[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7918BPADDTF1R3FGMAWBDF2":3,"skill-same:01M7918BPADDTF1R3FGMAWBDF2":67},{"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},"01M7918BPADDTF1R3FGMAWBDF2","modeling-simulation",null,"Build, step, and debug core Newton simulation models, states, controls, contacts, worlds, shapes, joints, and public loop patterns.","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\u002Fnewton\u002Fsub-skills\u002Fmodeling-simulation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: modeling-simulation\ndescription: \"Build, step, and debug core Newton simulation models, states,\n  controls, contacts, worlds, shapes, joints, and public loop patterns.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Newton modeling and simulation\n\nUse this sub-skill when the task is to create or debug a Newton model, state, control, shape, joint, articulation, world replication, collision-pipeline allocation, or a minimal simulation loop with public APIs.\n\n## Route here for\n\n- `newton.ModelBuilder`, `newton.Model`, `newton.State`, `newton.Control`, and `newton.Contacts` usage.\n- Choosing `add_body()` versus `add_link()` and connecting links with joints\u002Farticulations.\n- Adding primitive, mesh, heightfield, SDF, or site geometry through public builder methods.\n- Static, kinematic, and dynamic body setup.\n- Forward\u002Finverse kinematics helper calls such as `newton.eval_fk()` and `newton.eval_ik()`.\n- Allocating `CollisionPipeline`, contacts, state buffers, and control buffers.\n- Replicating worlds with `ModelBuilder.replicate()` and reasoning about `world_count`.\n- CPU\u002FCUDA device selection through Warp for small smoke checks.\n- Fixing no-contact or stale-state issues in a basic loop.\n\n## Route elsewhere\n\n- Solver choice, MuJoCo\u002FKamino\u002FVBD\u002FMPM\u002Fcoupled solver behavior, or contact tuning: use `..\u002Fsolvers-contacts\u002FSKILL.md`.\n- URDF, MJCF, USD, mesh file import, schema resolvers, or asset conversion: use `..\u002Fasset-import-export\u002FSKILL.md`.\n- Actuators, controller objects, IK objective workflows, and `ArticulationView`: use `..\u002Frobotics-control\u002FSKILL.md`.\n- Sensors, viewers, example CLI, recording, and visualization: use `..\u002Fsensors-visualization\u002FSKILL.md`.\n\n## Read order\n\n1. `references\u002Fapi-reference.md` for verified public constructors and core method signatures.\n2. `references\u002Fworkflows.md` for minimal loops, world replication, body\u002Fjoint patterns, and validation order.\n3. `references\u002Ftroubleshooting.md` for import\u002Fdevice, stale FK, target-layout, contact-capacity, and validation failures.\n4. `scripts\u002Fbuild_minimal_scene.py` when you need a safe, runnable public-API smoke test.\n\n## Core loop checklist\n\n1. Set global compatibility switches, such as `newton.use_coord_layout_targets = True`, before constructing a `ModelBuilder` when joint position targets are involved.\n2. Build or replicate the model with public `ModelBuilder` methods.\n3. Finalize the builder into a `Model`, optionally passing a Warp device string.\n4. Allocate two `State` buffers, one `Control`, one `CollisionPipeline`, and a `Contacts` buffer from the pipeline.\n5. Call `newton.eval_fk(model, model.joint_q, model.joint_qd, state)` before maximal-coordinate solvers or collision checks when generalized coordinates define the initial pose.\n6. Per substep: clear forces, collide, solver-step, then swap state buffers.\n7. Validate counts and array shapes before tuning physics.\n\n## Minimal safe smoke\n\nFrom this sub-skill directory, run:\n\n```bash\npython scripts\u002Fbuild_minimal_scene.py --device cpu --steps 3\n```\n\nUse `--device cuda:0` only after the root `scripts\u002Fcheck_newton_env.py --require-cuda` succeeds. The script prints body\u002Fshape\u002Fjoint counts and the final `body_q` shape; it does not download assets or open a viewer.\n\n## Operating rules\n\n- Use public imports only: `import newton`, `import newton.geometry`, and `import warp as wp`.\n- Do not teach future users to import from `newton._src`; private modules are implementation evidence, not runtime API.\n- Prefer small checks on CPU first, then repeat on CUDA only when the task requires acceleration.\n- Treat `ModelBuilder.finalize()` validation warnings as actionable evidence; do not hide them by using broad `skip_validation_*` flags unless the task explicitly asks for advanced recovery.\n- Keep model construction and solver tuning separate: prove the scene has the expected bodies, joints, shapes, worlds, and contacts before changing solver parameters.\n","# Newton modeling and simulation\n\nUse this sub-skill when the task is to create or debug a Newton model, state, control, shape, joint, articulation, world replication, collision-pipeline allocation, or a minimal simulation loop with public APIs.