[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M791WFSEAAMKKBX29VT28WP8":3,"skill-same:01M791WFSEAAMKKBX29VT28WP8":70},{"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},"01M791WFSEAAMKKBX29VT28WP8","openff-toolkit",null,"Use OpenFF Toolkit for molecule processing, SMIRNOFF force fields, topology\u002Fsystem preparation, and optional chemistry backend troubleshooting.","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\u002Fopenff-toolkit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: openff-toolkit\ndescription: \"Use OpenFF Toolkit for molecule processing, SMIRNOFF force fields,\n  topology\u002Fsystem preparation, and optional chemistry backend troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# OpenFF Toolkit\n\nUse this repo skill when a task involves the Open Force Field Toolkit (`openff.toolkit`), especially `Molecule`, `Topology`, SMIRNOFF `.offxml` force fields, toolkit wrappers, parameter assignment, molecule\u002Ftopology conversion, conformers, charges, PDB handling, OpenMM\u002FInterchange handoff, or force-field troubleshooting.\n\n## Read First\n\n- `references\u002Fpackage-overview.md` summarizes package purpose, install shape, important concepts, and cross-skill workflow order.\n- `references\u002Ftroubleshooting.md` covers cross-cutting install\u002Fimport, optional dependency, backend, force-field discovery, and workflow routing failures.\n- `references\u002Frepo-provenance.md` records the source snapshot and evidence paths used to create this skill; read it before deciding whether the skill is stale.\n- `scripts\u002Fcheck_openff_toolkit.py --json` checks importability, version, available force fields, core classes, and backend wrapper status in the current Python environment.\n\n## Route by Task\n\n| Task signal | Use this entry point | Why |\n| --- | --- | --- |\n| Build a molecule from SMILES, mapped SMILES, SDF\u002FMOL\u002FSMI\u002FPDB, RDKit\u002FOpenEye objects, conformers, partial charges, stereochemistry, tautomers, SMARTS, visualization, or molecule graph checks | `sub-skills\u002Fmolecules-and-io\u002FSKILL.md` | Focuses on single-molecule API usage and safe IO\u002Fvalidation recipes. |\n| Assemble systems from molecules, load PDB files, handle proteins\u002FHETATM records, manage hierarchy metadata, convert to\u002Ffrom OpenMM\u002FMDTraj, write PDB, add constraints, or prepare topologies for parameterization | `sub-skills\u002Ftopology-and-systems\u002FSKILL.md` | Owns multi-molecule `Topology` workflows and PDB\u002Fbiopolymer assumptions. |\n| Load or edit `.offxml`, discover installed OpenFF force fields, inspect\u002Fmodify SMIRNOFF handlers, label assigned parameters, serialize force fields, create Interchange\u002FOpenMM systems, or troubleshoot SMIRNOFF errors | `sub-skills\u002Fsmirnoff-force-fields\u002FSKILL.md` | Owns `ForceField` and SMIRNOFF parameter workflows. |\n| Choose RDKit\u002FOpenEye\u002FAmberTools\u002FNAGL\u002FBuiltIn wrappers, inspect `GLOBAL_TOOLKIT_REGISTRY`, control registry precedence, diagnose missing optional dependencies, unsupported formats, or charge method failures | `sub-skills\u002Ftoolkit-backends\u002FSKILL.md` | Owns optional backend and registry behavior. |\n\n## Common Workflow Order\n\n1. Check the environment with `scripts\u002Fcheck_openff_toolkit.py --json` if importability, force-field discovery, or optional backend availability is uncertain.\n2. Create or validate `Molecule` objects with `sub-skills\u002Fmolecules-and-io\u002FSKILL.md`.\n3. Build the `Topology` or load a PDB\u002Fsystem with `sub-skills\u002Ftopology-and-systems\u002FSKILL.md`.\n4. Load\u002Fapply\u002Fedit a SMIRNOFF force field with `sub-skills\u002Fsmirnoff-force-fields\u002FSKILL.md`.\n5. Return to `sub-skills\u002Ftoolkit-backends\u002FSKILL.md` when the failure is caused by an unavailable wrapper, unsupported file format, charge method, or registry ordering.