[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792NPS6QH6N1ASEEQWME3KF":3,"skill-same:01M792NPS6QH6N1ASEEQWME3KF":62},{"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},"01M792NPS6QH6N1ASEEQWME3KF","core-data-and-geometry",null,"Routes PhiFlow field, geometry, mesh, scene, and data-format workflows.","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\u002Fphi-flow\u002Fsub-skills\u002Fcore-data-and-geometry\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: core-data-and-geometry\ndescription: \"Routes PhiFlow field, geometry, mesh, scene, and data-format workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Core Data and Geometry\n\nUse this sub-skill for the core PhiFlow objects that most other workflows build\non: fields, grids, geometries, meshes, scenes, and field\u002Fscene I\u002FO.\n\n## Route here for\n\n- `CenteredGrid`, `StaggeredGrid`, `PointCloud`, `Noise`, and `AngularVelocity`\n- `Box`, `Sphere`, `Cuboid`, `Cylinder`, `UniformGrid`, `Mesh`, `Graph`,\n  `Heightmap`, `SDFGrid`, and `SDF`\n- `Scene.create()`, `Scene.at()`, `Scene.list()`, `Scene.write()`,\n  `Scene.read()`, and scene cleanup helpers\n- `field.read()`, `field.write()`, `field.resample()`, `field.sample()`, and\n  `field.reduce_sample()`\n- `Geometry` transformations and set operations such as `shift`, `rotate`,\n  `union`, and `intersection`\n- scene \u002F field file formats and legacy compatibility issues\n\n## Do not route here\n\n- installation or backend setup -> `installation-and-backends`\n- PDE stepping, fluids, waves, FLIP, or SPH -> `physics-and-simulation`\n- gradients, Jacobians, or inverse design -> `optimization-and-learning`\n- plotting, display, controls, or scalar logs -> `visualization-and-ui`\n\n## Start with these imports\n\n```python\nfrom phi.flow import *\nfrom phi import field, geom, math\nfrom phiml.math import batch, channel, instance, spatial, vec\n```\n\n## Most common decisions\n\n1. **Grid type:** use `CenteredGrid` for scalar quantities and `StaggeredGrid`\n   for velocity-like vector fields.\n2. **Sampling vs resampling:** use `field.sample()` when you need values at a\n   `Geometry`; use `field.resample()` or `Field.at()` when you need compatible\n   field representations.\n3. **Scene I\u002FO:** use `Scene.create()` for new scenes, `Scene.write()` to store\n   fields, and `Scene.read()` to recover them. The scene format stores `sim_`\n   folders with `*.npz` field files.\n4. **Geometry syntax:** prefer keyword constructors such as `Box(x=1, y=1)` or\n   the explicit slicing form `Box['x,y', 0:1, 0:1]`.\n5. **Mesh \u002F implicit geometry:** use `Mesh` for unstructured surfaces or\n   volumes, and `SDFGrid` \u002F `SDF` when you want implicit shapes.\n6. **Legacy code:** treat `Domain` as compatibility-only. New workflows should\n   construct grids directly with dictionaries and `extrapolation=` or\n   `boundary=` values.\n\n## Verified signatures to rely on\n\n- `Scene.create(parent_directory, shape=(), name='sim', copy_calling_script=True, **dimensions)`\n- `Scene.write(self, data=dict=None, frame=0, **kw_data)`\n- `Scene.read(self, *names, frame=0, convert_to_backend=True)`\n- `field.read(file, convert_to_backend=True)` \u002F `field.write(field, file)`\n- `field.resample(value, to, keep_boundary=False, **kwargs)`\n- `field.sample(field, geometry, at='center', boundary=None, **kwargs)`\n- `field.reduce_sample(field, geometry, **kwargs)`\n- `Box(*args, **kwargs)` and `Box['x,y', ...]`\n- `geom.Box`, `geom.Sphere`, `geom.Cylinder`, `geom.Mesh`, `geom.Graph`,\n  `geom.Heightmap`, `geom.SDFGrid`, and `geom.SDF`\n\n## Bundled references and helper\n\n- Detailed workflows: [`references\u002Fworkflows.md`](references\u002Fworkflows.md)\n- Failure handling: [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md)\n- Scene round-trip smoke: [`scripts\u002Fscene_roundtrip.py`](scripts\u002Fscene_roundtrip.py)\n\nFrom this sub-skill directory, run the smoke helper when you want to verify the\nfield \u002F scene I\u002FO path:\n\n```bash\npython scripts\u002Fscene_roundtrip.py --resolution 16\n```\n\nThe helper writes temporary scene data, reads it back through both the scene\nAPI and `field.read()`, and cleans up afterwards.\n","# Core Data and Geometry\n\nUse this sub-skill for the core PhiFlow objects that most other workflows build\non: fields, grids, geometries, meshes, scenes, and field\u002Fscene I\u002FO.