smpl_shape.py` to create `humanoidverse\u002Fdata\u002Fshape\u002F\u003Chumanoid_type>\u002Fshape_optimized_v1.pkl`.\n- Run `fit_smpl_motion.py` to create per-motion joblib files under `humanoidverse\u002Fdata\u002Fmotions\u002F\u003Chumanoid_type>\u002FTairanTestbed\u002Fsingles\u002F`.\n- Run `vis_q_mj.py` with `+visualize_motion_file=...` to inspect the retargeted motion in MuJoCo.\n\n## Do not use this sub-skill for\n\n- PPO, motion-tracking, locomotion, or delta-action policy training. Use [`..\u002Ftraining-and-evaluation\u002FSKILL.md`](..\u002Ftraining-and-evaluation\u002FSKILL.md).\n- ROS2, Unitree SDK, joystick, ONNX policy runtime, or live robot deployment. Use [`..\u002Fsim2real-deployment\u002FSKILL.md`](..\u002Fsim2real-deployment\u002FSKILL.md).\n- Generic SMPL or AMASS conversion outside the ASAP\u002FHumanoidVerse file layout unless the user explicitly wants to adapt files into ASAP's expected layout.\n\n## Required reading order\n\n1. Read the root ASAP router and install guidance first: [`..\u002F..\u002FSKILL.md`](..\u002F..\u002FSKILL.md) and [`..\u002F..\u002Freferences\u002Finstall-and-backends.md`](..\u002F..\u002Freferences\u002Finstall-and-backends.md).\n2. Read [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for the five-step retargeting flow and exact commands.\n3. Read [`references\u002Fdata-formats.md`](references\u002Fdata-formats.md) before changing file names, joblib keys, or robot config values.\n4. Run the bundled safe checker before expensive fitting:\n\n```bash\npython sub-skills\u002Fmotion-retargeting\u002Fscripts\u002Fvalidate_motion_assets.py \\\n  --repo-root \u003Casap-checkout> \\\n  --robot g1\u002Fg1_29dof_anneal_23dof \\\n  --check-raw\n```\n\n5. If an error occurs, read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md), then the root troubleshooting page [`..\u002F..\u002Freferences\u002Ftroubleshooting.md`](..\u002F..\u002Freferences\u002Ftroubleshooting.md) for shared install, Hydra, and backend issues.\n\n## Fast command map\n\nPreflight current G1 assets and a known retargeted motion file:\n\n```bash\npython sub-skills\u002Fmotion-retargeting\u002Fscripts\u002Fvalidate_motion_assets.py \\\n  --repo-root \u003Casap-checkout> \\\n  --robot g1\u002Fg1_29dof_anneal_23dof \\\n  --motion-file humanoidverse\u002Fdata\u002Fmotions\u002Fg1_29dof_anneal_23dof\u002FTairanTestbed\u002Fsingles\u002F0-motions_raw_tairantestbed_smpl_video_side_jump_level4_filter_amass.pkl \\\n  --check-raw\n```\n\nFit robot shape after SMPL files are present:\n\n```bash\npython scripts\u002Fdata_process\u002Ffit_smpl_shape.py +robot=g1\u002Fg1_29dof_anneal_23dof\n```\n\nFit motions after the shape file and raw `.npz` motion files are present:\n\n```bash\npython scripts\u002Fdata_process\u002Ffit_smpl_motion.py +robot=g1\u002Fg1_29dof_anneal_23dof\n```\n\nVisualize one retargeted output:\n\n```bash\npython scripts\u002Fvis\u002Fvis_q_mj.py \\\n  +robot=g1\u002Fg1_29dof_anneal_23dof \\\n  +visualize_motion_file=\"humanoidverse\u002Fdata\u002Fmotions\u002Fg1_29dof_anneal_23dof\u002FTairanTestbed\u002Fsingles\u002F0-motions_raw_tairantestbed_smpl_video_side_jump_level4_filter_amass.pkl\"\n```\n\n## Dependency and asset gates\n\n- The fitting scripts require the normal ASAP Python dependencies plus external `smpl_sim`. ASAP's package metadata includes `hydra-core`, `lxml`, `joblib`, `numpy-stl`, `open3d`, and other scientific dependencies, but `smpl_sim` is a separate required dependency for shape and motion fitting.\n- `fit_smpl_shape.py` and `fit_smpl_motion.py` import `smpl_sim.smpllib.smpl_parser`, `smpl_sim.smpllib.smpl_joint_names`, and, for motion fitting, `smpl_sim.utils.smoothing_utils`.\n- The bundled checker intentionally avoids importing ASAP or `smpl_sim`; it validates file layout and joblib structure without running optimization.\n\n## Expected outputs\n\n- Shape fit output: `humanoidverse\u002Fdata\u002Fshape\u002Fg1_29dof_anneal_23dof\u002Fshape_optimized_v1.pkl`.\n- Retargeted single-motion outputs: `humanoidverse\u002Fdata\u002Fmotions\u002Fg1_29dof_anneal_23dof\u002FTairanTestbed\u002Fsingles\u002F\u003Cmotion-key>.pkl`.