\n\n## Installation and Import Baseline\n\nPrefer package-manager installation for normal users because OpenFF Toolkit depends on compiled chemistry\u002Fsimulation packages:\n\n```bash\nmamba create -n openff-toolkit -c conda-forge openff-toolkit\n```\n\nMinimal import check:\n\n```python\nfrom openff.toolkit import ForceField, Molecule, Topology\nfrom openff.toolkit.utils.toolkits import GLOBAL_TOOLKIT_REGISTRY\n\nmolecule = Molecule.from_smiles(\"CCO\")\ntopology = Topology.from_molecules([molecule])\nforce_field = ForceField(\"openff-2.3.0.offxml\")\nprint(molecule.n_atoms, topology.n_molecules, force_field.registered_parameter_handlers)\nprint(GLOBAL_TOOLKIT_REGISTRY.registered_toolkit_versions)\n```\n\nIf `ForceField(\"openff-2.3.0.offxml\")` fails, inspect available force fields and package installation before changing molecule\u002Ftopology code.\n\n## Safe Defaults\n\n- Use Python versions supported by the installed release; this repository snapshot declares Python `>=3.12`.\n- Prefer conda-forge packages for RDKit, AmberTools, OpenMM, Interchange, OpenFF force fields, and OpenFF units.\n- Keep toolkit selection explicit for reproducibility: pass `toolkit_registry=` or a wrapper when behavior must match RDKit, OpenEye, AmberTools, or BuiltIn paths.\n- Treat PDB files as topology\u002Fsystem inputs, not reliable molecule graph sources unless hydrogens, elements, bonds, and unique molecules are known.\n- Treat `.offxml` files as SMIRNOFF force-field sources; preserve originals when troubleshooting version, handler, or parameter errors.\n\n## What Not To Do\n\n- Do not assume OpenEye, AmberTools, or NAGL are available just because `openff.toolkit` imports.\n- Do not use a bare PDB file as the only source of small-molecule bond orders; prepare `unique_molecules` when loading PDB systems.\n- Do not mutate `GLOBAL_TOOLKIT_REGISTRY` globally unless the task explicitly needs process-wide behavior; prefer temporary context managers or explicit arguments.\n- Do not route force-field parameter problems to molecule IO only; use the SMIRNOFF sub-skill once molecules\u002Ftopologies are valid.\n","# OpenFF Toolkit\n\nUse this repo skill when a task involves the Open Force Field Toolkit (`openff.toolkit`), especially `Molecule`, `Topology`, SMIRNOFF `.offxml` force fields, toolkit wrappers, parameter assignment, molecule\u002Ftopology conversion, conformers, charges, PDB handling, OpenMM\u002FInterchange handoff, or force-field troubleshooting.\n\n## Read First\n\n- `references\u002Fpackage-overview.md` summarizes package purpose, install shape, important concepts, and cross-skill workflow order.\n- `references\u002Ftroubleshooting.md` covers cross-cutting install\u002Fimport, optional dependency, backend, force-field discovery, and workflow routing failures.\n- `references\u002Frepo-provenance.md` records the source snapshot and evidence paths used to create this skill; read it before deciding whether the skill is stale.\n- `scripts\u002Fcheck_openff_toolkit.py --json` checks importability, version, available force fields, core classes, and backend wrapper status in the current Python environment.\n\n## Route by Task\n\n| Task signal | Use this entry point | Why |\n| --- | --- | --- |\n| Build a molecule from SMILES, mapped SMILES, SDF\u002FMOL\u002FSMI\u002FPDB, RDKit\u002FOpenEye objects, conformers, partial charges, stereochemistry, tautomers, SMARTS, visualization, or molecule graph checks | `sub-skills\u002Fmolecules-and-io\u002FSKILL.md` | Focuses on single-molecule API usage and safe IO\u002Fvalidation recipes. |\n| Assemble systems from molecules, load PDB files, handle proteins\u002FHETATM records, manage hierarchy metadata, convert to\u002Ffrom OpenMM\u002FMDTraj, write PDB, add constraints, or prepare topologies for parameterization | `sub-skills\u002Ftopology-and-systems\u002FSKILL.md` | Owns multi-molecule `Topology` workflows and PDB\u002Fbiopolymer assumptions. |\n| Load or edit `.offxml`, discover installed OpenFF force fields, inspect\u002Fmodify SMIRNOFF handlers, label assigned parameters, serialize force fields, create Interchange\u002FOpenMM systems, or troubleshoot SMIRNOFF errors | `sub-skills\u002Fsmirnoff-force-fields\u002FSKILL.md` | Owns `ForceField` and SMIRNOFF parameter workflows. |\n| Choose RDKit\u002FOpenEye\u002FAmberTools\u002FNAGL\u002FBuiltIn wrappers, inspect `GLOBAL_TOOLKIT_REGISTRY`, control registry precedence, diagnose missing optional dependencies, unsupported formats, or charge method failures | `sub-skills\u002Ftoolkit-backends\u002FSKILL.md` | Owns optional backend and registry behavior. |\n\n## Common Workflow Order\n\n1. Check the environment with `scripts\u002Fcheck_openff_toolkit.py --json` if importability, force-field discovery, or optional backend availability is uncertain.