[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M791VJSGF92KSS3ZA49BN2QJ":3,"skill-same:01M791VJSGF92KSS3ZA49BN2QJ":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},"01M791VJSGF92KSS3ZA49BN2QJ","openfe",null,"Use OpenFE for alchemical free energy setup, network planning, protocol configuration, CLI execution, and result analysis workflows in molecular simulation campaigns.","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\u002Fopenfe\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: openfe\ndescription: \"Use OpenFE for alchemical free energy setup, network planning,\n  protocol configuration, CLI execution, and result analysis workflows in\n  molecular simulation campaigns.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# OpenFE\n\nUse this repo skill when a task involves OpenFE, Open Free Energy, alchemical free energy calculations, RBFE\u002FRHFE, ABFE\u002FAHFE, SepTop, OpenMM-backed protocol setup, `openfe` CLI workflows, or post-run OpenFE result analysis.\n\nOpenFE is a Python package and CLI for planning and executing alchemical free energy calculations. Keep future-agent work safe by separating planning, protocol configuration, execution commands, and result interpretation.\n\n## Start Here\n\n1. Read [Repository Provenance](references\u002Frepo-provenance.md) before deciding whether this skill matches a current checkout or should be refreshed.\n2. Read [Installation and Environment](references\u002Finstallation-and-environment.md) for public install routes, import checks, Python support, and OpenMM\u002FGPU environment notes.\n3. Run or adapt [check_openfe_environment.py](scripts\u002Fcheck_openfe_environment.py) for a safe local diagnostic that does not run simulations.\n4. Use [Troubleshooting](references\u002Ftroubleshooting.md) for cross-cutting install\u002Fimport\u002FOpenMM\u002FCUDA\u002FJAX\u002Flogging failures.\n5. Route the actual task to one of the sub-skills below.\n\n## Route by Task\n\n- Use [network-planning](sub-skills\u002Fnetwork-planning\u002FSKILL.md) for components, ligand\u002Fprotein\u002Fsolvent inputs, atom mapping, ligand networks, RBFE\u002FRHFE planning, mapper\u002Fscorer choices, and pre-execution data validation.\n- Use [protocols](sub-skills\u002Fprotocols\u002FSKILL.md) for selecting `RelativeHybridTopologyProtocol`, `AbsoluteBindingProtocol`, `AbsoluteSolvationProtocol`, `SepTopProtocol`, or `PlainMDProtocol`; editing settings; understanding `Transformation`, `ProtocolDAG`, `execute_DAG`; and OpenMM backend settings.\n- Use [cli-workflows](sub-skills\u002Fcli-workflows\u002FSKILL.md) for `openfe` command routing, `plan-rbfe-network`, `plan-rhfe-network`, `quickrun`, `charge-molecules`, `fetch`, `test`, repeat-safe command generation, resume behavior, and command-line troubleshooting.\n- Use [results-analysis](sub-skills\u002Fresults-analysis\u002FSKILL.md) for result JSON decoding, `estimate` \u002F `uncertainty`, `ProtocolResult` methods, `gather`, `gather-abfe`, `gather-septop`, repeat folders, TSV interpretation, storage metadata, and partial\u002Ffailed result diagnosis.\n\n## Safe Defaults\n\n- Prefer read-only inspection and command construction before execution. `openfe quickrun`, full planning commands, charge generation, `fetch`, and long tests can create files, download data, or run expensive simulation work.\n- Use API-side planning for interactive or programmatic workflows; use CLI-side planning when the desired output is a directory of transformation JSONs for `quickrun`.\n- Treat OpenFE components, ligand networks, protocols, transformations, and results as provenance-sensitive objects. Rebuild corrected objects rather than mutating existing ones in place.\n- Keep repeat execution paths unique. Reusing the same `quickrun` output file or work directory across repeats risks overwrite or resume-cache confusion.\n- Preserve physical units when reporting free energies and uncertainties.