[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79322B67JPRF8MFQWTNRD99":3,"skill-same:01M79322B67JPRF8MFQWTNRD99":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},"01M79322B67JPRF8MFQWTNRD99","inference-design",null,"Run and adapt ProteinMPNN inference\u002Fdesign workflows, including single-PDB design, parsed JSONL batches, monomer and multichain design, CA-only and soluble models, score-only mode, probability outputs, output interpretation, and CPU\u002FGPU-safe command construction.","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\u002Fprotein-mpnn\u002Fsub-skills\u002Finference-design\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: inference-design\ndescription: \"Run and adapt ProteinMPNN inference\u002Fdesign workflows, including\n  single-PDB design, parsed JSONL batches, monomer and multichain design,\n  CA-only and soluble models, score-only mode, probability outputs, output\n  interpretation, and CPU\u002FGPU-safe command construction.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# ProteinMPNN Inference Design\n\nUse this sub-skill when a user wants to run `protein_mpnn_run.py`, change inference flags, choose model weights, interpret generated FASTA\u002FNPZ outputs, or debug ProteinMPNN design runs.\n\n## Quick Routing\n\n- Use direct PDB mode when the user has one structure: `--pdb_path structure.pdb --pdb_path_chains \"A B\"`.\n- Use parsed JSONL mode when the user has many PDBs or precomputed helper JSONL inputs: `--jsonl_path parsed_pdbs.jsonl` plus optional constraint JSONL files.\n- Route chain assignment, fixed positions, tied positions, amino-acid bias, omit masks, and PSSM builder details to `..\u002Fconstraint-inputs\u002F`.\n- Route retraining, custom checkpoint production, or modifying model architecture\u002Ftraining scripts to `..\u002Ftraining-custom-models\u002F`.\n- Use `scripts\u002Fbuild_inference_command.py` to print safe `protein_mpnn_run.py` commands without copying ProteinMPNN model code.\n\n## Minimum Runtime Assumptions\n\n- The user runs from a ProteinMPNN checkout containing `protein_mpnn_run.py`, `protein_mpnn_utils.py`, and model weight folders.\n- Python can import `torch` and `numpy` in the selected environment.\n- Model weights are present locally; this skill does not bundle or copy `.pt` weight files.\n- `--out_folder` is required because ProteinMPNN writes `seqs\u002F`, `scores\u002F`, `probs\u002F`, `score_only\u002F`, `conditional_probs_only\u002F`, or `unconditional_probs_only\u002F` under it.\n\n## Start Here\n\n1. Identify input style: single PDB (`--pdb_path`) or parsed batch JSONL (`--jsonl_path`). Do not pass both unless intentionally testing argument precedence; direct PDB mode wins when `--pdb_path` is non-empty.\n2. Identify task mode: design sequences, score existing sequence\u002Fbackbone pairs, save sampled probabilities, or emit conditional\u002Funconditional probabilities.\n3. Choose weights: default full-backbone vanilla, `--use_soluble_model` for soluble full-backbone weights, or `--ca_only` for CA-only weights.\n4. Set conservative controls first: `--batch_size 1`, explicit `--seed`, one or more `--sampling_temp` values, and a small `--num_seq_per_target` for dry runs.\n5. Read the references in this sub-skill before changing less common flags.\n\n## References\n\n- `references\u002Fcli-reference.md` lists the important `protein_mpnn_run.py` flags and model-family rules.\n- `references\u002Fworkflows.md` gives distilled recipes for examples 1, 2, 3, score-only, score-only from FASTA, CA-only, soluble, and probability-only runs.\n- `references\u002Foutput-formats.md` explains `seqs\u002F*.fa` headers and NPZ payloads.\n- `references\u002Ftroubleshooting.md` covers common runtime failures and safe CPU\u002FGPU adjustments.\n\n## Bundled Helper\n\nPrint a direct-PDB dry-run command:\n\n```bash\npython skills\u002Fprotein-mpnn\u002Fsub-skills\u002Finference-design\u002Fscripts\u002Fbuild_inference_command.py \\\n  --pdb-path inputs\u002Fmy_target.pdb \\\n  --chains \"A B\" \\\n  --out-folder outputs\u002Fmy_design \\\n  --num-seq-per-target 2 \\\n  --batch-size 1 \\\n  --seed 37\n```\n\nPrint a parsed-JSONL score-only command using a FASTA:\n\n```bash\npython skills\u002Fprotein-mpnn\u002Fsub-skills\u002Finference-design\u002Fscripts\u002Fbuild_inference_command.py \\\n  --jsonl-path outputs\u002Fparsed_pdbs.jsonl \\\n  --out-folder outputs\u002Fscore_existing \\\n  --score-only \\\n  --path-to-fasta outputs\u002Fseqs\u002Ftarget.fa \\\n  --num-seq-per-target 5 \\\n  --batch-size 1\n```\n\nThe helper prints a command only; it does not run ProteinMPNN and does not create helper JSONL files.\n","# ProteinMPNN Inference Design\n\nUse this sub-skill when a user wants to run `protein_mpnn_run.py`, change inference flags, choose model weights, interpret generated FASTA\u002FNPZ outputs, or debug ProteinMPNN design runs.