[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78ZX8EEA2YZWNF92EEZ4MBV":3,"skill-same:01M78ZX8EEA2YZWNF92EEZ4MBV":74},{"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},"01M78ZX8EEA2YZWNF92EEZ4MBV","mattergen",null,"Guide MatterGen inorganic-crystal generation, structure evaluation, dataset preparation, Hydra training, and property fine-tuning with CUDA-aware validation and safe artifact handling.","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\u002Fmattergen\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: mattergen\ndescription: \"Guide MatterGen inorganic-crystal generation, structure\n  evaluation, dataset preparation, Hydra training, and property fine-tuning with\n  CUDA-aware validation and safe artifact handling.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# MatterGen\n\nMatterGen is a generative model for inorganic materials design. Use this root\nroute to choose the smallest workflow-specific guide before running commands.\nThe generated skill is self-contained: it describes package contracts and\nbundles safe preflight helpers, but it does not download checkpoints, datasets,\nMatterSim potentials, or start expensive jobs implicitly.\n\n## First route the request\n\n- **Generate crystal structures** — read\n  [generation](sub-skills\u002Fgeneration\u002FSKILL.md). This covers named or local\n  checkpoints, unconditional\u002Fproperty\u002Fmulti-property sampling, CSP target\n  compositions, guidance, sampling overrides, and output files.\n- **Score or relax structures** — read\n  [evaluation](sub-skills\u002Fevaluation\u002FSKILL.md). This covers MatterSim relaxation,\n  precomputed-energy evaluation, matching, compatible references, correction\n  schemes, and metrics.\n- **Prepare or validate data** — read\n  [data-preparation](sub-skills\u002Fdata-preparation\u002FSKILL.md). This covers MP-20 and\n  Alex-MP-20 layout, CSV schema, cache splits, custom properties, and storage\n  preflight.\n- **Train or fine-tune** — read\n  [training-finetuning](sub-skills\u002Ftraining-finetuning\u002FSKILL.md). This covers\n  Hydra base\u002FCSP training, adapters, multi-property wiring, custom embeddings,\n  resource controls, and no-launch validation.\n\nFor a request that spans routes, prepare data first, train\u002Ffine-tune second,\ngenerate third, and evaluate last. Keep each stage's inputs, resolved config,\ncheckpoint identity, data\u002Freference version, device, and output directory in an\nexternal experiment record.\n\n## Install and smoke-check\n\nMatterGen requires Python 3.10+; the repository's documented Linux path uses a\nCUDA-capable PyTorch stack. Install the package using its supported distribution\nor editable source checkout, then run the bundled environment check:\n\n```bash\npython -m pip install -e \u003Cmattergen-source>\npython \u003Cmattergen-skill-root>\u002Fscripts\u002Fcheck_environment.py\n```\n\nThe source distribution pins a Linux CUDA family around PyTorch 2.2.1 + cu118\nand matching PyG extensions. Respect the package's platform-specific install\ninstructions rather than mixing CPU\u002FCUDA\u002FROCm wheels. Apple Silicon is\nexperimental and requires `PYTORCH_ENABLE_MPS_FALLBACK=1` for documented MPS\nruns. Read [installation and assets](references\u002Finstallation-and-assets.md)\nwhen deciding package variants, checkpoints, Git LFS, Hugging Face access, or\nlarge data acquisition.\n\nThe helper checks package metadata\u002Fimports and reports CUDA\u002FMPS availability;\nit does not install packages, contact external services, or launch a model.\nRead [API and CLI overview](references\u002Fapi-and-cli-overview.md) for the five\nconsole entry points and the verified public Python objects.\n\n## Operational guardrails\n\n1. Treat checkpoint, dataset, reference, and potential files as explicit\n   inputs. An LFS pointer is not a hydrated model or archive.\n2. Preflight arguments, paths, schemas, and backend availability before any\n   large job. Use the nearest bundled helper; dry-run is the default where\n   offered.\n3. Keep generation\u002Fevaluation on a visible CUDA device when the workflow needs\n   the GPU. CPU checks validate imports and lightweight behavior, not full\n   generation throughput or MatterSim relaxation.\n4. Use a new output directory for retries. Preserve resolved configs and\n   partial artifacts rather than silently overwriting them.\n5. Do not compare MP2020 and TRI2024 evaluation results as if they used the\n   same hull\u002Freference convention; do not treat MatterSim predictions as DFT.\n6. Before publication or scientific claims, record data\u002Flicense provenance,\n   conditioning\u002Fcheckpoint identity, random seeds, sampling settings, device,\n   and whether metrics came from MatterSim or DFT.\n\nFor cross-cutting install, import, backend, asset, and artifact failures, read\n[troubleshooting](references\u002Ftroubleshooting.md). For source-version checks or\nrefresh decisions, read [repository provenance](references\u002Frepo-provenance.md).\n","# MatterGen\n\nMatterGen is a generative model for inorganic materials design. Use this root\nroute to choose the smallest workflow-specific guide before running commands.\nThe generated skill is self-contained: it describes package contracts and\nbundles safe preflight helpers, but it does not download checkpoints, datasets,\nMatterSim potentials, or start expensive jobs implicitly.