\n\n## Route here for\n\n- `newton.ModelBuilder`, `newton.Model`, `newton.State`, `newton.Control`, and `newton.Contacts` usage.\n- Choosing `add_body()` versus `add_link()` and connecting links with joints\u002Farticulations.\n- Adding primitive, mesh, heightfield, SDF, or site geometry through public builder methods.\n- Static, kinematic, and dynamic body setup.\n- Forward\u002Finverse kinematics helper calls such as `newton.eval_fk()` and `newton.eval_ik()`.\n- Allocating `CollisionPipeline`, contacts, state buffers, and control buffers.\n- Replicating worlds with `ModelBuilder.replicate()` and reasoning about `world_count`.\n- CPU\u002FCUDA device selection through Warp for small smoke checks.\n- Fixing no-contact or stale-state issues in a basic loop.\n\n## Route elsewhere\n\n- Solver choice, MuJoCo\u002FKamino\u002FVBD\u002FMPM\u002Fcoupled solver behavior, or contact tuning: use `..\u002Fsolvers-contacts\u002FSKILL.md`.\n- URDF, MJCF, USD, mesh file import, schema resolvers, or asset conversion: use `..\u002Fasset-import-export\u002FSKILL.md`.\n- Actuators, controller objects, IK objective workflows, and `ArticulationView`: use `..\u002Frobotics-control\u002FSKILL.md`.\n- Sensors, viewers, example CLI, recording, and visualization: use `..\u002Fsensors-visualization\u002FSKILL.md`.\n\n## Read order\n\n1. `references\u002Fapi-reference.md` for verified public constructors and core method signatures.\n2. `references\u002Fworkflows.md` for minimal loops, world replication, body\u002Fjoint patterns, and validation order.\n3. `references\u002Ftroubleshooting.md` for import\u002Fdevice, stale FK, target-layout, contact-capacity, and validation failures.\n4. `scripts\u002Fbuild_minimal_scene.py` when you need a safe, runnable public-API smoke test.\n\n## Core loop checklist\n\n1. Set global compatibility switches, such as `newton.use_coord_layout_targets = True`, before constructing a `ModelBuilder` when joint position targets are involved.\n2. Build or replicate the model with public `ModelBuilder` methods.\n3. Finalize the builder into a `Model`, optionally passing a Warp device string.\n4. Allocate two `State` buffers, one `Control`, one `CollisionPipeline`, and a `Contacts` buffer from the pipeline.\n5. Call `newton.eval_fk(model, model.joint_q, model.joint_qd, state)` before maximal-coordinate solvers or collision checks when generalized coordinates define the initial pose.\n6. Per substep: clear forces, collide, solver-step, then swap state buffers.\n7. Validate counts and array shapes before tuning physics.\n\n## Minimal safe smoke\n\nFrom this sub-skill directory, run:\n\n```bash\npython scripts\u002Fbuild_minimal_scene.py --device cpu --steps 3\n```\n\nUse `--device cuda:0` only after the root `scripts\u002Fcheck_newton_env.py --require-cuda` succeeds. The script prints body\u002Fshape\u002Fjoint counts and the final `body_q` shape; it does not download assets or open a viewer.\n\n## Operating rules\n\n- Use public imports only: `import newton`, `import newton.geometry`, and `import warp as wp`.\n- Do not teach future users to import from `newton._src`; private modules are implementation evidence, not runtime API.\n- Prefer small checks on CPU first, then repeat on CUDA only when the task requires acceleration.\n- Treat `ModelBuilder.finalize()` validation warnings as actionable evidence; do not hide them by using broad `skip_validation_*` flags unless the task explicitly asks for advanced recovery.\n- Keep model construction and solver tuning separate: prove the scene has the expected bodies, joints, shapes, worlds, and contacts before changing solver parameters.\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\u002Fnewton\u002Fsub-skills\u002Fmodeling-simulation",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 modeling-simulation",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill modeling-simulation",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill modeling-simulation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnewton\u002Fsub-skills\u002Fmodeling-simulation\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",5182,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnewton\u002Fsub-skills\u002Fmodeling-simulation\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",2800,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnewton\u002Fsub-skills\u002Fmodeling-simulation\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",3850,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnewton\u002Fsub-skills\u002Fmodeling-simulation\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fbuild_minimal_scene.py","SCRIPT","脚本",2607,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnewton\u002Fsub-skills\u002Fmodeling-simulation\u002Fscripts\u002Fbuild_minimal_scene.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]