\n\n## Minimal Checks\n\nAfter installing OpenFE in a user environment, start with:\n\n```bash\npython - \u003C\u003C'PY'\nimport openfe, openfecli\nprint(openfe.__version__)\nprint(openfecli.__version__)\nPY\nopenfe --help\n```\n\nFor deeper non-mutating checks, run:\n\n```bash\npython scripts\u002Fcheck_openfe_environment.py --json\n```\n\n## Common Handoffs\n\n- Planning produced transformation JSONs and the user wants to run them: go from [network-planning](sub-skills\u002Fnetwork-planning\u002FSKILL.md) to [cli-workflows](sub-skills\u002Fcli-workflows\u002FSKILL.md).\n- Planning found charged transformations or protocol-repeat concerns: go from [network-planning](sub-skills\u002Fnetwork-planning\u002FSKILL.md) to [protocols](sub-skills\u002Fprotocols\u002FSKILL.md), then back to [cli-workflows](sub-skills\u002Fcli-workflows\u002FSKILL.md) for commands.\n- `quickrun` finished or failed and the user has result files: go from [cli-workflows](sub-skills\u002Fcli-workflows\u002FSKILL.md) to [results-analysis](sub-skills\u002Fresults-analysis\u002FSKILL.md).\n- Gather output looks incomplete: use [results-analysis](sub-skills\u002Fresults-analysis\u002FSKILL.md) first, then route missing-input or failed-execution causes to [cli-workflows](sub-skills\u002Fcli-workflows\u002FSKILL.md) or [protocols](sub-skills\u002Fprotocols\u002FSKILL.md).\n\n## What Not to Do\n\n- Do not run simulations, submit scheduler jobs, download tutorial data, or execute long tests just to answer a planning or diagnostic question.\n- Do not assume a GPU warning means OpenMM simulation is on CPU; distinguish OpenMM platform settings from JAX\u002FPyMBAR analysis warnings.\n- Do not tell users to inspect original repository docs or tests as part of this runtime skill; use the bundled references and scripts here.\n","# OpenFE\n\nUse this repo skill when a task involves OpenFE, Open Free Energy, alchemical free energy calculations, RBFE\u002FRHFE, ABFE\u002FAHFE, SepTop, OpenMM-backed protocol setup, `openfe` CLI workflows, or post-run OpenFE result analysis.\n\nOpenFE is a Python package and CLI for planning and executing alchemical free energy calculations. Keep future-agent work safe by separating planning, protocol configuration, execution commands, and result interpretation.\n\n## Start Here\n\n1. Read [Repository Provenance](references\u002Frepo-provenance.md) before deciding whether this skill matches a current checkout or should be refreshed.\n2. Read [Installation and Environment](references\u002Finstallation-and-environment.md) for public install routes, import checks, Python support, and OpenMM\u002FGPU environment notes.\n3. Run or adapt [check_openfe_environment.py](scripts\u002Fcheck_openfe_environment.py) for a safe local diagnostic that does not run simulations.\n4. Use [Troubleshooting](references\u002Ftroubleshooting.md) for cross-cutting install\u002Fimport\u002FOpenMM\u002FCUDA\u002FJAX\u002Flogging failures.\n5. Route the actual task to one of the sub-skills below.\n\n## Route by Task\n\n- Use [network-planning](sub-skills\u002Fnetwork-planning\u002FSKILL.md) for components, ligand\u002Fprotein\u002Fsolvent inputs, atom mapping, ligand networks, RBFE\u002FRHFE planning, mapper\u002Fscorer choices, and pre-execution data validation.\n- Use [protocols](sub-skills\u002Fprotocols\u002FSKILL.md) for selecting `RelativeHybridTopologyProtocol`, `AbsoluteBindingProtocol`, `AbsoluteSolvationProtocol`, `SepTopProtocol`, or `PlainMDProtocol`; editing settings; understanding `Transformation`, `ProtocolDAG`, `execute_DAG`; and OpenMM backend settings.\n- Use [cli-workflows](sub-skills\u002Fcli-workflows\u002FSKILL.md) for `openfe` command routing, `plan-rbfe-network`, `plan-rhfe-network`, `quickrun`, `charge-molecules`, `fetch`, `test`, repeat-safe command generation, resume behavior, and command-line troubleshooting.