\n\n## Quick Routing\n\n- Use direct PDB mode when the user has one structure: `--pdb_path structure.pdb --pdb_path_chains \"A B\"`.\n- Use parsed JSONL mode when the user has many PDBs or precomputed helper JSONL inputs: `--jsonl_path parsed_pdbs.jsonl` plus optional constraint JSONL files.\n- Route chain assignment, fixed positions, tied positions, amino-acid bias, omit masks, and PSSM builder details to `..\u002Fconstraint-inputs\u002F`.\n- Route retraining, custom checkpoint production, or modifying model architecture\u002Ftraining scripts to `..\u002Ftraining-custom-models\u002F`.\n- Use `scripts\u002Fbuild_inference_command.py` to print safe `protein_mpnn_run.py` commands without copying ProteinMPNN model code.\n\n## Minimum Runtime Assumptions\n\n- The user runs from a ProteinMPNN checkout containing `protein_mpnn_run.py`, `protein_mpnn_utils.py`, and model weight folders.\n- Python can import `torch` and `numpy` in the selected environment.\n- Model weights are present locally; this skill does not bundle or copy `.pt` weight files.\n- `--out_folder` is required because ProteinMPNN writes `seqs\u002F`, `scores\u002F`, `probs\u002F`, `score_only\u002F`, `conditional_probs_only\u002F`, or `unconditional_probs_only\u002F` under it.\n\n## Start Here\n\n1. Identify input style: single PDB (`--pdb_path`) or parsed batch JSONL (`--jsonl_path`). Do not pass both unless intentionally testing argument precedence; direct PDB mode wins when `--pdb_path` is non-empty.\n2. Identify task mode: design sequences, score existing sequence\u002Fbackbone pairs, save sampled probabilities, or emit conditional\u002Funconditional probabilities.\n3. Choose weights: default full-backbone vanilla, `--use_soluble_model` for soluble full-backbone weights, or `--ca_only` for CA-only weights.\n4. Set conservative controls first: `--batch_size 1`, explicit `--seed`, one or more `--sampling_temp` values, and a small `--num_seq_per_target` for dry runs.\n5. Read the references in this sub-skill before changing less common flags.\n\n## References\n\n- `references\u002Fcli-reference.md` lists the important `protein_mpnn_run.py` flags and model-family rules.\n- `references\u002Fworkflows.md` gives distilled recipes for examples 1, 2, 3, score-only, score-only from FASTA, CA-only, soluble, and probability-only runs.\n- `references\u002Foutput-formats.md` explains `seqs\u002F*.fa` headers and NPZ payloads.\n- `references\u002Ftroubleshooting.md` covers common runtime failures and safe CPU\u002FGPU adjustments.\n\n## Bundled Helper\n\nPrint a direct-PDB dry-run command:\n\n```bash\npython skills\u002Fprotein-mpnn\u002Fsub-skills\u002Finference-design\u002Fscripts\u002Fbuild_inference_command.py \\\n  --pdb-path inputs\u002Fmy_target.pdb \\\n  --chains \"A B\" \\\n  --out-folder outputs\u002Fmy_design \\\n  --num-seq-per-target 2 \\\n  --batch-size 1 \\\n  --seed 37\n```\n\nPrint a parsed-JSONL score-only command using a FASTA:\n\n```bash\npython skills\u002Fprotein-mpnn\u002Fsub-skills\u002Finference-design\u002Fscripts\u002Fbuild_inference_command.py \\\n  --jsonl-path outputs\u002Fparsed_pdbs.jsonl \\\n  --out-folder outputs\u002Fscore_existing \\\n  --score-only \\\n  --path-to-fasta outputs\u002Fseqs\u002Ftarget.fa \\\n  --num-seq-per-target 5 \\\n  --batch-size 1\n```\n\nThe helper prints a command only; it does not run ProteinMPNN and does not create helper JSONL files.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fprotein-mpnn\u002Fsub-skills\u002Finference-design",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 inference-design",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill inference-design",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill inference-design","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fprotein-mpnn\u002Fsub-skills\u002Finference-design\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fcli-reference.md","REFERENCE","参考文档",4580,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fprotein-mpnn\u002Fsub-skills\u002Finference-design\u002Freferences\u002Fcli-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Foutput-formats.md",4617,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fprotein-mpnn\u002Fsub-skills\u002Finference-design\u002Freferences\u002Foutput-formats.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",4650,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fprotein-mpnn\u002Fsub-skills\u002Finference-design\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fworkflows.md",6147,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fprotein-mpnn\u002Fsub-skills\u002Finference-design\u002Freferences\u002Fworkflows.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fbuild_inference_command.py","SCRIPT","脚本",10293,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fprotein-mpnn\u002Fsub-skills\u002Finference-design\u002Fscripts\u002Fbuild_inference_command.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",[],[]]