[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79479SWGGYB2ABWWY6PA6K1":3,"skill-same:01M79479SWGGYB2ABWWY6PA6K1":71},{"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},"01M79479SWGGYB2ABWWY6PA6K1","scoring",null,"Build and troubleshoot REINVENT4 scoring configurations, components, transforms, aggregation, and scoring plugins.","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\u002Freinvent4\u002Fsub-skills\u002Fscoring\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: scoring\ndescription: \"Build and troubleshoot REINVENT4 scoring configurations,\n  components, transforms, aggregation, and scoring plugins.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Scoring\n\nUse this sub-skill when a task mentions `scoring.toml`, `run_type = \"scoring\"`, scoring components, transforms, aggregation, `comp_*` plugin files, `@add_tag`, `QED`, `MolecularWeight`, `TanimotoSimilarity`, `TanimotoDistance`, OpenEye ROCS, Chemprop, `ExternalProcess`, or REST scoring.\n\n## Scope\n\nThis skill covers scoring-only jobs and scoring-function design that will later be reused by staged learning. For model sampling setup, use the sibling sampling skill. For transfer-learning or staged-learning orchestration, use the learning skill and return here only for `[scoring]` or `[stage.scoring]` blocks. For SMILES preprocessing, use the data-pipeline skill.\n\n## Start Here\n\n1. Use `run_type = \"scoring\"` for a standalone scoring run and provide a `[parameters]` block with `smiles_file` and optional `output_csv`.\n2. Build a `[scoring]` block with `type = \"geometric_mean\"` or `type = \"arithmetic_mean\"`, optional `parallel`, optional `use_pumas`, and one or more `[[scoring.component]]` blocks.\n3. Keep each component block in this shape: `[[scoring.component]]`, `[scoring.component.ComponentName]`, then one or more `[[scoring.component.ComponentName.endpoint]]` tables with `name`, optional `weight`, optional `params.*`, and optional `transform.*`.\n4. Prefer a scoring-only run on representative SMILES before using the same scoring function in RL.\n\n## References\n\n- `references\u002Fcomponents-and-plugins.md`: component block shapes, common built-ins, external components, and custom plugin discovery.\n- `references\u002Ftransforms-and-aggregation.md`: transform choice, endpoint weights, geometric\u002Farithmetic aggregation, filters, and penalties.\n- `references\u002Ftroubleshooting.md`: config parsing, plugin import, optional dependency, external service, and transform-debugging failures.\n\n## Bundled Helpers\n\n- `scripts\u002Fvalidate_scoring_config.py`: parse a TOML scoring config and summarize scoring blocks, components, endpoints, params, transforms, and likely structural issues without running scoring.\n- `scripts\u002Flist_scoring_components.py`: inspect installed `reinvent_plugins.components` namespace packages and list discovered `comp_*` modules\u002Fclasses without executing a scoring job.\n\nRun each helper with `--help` first. Both helpers are read-only; they inspect installed Python packages and config files but do not launch `reinvent`, score molecules, call external services, or load model checkpoints intentionally.\n\n## Practical Defaults\n\n- Use `QED` without a transform because it already returns a 0-1 value.\n- Use `MolecularWeight` with `double_sigmoid` for a preferred mass window such as 200-500 Da.\n- Use `TanimotoSimilarity` for new configs; treat `TanimotoDistance` as a backward-compatible deprecated alias.\n- Use `custom_alerts` for must-fail SMARTS filters and do not rely on its `weight` for optimization.\n- Use `geometric_mean` when every objective must remain acceptable; use `arithmetic_mean` when compensation between objectives is acceptable.\n","# Scoring\n\nUse this sub-skill when a task mentions `scoring.toml`, `run_type = \"scoring\"`, scoring components, transforms, aggregation, `comp_*` plugin files, `@add_tag`, `QED`, `MolecularWeight`, `TanimotoSimilarity`, `TanimotoDistance`, OpenEye ROCS, Chemprop, `ExternalProcess`, or REST scoring.\n\n## Scope\n\nThis skill covers scoring-only jobs and scoring-function design that will later be reused by staged learning. For model sampling setup, use the sibling sampling skill. For transfer-learning or staged-learning orchestration, use the learning skill and return here only for `[scoring]` or `[stage.scoring]` blocks. For SMILES preprocessing, use the data-pipeline skill.\n\n## Start Here\n\n1. Use `run_type = \"scoring\"` for a standalone scoring run and provide a `[parameters]` block with `smiles_file` and optional `output_csv`.\n2. Build a `[scoring]` block with `type = \"geometric_mean\"` or `type = \"arithmetic_mean\"`, optional `parallel`, optional `use_pumas`, and one or more `[[scoring.component]]` blocks.\n3. Keep each component block in this shape: `[[scoring.component]]`, `[scoring.component.ComponentName]`, then one or more `[[scoring.component.ComponentName.endpoint]]` tables with `name`, optional `weight`, optional `params.*`, and optional `transform.*`.\n4. Prefer a scoring-only run on representative SMILES before using the same scoring function in RL.\n\n## References\n\n- `references\u002Fcomponents-and-plugins.md`: component block shapes, common built-ins, external components, and custom plugin discovery.\n- `references\u002Ftransforms-and-aggregation.md`: transform choice, endpoint weights, geometric\u002Farithmetic aggregation, filters, and penalties.\n- `references\u002Ftroubleshooting.md`: config parsing, plugin import, optional dependency, external service, and transform-debugging failures.\n\n## Bundled Helpers\n\n- `scripts\u002Fvalidate_scoring_config.py`: parse a TOML scoring config and summarize scoring blocks, components, endpoints, params, transforms, and likely structural issues without running scoring.\n- `scripts\u002Flist_scoring_components.py`: inspect installed `reinvent_plugins.components` namespace packages and list discovered `comp_*` modules\u002Fclasses without executing a scoring job.\n\nRun each helper with `--help` first. Both helpers are read-only; they inspect installed Python packages and config files but do not launch `reinvent`, score molecules, call external services, or load model checkpoints intentionally.\n\n## Practical Defaults\n\n- Use `QED` without a transform because it already returns a 0-1 value.\n- Use `MolecularWeight` with `double_sigmoid` for a preferred mass window such as 200-500 Da.\n- Use `TanimotoSimilarity` for new configs; treat `TanimotoDistance` as a backward-compatible deprecated alias.\n- Use `custom_alerts` for must-fail SMARTS filters and do not rely on its `weight` for optimization.\n- Use `geometric_mean` when every objective must remain acceptable; use `arithmetic_mean` when compensation between objectives is acceptable.\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\u002Freinvent4\u002Fsub-skills\u002Fscoring",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 scoring",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill scoring",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill scoring","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Freinvent4\u002Fsub-skills\u002Fscoring\u002FSKILL.md",[47,53,57,61,67],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcomponents-and-plugins.md","REFERENCE","参考文档",8916,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Freinvent4\u002Fsub-skills\u002Fscoring\u002Freferences\u002Fcomponents-and-plugins.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftransforms-and-aggregation.md",6425,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Freinvent4\u002Fsub-skills\u002Fscoring\u002Freferences\u002Ftransforms-and-aggregation.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",7601,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Freinvent4\u002Fsub-skills\u002Fscoring\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Flist_scoring_components.py","SCRIPT","脚本",5627,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Freinvent4\u002Fsub-skills\u002Fscoring\u002Fscripts\u002Flist_scoring_components.py",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fvalidate_scoring_config.py",12570,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Freinvent4\u002Fsub-skills\u002Fscoring\u002Fscripts\u002Fvalidate_scoring_config.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]