\n\n## First route the request\n\n- **Generate crystal structures** — read\n  [generation](sub-skills\u002Fgeneration\u002FSKILL.md). This covers named or local\n  checkpoints, unconditional\u002Fproperty\u002Fmulti-property sampling, CSP target\n  compositions, guidance, sampling overrides, and output files.\n- **Score or relax structures** — read\n  [evaluation](sub-skills\u002Fevaluation\u002FSKILL.md). This covers MatterSim relaxation,\n  precomputed-energy evaluation, matching, compatible references, correction\n  schemes, and metrics.\n- **Prepare or validate data** — read\n  [data-preparation](sub-skills\u002Fdata-preparation\u002FSKILL.md). This covers MP-20 and\n  Alex-MP-20 layout, CSV schema, cache splits, custom properties, and storage\n  preflight.\n- **Train or fine-tune** — read\n  [training-finetuning](sub-skills\u002Ftraining-finetuning\u002FSKILL.md). This covers\n  Hydra base\u002FCSP training, adapters, multi-property wiring, custom embeddings,\n  resource controls, and no-launch validation.\n\nFor a request that spans routes, prepare data first, train\u002Ffine-tune second,\ngenerate third, and evaluate last. Keep each stage's inputs, resolved config,\ncheckpoint identity, data\u002Freference version, device, and output directory in an\nexternal experiment record.\n\n## Install and smoke-check\n\nMatterGen requires Python 3.10+; the repository's documented Linux path uses a\nCUDA-capable PyTorch stack. Install the package using its supported distribution\nor editable source checkout, then run the bundled environment check:\n\n```bash\npython -m pip install -e \u003Cmattergen-source>\npython \u003Cmattergen-skill-root>\u002Fscripts\u002Fcheck_environment.py\n```\n\nThe source distribution pins a Linux CUDA family around PyTorch 2.2.1 + cu118\nand matching PyG extensions. Respect the package's platform-specific install\ninstructions rather than mixing CPU\u002FCUDA\u002FROCm wheels. Apple Silicon is\nexperimental and requires `PYTORCH_ENABLE_MPS_FALLBACK=1` for documented MPS\nruns. Read [installation and assets](references\u002Finstallation-and-assets.md)\nwhen deciding package variants, checkpoints, Git LFS, Hugging Face access, or\nlarge data acquisition.\n\nThe helper checks package metadata\u002Fimports and reports CUDA\u002FMPS availability;\nit does not install packages, contact external services, or launch a model.\nRead [API and CLI overview](references\u002Fapi-and-cli-overview.md) for the five\nconsole entry points and the verified public Python objects.\n\n## Operational guardrails\n\n1. Treat checkpoint, dataset, reference, and potential files as explicit\n   inputs. An LFS pointer is not a hydrated model or archive.\n2. Preflight arguments, paths, schemas, and backend availability before any\n   large job. Use the nearest bundled helper; dry-run is the default where\n   offered.\n3. Keep generation\u002Fevaluation on a visible CUDA device when the workflow needs\n   the GPU. CPU checks validate imports and lightweight behavior, not full\n   generation throughput or MatterSim relaxation.\n4. Use a new output directory for retries. Preserve resolved configs and\n   partial artifacts rather than silently overwriting them.\n5. Do not compare MP2020 and TRI2024 evaluation results as if they used the\n   same hull\u002Freference convention; do not treat MatterSim predictions as DFT.\n6. Before publication or scientific claims, record data\u002Flicense provenance,\n   conditioning\u002Fcheckpoint identity, random seeds, sampling settings, device,\n   and whether metrics came from MatterSim or DFT.\n\nFor cross-cutting install, import, backend, asset, and artifact failures, read\n[troubleshooting](references\u002Ftroubleshooting.md). For source-version checks or\nrefresh decisions, read [repository provenance](references\u002Frepo-provenance.md).\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fmattergen",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 mattergen",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill mattergen",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill mattergen","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmattergen\u002FSKILL.md",[46,52,56,60,64,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-and-cli-overview.md","REFERENCE","参考文档",2362,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmattergen\u002Freferences\u002Fapi-and-cli-overview.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Finstallation-and-assets.md",3166,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmattergen\u002Freferences\u002Finstallation-and-assets.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-provenance.md",2013,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmattergen\u002Freferences\u002Frepo-provenance.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Frepo-routing-metadata.json",330,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmattergen\u002Freferences\u002Frepo-routing-metadata.json",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftroubleshooting.md",4416,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmattergen\u002Freferences\u002Ftroubleshooting.md",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fcheck_environment.py","SCRIPT","脚本",4131,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmattergen\u002Fscripts\u002Fcheck_environment.py",[75,83,90,97,104,111],{"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":79,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]