\n\n## Route here for\n\n- `CenteredGrid`, `StaggeredGrid`, `PointCloud`, `Noise`, and `AngularVelocity`\n- `Box`, `Sphere`, `Cuboid`, `Cylinder`, `UniformGrid`, `Mesh`, `Graph`,\n  `Heightmap`, `SDFGrid`, and `SDF`\n- `Scene.create()`, `Scene.at()`, `Scene.list()`, `Scene.write()`,\n  `Scene.read()`, and scene cleanup helpers\n- `field.read()`, `field.write()`, `field.resample()`, `field.sample()`, and\n  `field.reduce_sample()`\n- `Geometry` transformations and set operations such as `shift`, `rotate`,\n  `union`, and `intersection`\n- scene \u002F field file formats and legacy compatibility issues\n\n## Do not route here\n\n- installation or backend setup -> `installation-and-backends`\n- PDE stepping, fluids, waves, FLIP, or SPH -> `physics-and-simulation`\n- gradients, Jacobians, or inverse design -> `optimization-and-learning`\n- plotting, display, controls, or scalar logs -> `visualization-and-ui`\n\n## Start with these imports\n\n```python\nfrom phi.flow import *\nfrom phi import field, geom, math\nfrom phiml.math import batch, channel, instance, spatial, vec\n```\n\n## Most common decisions\n\n1. **Grid type:** use `CenteredGrid` for scalar quantities and `StaggeredGrid`\n   for velocity-like vector fields.\n2. **Sampling vs resampling:** use `field.sample()` when you need values at a\n   `Geometry`; use `field.resample()` or `Field.at()` when you need compatible\n   field representations.\n3. **Scene I\u002FO:** use `Scene.create()` for new scenes, `Scene.write()` to store\n   fields, and `Scene.read()` to recover them. The scene format stores `sim_`\n   folders with `*.npz` field files.\n4. **Geometry syntax:** prefer keyword constructors such as `Box(x=1, y=1)` or\n   the explicit slicing form `Box['x,y', 0:1, 0:1]`.\n5. **Mesh \u002F implicit geometry:** use `Mesh` for unstructured surfaces or\n   volumes, and `SDFGrid` \u002F `SDF` when you want implicit shapes.\n6. **Legacy code:** treat `Domain` as compatibility-only. New workflows should\n   construct grids directly with dictionaries and `extrapolation=` or\n   `boundary=` values.\n\n## Verified signatures to rely on\n\n- `Scene.create(parent_directory, shape=(), name='sim', copy_calling_script=True, **dimensions)`\n- `Scene.write(self, data=dict=None, frame=0, **kw_data)`\n- `Scene.read(self, *names, frame=0, convert_to_backend=True)`\n- `field.read(file, convert_to_backend=True)` \u002F `field.write(field, file)`\n- `field.resample(value, to, keep_boundary=False, **kwargs)`\n- `field.sample(field, geometry, at='center', boundary=None, **kwargs)`\n- `field.reduce_sample(field, geometry, **kwargs)`\n- `Box(*args, **kwargs)` and `Box['x,y', ...]`\n- `geom.Box`, `geom.Sphere`, `geom.Cylinder`, `geom.Mesh`, `geom.Graph`,\n  `geom.Heightmap`, `geom.SDFGrid`, and `geom.SDF`\n\n## Bundled references and helper\n\n- Detailed workflows: [`references\u002Fworkflows.md`](references\u002Fworkflows.md)\n- Failure handling: [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md)\n- Scene round-trip smoke: [`scripts\u002Fscene_roundtrip.py`](scripts\u002Fscene_roundtrip.py)\n\nFrom this sub-skill directory, run the smoke helper when you want to verify the\nfield \u002F scene I\u002FO path:\n\n```bash\npython scripts\u002Fscene_roundtrip.py --resolution 16\n```\n\nThe helper writes temporary scene data, reads it back through both the scene\nAPI and `field.read()`, and cleans up afterwards.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fphi-flow\u002Fsub-skills\u002Fcore-data-and-geometry",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 core-data-and-geometry",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill core-data-and-geometry",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill core-data-and-geometry","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphi-flow\u002Fsub-skills\u002Fcore-data-and-geometry\u002FSKILL.md",[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Ftroubleshooting.md","REFERENCE","参考文档",2223,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphi-flow\u002Fsub-skills\u002Fcore-data-and-geometry\u002Freferences\u002Ftroubleshooting.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fworkflows.md",3562,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphi-flow\u002Fsub-skills\u002Fcore-data-and-geometry\u002Freferences\u002Fworkflows.md",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"scripts\u002Fscene_roundtrip.py","SCRIPT","脚本",2132,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphi-flow\u002Fsub-skills\u002Fcore-data-and-geometry\u002Fscripts\u002Fscene_roundtrip.py",[63,71,78,85,92,99],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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",[],[]]