\n- A retargeted `.pkl` is a joblib-loaded dictionary. For directory-mode consumers, each file's top-level key should match the file stem. See [`references\u002Fdata-formats.md`](references\u002Fdata-formats.md).\n\n## Cross-links\n\n- Root ASAP skill: [`..\u002F..\u002FSKILL.md`](..\u002F..\u002FSKILL.md).\n- Root install and backend notes: [`..\u002F..\u002Freferences\u002Finstall-and-backends.md`](..\u002F..\u002Freferences\u002Finstall-and-backends.md).\n- Root troubleshooting: [`..\u002F..\u002Freferences\u002Ftroubleshooting.md`](..\u002F..\u002Freferences\u002Ftroubleshooting.md).\n- Training and evaluation: [`..\u002Ftraining-and-evaluation\u002FSKILL.md`](..\u002Ftraining-and-evaluation\u002FSKILL.md) for consuming generated motion files in policy training.\n- Sim2real deployment: [`..\u002Fsim2real-deployment\u002FSKILL.md`](..\u002Fsim2real-deployment\u002FSKILL.md) for MuJoCo\u002FROS2\u002FUnitree runtime control after a policy exists.\n","# motion-retargeting\n\nUse this sub-skill when an ASAP task is about turning SMPL or AMASS motion into robot motion `.pkl` files, checking robot XML\u002Fmotion config assets, fitting a humanoid shape, retargeting motion, or visualizing retargeted motion with MuJoCo.\n\nRun ASAP retargeting entry points from the repository checkout root. Run bundled validation helpers from the generated ASAP skill root with `--repo-root \u003Casap-checkout>`. If the request is about policy training, checkpoint evaluation, or deployment\u002Fcontrol rather than motion file preparation, route to the sibling skills instead.\n\n## When to use this sub-skill\n\n- Prepare SMPL model files under `humanoidverse\u002Fdata\u002Fsmpl\u002F`.\n- Prepare AMASS-style `.npz` motion files for the ASAP retargeting scripts.\n- Check `robot.motion` config fields, MuJoCo XML, URDF, and mesh layout for a robot such as `g1\u002Fg1_29dof_anneal_23dof`.\n- Run `fit_smpl_shape.py` to create `humanoidverse\u002Fdata\u002Fshape\u002F\u003Chumanoid_type>\u002Fshape_optimized_v1.pkl`.\n- Run `fit_smpl_motion.py` to create per-motion joblib files under `humanoidverse\u002Fdata\u002Fmotions\u002F\u003Chumanoid_type>\u002FTairanTestbed\u002Fsingles\u002F`.\n- Run `vis_q_mj.py` with `+visualize_motion_file=...` to inspect the retargeted motion in MuJoCo.\n\n## Do not use this sub-skill for\n\n- PPO, motion-tracking, locomotion, or delta-action policy training. Use [`..\u002Ftraining-and-evaluation\u002FSKILL.md`](..\u002Ftraining-and-evaluation\u002FSKILL.md).\n- ROS2, Unitree SDK, joystick, ONNX policy runtime, or live robot deployment. Use [`..\u002Fsim2real-deployment\u002FSKILL.md`](..\u002Fsim2real-deployment\u002FSKILL.md).\n- Generic SMPL or AMASS conversion outside the ASAP\u002FHumanoidVerse file layout unless the user explicitly wants to adapt files into ASAP's expected layout.\n\n## Required reading order\n\n1. Read the root ASAP router and install guidance first: [`..\u002F..\u002FSKILL.md`](..\u002F..\u002FSKILL.md) and [`..\u002F..\u002Freferences\u002Finstall-and-backends.md`](..\u002F..\u002Freferences\u002Finstall-and-backends.md).\n2. Read [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for the five-step retargeting flow and exact commands.\n3. Read [`references\u002Fdata-formats.md`](references\u002Fdata-formats.md) before changing file names, joblib keys, or robot config values.\n4. Run the bundled safe checker before expensive fitting:\n\n```bash\npython sub-skills\u002Fmotion-retargeting\u002Fscripts\u002Fvalidate_motion_assets.py \\\n  --repo-root \u003Casap-checkout> \\\n  --robot g1\u002Fg1_29dof_anneal_23dof \\\n  --check-raw\n```\n\n5. If an error occurs, read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md), then the root troubleshooting page [`..\u002F..\u002Freferences\u002Ftroubleshooting.md`](..\u002F..\u002Freferences\u002Ftroubleshooting.md) for shared install, Hydra, and backend issues.