\n- Use [results-analysis](sub-skills\u002Fresults-analysis\u002FSKILL.md) for result JSON decoding, `estimate` \u002F `uncertainty`, `ProtocolResult` methods, `gather`, `gather-abfe`, `gather-septop`, repeat folders, TSV interpretation, storage metadata, and partial\u002Ffailed result diagnosis.\n\n## Safe Defaults\n\n- Prefer read-only inspection and command construction before execution. `openfe quickrun`, full planning commands, charge generation, `fetch`, and long tests can create files, download data, or run expensive simulation work.\n- Use API-side planning for interactive or programmatic workflows; use CLI-side planning when the desired output is a directory of transformation JSONs for `quickrun`.\n- Treat OpenFE components, ligand networks, protocols, transformations, and results as provenance-sensitive objects. Rebuild corrected objects rather than mutating existing ones in place.\n- Keep repeat execution paths unique. Reusing the same `quickrun` output file or work directory across repeats risks overwrite or resume-cache confusion.\n- Preserve physical units when reporting free energies and uncertainties.\n\n## Minimal Checks\n\nAfter installing OpenFE in a user environment, start with:\n\n```bash\npython - \u003C\u003C'PY'\nimport openfe, openfecli\nprint(openfe.__version__)\nprint(openfecli.__version__)\nPY\nopenfe --help\n```\n\nFor deeper non-mutating checks, run:\n\n```bash\npython scripts\u002Fcheck_openfe_environment.py --json\n```\n\n## Common Handoffs\n\n- Planning produced transformation JSONs and the user wants to run them: go from [network-planning](sub-skills\u002Fnetwork-planning\u002FSKILL.md) to [cli-workflows](sub-skills\u002Fcli-workflows\u002FSKILL.md).\n- Planning found charged transformations or protocol-repeat concerns: go from [network-planning](sub-skills\u002Fnetwork-planning\u002FSKILL.md) to [protocols](sub-skills\u002Fprotocols\u002FSKILL.md), then back to [cli-workflows](sub-skills\u002Fcli-workflows\u002FSKILL.md) for commands.\n- `quickrun` finished or failed and the user has result files: go from [cli-workflows](sub-skills\u002Fcli-workflows\u002FSKILL.md) to [results-analysis](sub-skills\u002Fresults-analysis\u002FSKILL.md).\n- Gather output looks incomplete: use [results-analysis](sub-skills\u002Fresults-analysis\u002FSKILL.md) first, then route missing-input or failed-execution causes to [cli-workflows](sub-skills\u002Fcli-workflows\u002FSKILL.md) or [protocols](sub-skills\u002Fprotocols\u002FSKILL.md).\n\n## What Not to Do\n\n- Do not run simulations, submit scheduler jobs, download tutorial data, or execute long tests just to answer a planning or diagnostic question.\n- Do not assume a GPU warning means OpenMM simulation is on CPU; distinguish OpenMM platform settings from JAX\u002FPyMBAR analysis warnings.\n- Do not tell users to inspect original repository docs or tests as part of this runtime skill; use the bundled references and scripts here.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fopenfe",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 openfe",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill openfe",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill openfe","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenfe\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Finstallation-and-environment.md","REFERENCE","参考文档",3338,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenfe\u002Freferences\u002Finstallation-and-environment.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",1825,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenfe\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",328,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenfe\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",3696,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenfe\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_openfe_environment.py","SCRIPT","脚本",5268,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopenfe\u002Fscripts\u002Fcheck_openfe_environment.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",[],[]]