[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79093HTSYAAMRG8B9M723F3":3,"skill-same:01M79093HTSYAAMRG8B9M723F3":61},{"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},"01M79093HTSYAAMRG8B9M723F3","adversarial-control",null,"AMP, ADD, ASE, and task-conditioned adversarial control workflows.","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\u002Fmimic-kit\u002Fsub-skills\u002Fadversarial-control\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: adversarial-control\ndescription: \"AMP, ADD, ASE, and task-conditioned adversarial control workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# adversarial-control\n\nUse this sub-skill for AMP, ADD, and ASE workflows in MimicKit, plus AMP task-conditioned location and steering routes. If the request is about SMP score-matching priors or prior-based task policies, hand off to the `smp` sub-skill instead.\n\n## What it covers\n- AMP imitation-only controllers and AMP task-mixed controllers.\n- ADD differential discriminator training and control.\n- ASE latent skill routing, encoder rewards, and diversity regularization.\n- Task-conditioned location and steering control built on the AMP family.\n- The task-dodgeball environment shape as a related reference point, with the full policy route handled elsewhere.\n\n## Start here\n1. Pick the route in `references\u002Famp-add-ase-workflows.md`.\n2. Confirm the discriminator, reward, and latent knobs in `references\u002Fdiscriminator-and-latent-configs.md`.\n3. Use `references\u002Ftroubleshooting.md` before changing configs or claiming a blocker.\n4. Keep unresolved simulator, asset, or data gaps explicit.\n\n## Route rules\n- AMP imitation-only: same motion-clip imitation path, no task reward mix.\n- AMP task-conditioned: combine motion imitation with location or steering tasks using the task AMP configs.\n- ADD: use the differential discriminator path; the discriminator learns on target-vs-agent observation differences.\n- ASE: use the latent-conditioned AMP path with encoder reward and diversity loss.\n- Task-dodgeball: use the task env as a reference point only; the full policy route belongs with the SMP sub-skill.\n\n## Do not route here\n- SMP score-matching priors and task-policy training around those priors.\n- DeepMimic, AWR, or LCP motion-imitation workflows.\n- Motion conversion and visualization.\n- Backend install, simulator selection, or low-level engine plumbing.\n\n## Evidence distilled into this skill\nThis sub-skill was distilled from the AMP, ADD, and ASE docs plus the matching env, agent, and config families in a MimicKit checkout. Use the bundled references in this subtree for operational details; do not send future agents back to source-doc reads for routine routing.\n\n## Stable config warning\nIf a change affects `num_disc_obs_steps`, `disc_dof_vel_obs`, or `latent_dim`, assume the saved model and the surrounding config pair may no longer match and re-check the whole route before reusing a checkpoint.\n","# adversarial-control\n\nUse this sub-skill for AMP, ADD, and ASE workflows in MimicKit, plus AMP task-conditioned location and steering routes. If the request is about SMP score-matching priors or prior-based task policies, hand off to the `smp` sub-skill instead.\n\n## What it covers\n- AMP imitation-only controllers and AMP task-mixed controllers.\n- ADD differential discriminator training and control.\n- ASE latent skill routing, encoder rewards, and diversity regularization.\n- Task-conditioned location and steering control built on the AMP family.\n- The task-dodgeball environment shape as a related reference point, with the full policy route handled elsewhere.\n\n## Start here\n1. Pick the route in `references\u002Famp-add-ase-workflows.md`.\n2. Confirm the discriminator, reward, and latent knobs in `references\u002Fdiscriminator-and-latent-configs.md`.\n3. Use `references\u002Ftroubleshooting.md` before changing configs or claiming a blocker.\n4. Keep unresolved simulator, asset, or data gaps explicit.\n\n## Route rules\n- AMP imitation-only: same motion-clip imitation path, no task reward mix.\n- AMP task-conditioned: combine motion imitation with location or steering tasks using the task AMP configs.\n- ADD: use the differential discriminator path; the discriminator learns on target-vs-agent observation differences.\n- ASE: use the latent-conditioned AMP path with encoder reward and diversity loss.\n- Task-dodgeball: use the task env as a reference point only; the full policy route belongs with the SMP sub-skill.\n\n## Do not route here\n- SMP score-matching priors and task-policy training around those priors.\n- DeepMimic, AWR, or LCP motion-imitation workflows.\n- Motion conversion and visualization.\n- Backend install, simulator selection, or low-level engine plumbing.\n\n## Evidence distilled into this skill\nThis sub-skill was distilled from the AMP, ADD, and ASE docs plus the matching env, agent, and config families in a MimicKit checkout. Use the bundled references in this subtree for operational details; do not send future agents back to source-doc reads for routine routing.\n\n## Stable config warning\nIf a change affects `num_disc_obs_steps`, `disc_dof_vel_obs`, or `latent_dim`, assume the saved model and the surrounding config pair may no longer match and re-check the whole route before reusing a checkpoint.\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\u002Fmimic-kit\u002Fsub-skills\u002Fadversarial-control",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 adversarial-control",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill adversarial-control",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill adversarial-control","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmimic-kit\u002Fsub-skills\u002Fadversarial-control\u002FSKILL.md",[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Famp-add-ase-workflows.md","REFERENCE","参考文档",6243,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmimic-kit\u002Fsub-skills\u002Fadversarial-control\u002Freferences\u002Famp-add-ase-workflows.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fdiscriminator-and-latent-configs.md",6445,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmimic-kit\u002Fsub-skills\u002Fadversarial-control\u002Freferences\u002Fdiscriminator-and-latent-configs.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",5888,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmimic-kit\u002Fsub-skills\u002Fadversarial-control\u002Freferences\u002Ftroubleshooting.md",[62,69,76,83,90,97],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":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},"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":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},"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":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},"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":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},"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",[],[]]