\n\n## Fast command map\n\nPreflight current G1 assets and a known retargeted motion file:\n\n```bash\npython sub-skills\u002Fmotion-retargeting\u002Fscripts\u002Fvalidate_motion_assets.py \\\n  --repo-root \u003Casap-checkout> \\\n  --robot g1\u002Fg1_29dof_anneal_23dof \\\n  --motion-file humanoidverse\u002Fdata\u002Fmotions\u002Fg1_29dof_anneal_23dof\u002FTairanTestbed\u002Fsingles\u002F0-motions_raw_tairantestbed_smpl_video_side_jump_level4_filter_amass.pkl \\\n  --check-raw\n```\n\nFit robot shape after SMPL files are present:\n\n```bash\npython scripts\u002Fdata_process\u002Ffit_smpl_shape.py +robot=g1\u002Fg1_29dof_anneal_23dof\n```\n\nFit motions after the shape file and raw `.npz` motion files are present:\n\n```bash\npython scripts\u002Fdata_process\u002Ffit_smpl_motion.py +robot=g1\u002Fg1_29dof_anneal_23dof\n```\n\nVisualize one retargeted output:\n\n```bash\npython scripts\u002Fvis\u002Fvis_q_mj.py \\\n  +robot=g1\u002Fg1_29dof_anneal_23dof \\\n  +visualize_motion_file=\"humanoidverse\u002Fdata\u002Fmotions\u002Fg1_29dof_anneal_23dof\u002FTairanTestbed\u002Fsingles\u002F0-motions_raw_tairantestbed_smpl_video_side_jump_level4_filter_amass.pkl\"\n```\n\n## Dependency and asset gates\n\n- The fitting scripts require the normal ASAP Python dependencies plus external `smpl_sim`. ASAP's package metadata includes `hydra-core`, `lxml`, `joblib`, `numpy-stl`, `open3d`, and other scientific dependencies, but `smpl_sim` is a separate required dependency for shape and motion fitting.\n- `fit_smpl_shape.py` and `fit_smpl_motion.py` import `smpl_sim.smpllib.smpl_parser`, `smpl_sim.smpllib.smpl_joint_names`, and, for motion fitting, `smpl_sim.utils.smoothing_utils`.\n- The bundled checker intentionally avoids importing ASAP or `smpl_sim`; it validates file layout and joblib structure without running optimization.\n\n## Expected outputs\n\n- Shape fit output: `humanoidverse\u002Fdata\u002Fshape\u002Fg1_29dof_anneal_23dof\u002Fshape_optimized_v1.pkl`.\n- Retargeted single-motion outputs: `humanoidverse\u002Fdata\u002Fmotions\u002Fg1_29dof_anneal_23dof\u002FTairanTestbed\u002Fsingles\u002F\u003Cmotion-key>.pkl`.\n- A retargeted `.pkl` is a joblib-loaded dictionary. For directory-mode consumers, each file's top-level key should match the file stem. See [`references\u002Fdata-formats.md`](references\u002Fdata-formats.md).\n\n## Cross-links\n\n- Root ASAP skill: [`..\u002F..\u002FSKILL.md`](..\u002F..\u002FSKILL.md).\n- Root install and backend notes: [`..\u002F..\u002Freferences\u002Finstall-and-backends.md`](..\u002F..\u002Freferences\u002Finstall-and-backends.md).\n- Root troubleshooting: [`..\u002F..\u002Freferences\u002Ftroubleshooting.md`](..\u002F..\u002Freferences\u002Ftroubleshooting.md).\n- Training and evaluation: [`..\u002Ftraining-and-evaluation\u002FSKILL.md`](..\u002Ftraining-and-evaluation\u002FSKILL.md) for consuming generated motion files in policy training.\n- Sim2real deployment: [`..\u002Fsim2real-deployment\u002FSKILL.md`](..\u002Fsim2real-deployment\u002FSKILL.md) for MuJoCo\u002FROS2\u002FUnitree runtime control after a policy exists.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fasap\u002Fsub-skills\u002Fmotion-retargeting",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 motion-retargeting",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill motion-retargeting",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill motion-retargeting","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fasap\u002Fsub-skills\u002Fmotion-retargeting\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdata-formats.md","REFERENCE","参考文档",9116,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fasap\u002Fsub-skills\u002Fmotion-retargeting\u002Freferences\u002Fdata-formats.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",9273,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fasap\u002Fsub-skills\u002Fmotion-retargeting\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",7363,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fasap\u002Fsub-skills\u002Fmotion-retargeting\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fvalidate_motion_assets.py","SCRIPT","脚本",23597,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fasap\u002Fsub-skills\u002Fmotion-retargeting\u002Fscripts\u002Fvalidate_motion_assets.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",[],[]]