\n2. Create or validate `Molecule` objects with `sub-skills\u002Fmolecules-and-io\u002FSKILL.md`.\n3. Build the `Topology` or load a PDB\u002Fsystem with `sub-skills\u002Ftopology-and-systems\u002FSKILL.md`.\n4. Load\u002Fapply\u002Fedit a SMIRNOFF force field with `sub-skills\u002Fsmirnoff-force-fields\u002FSKILL.md`.\n5. Return to `sub-skills\u002Ftoolkit-backends\u002FSKILL.md` when the failure is caused by an unavailable wrapper, unsupported file format, charge method, or registry ordering.\n\n## Installation and Import Baseline\n\nPrefer package-manager installation for normal users because OpenFF Toolkit depends on compiled chemistry\u002Fsimulation packages:\n\n```bash\nmamba create -n openff-toolkit -c conda-forge openff-toolkit\n```\n\nMinimal import check:\n\n```python\nfrom openff.toolkit import ForceField, Molecule, Topology\nfrom openff.toolkit.utils.toolkits import GLOBAL_TOOLKIT_REGISTRY\n\nmolecule = Molecule.from_smiles(\"CCO\")\ntopology = Topology.from_molecules([molecule])\nforce_field = ForceField(\"openff-2.3.0.offxml\")\nprint(molecule.n_atoms, topology.n_molecules, force_field.registered_parameter_handlers)\nprint(GLOBAL_TOOLKIT_REGISTRY.registered_toolkit_versions)\n```\n\nIf `ForceField(\"openff-2.3.0.offxml\")` fails, inspect available force fields and package installation before changing molecule\u002Ftopology code.\n\n## Safe Defaults\n\n- Use Python versions supported by the installed release; this repository snapshot declares Python `>=3.12`.\n- Prefer conda-forge packages for RDKit, AmberTools, OpenMM, Interchange, OpenFF force fields, and OpenFF units.\n- Keep toolkit selection explicit for reproducibility: pass `toolkit_registry=` or a wrapper when behavior must match RDKit, OpenEye, AmberTools, or BuiltIn paths.\n- Treat PDB files as topology\u002Fsystem inputs, not reliable molecule graph sources unless hydrogens, elements, bonds, and unique molecules are known.\n- Treat `.offxml` files as SMIRNOFF force-field sources; preserve originals when troubleshooting version, handler, or parameter errors.\n\n## What Not To Do\n\n- Do not assume OpenEye, AmberTools, or NAGL are available just because `openff.toolkit` imports.\n- Do not use a bare PDB file as the only source of small-molecule bond orders; prepare `unique_molecules` when loading PDB systems.\n- Do not mutate `GLOBAL_TOOLKIT_REGISTRY` globally unless the task explicitly needs process-wide behavior; prefer temporary context managers or explicit arguments.\n- Do not route force-field parameter problems to molecule IO only; use the SMIRNOFF sub-skill once molecules\u002Ftopologies are valid.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fopenff-toolkit",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 openff-toolkit",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill openff-toolkit",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill openff-toolkit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenff-toolkit\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fpackage-overview.md","REFERENCE","参考文档",2802,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenff-toolkit\u002Freferences\u002Fpackage-overview.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",2731,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenff-toolkit\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",435,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenff-toolkit\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",3906,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenff-toolkit\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_openff_toolkit.py","SCRIPT","脚本",6527,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenff-toolkit\u002Fscripts\u002Fcheck_openff_toolkit.py",[71,79,86,93,100,107],{"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":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]