[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74M8PFWFZ9M4CNZRH6JC4JJ":3,"skill-same:01M74M8PFWFZ9M4CNZRH6JC4JJ":65},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":41,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M74M8PFWFZ9M4CNZRH6JC4JJ","diffdock",null,"Predict small-molecule binding poses with DiffDock-L (Corso et al. 2023\u002F2024, github.com\u002Fgcorso\u002FDiffDock) — blind diffusion docking that places a ligand into a protein pocket without a predefined search box and ranks the samples with a learned confidence model. Reach for this skill to dock a SMILES or SDF against a PDB, to generate ranked 3D poses for a small fragment library, or to get a starting pose for downstream rescoring. DiffDock predicts geometry, not affinity.","pengqianhan\u002FAI-Human-Research-OS","pengqianhan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4286531?v=4","01M74M3DT9HNZ6HPAK8TX69EX9","PengqianHan","01M74M3DTVSN2GXW0JH2W396FK",3,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Fdiffdock\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: diffdock\ndescription: >\n  Predict small-molecule binding poses with DiffDock-L (Corso et al. 2023\u002F2024,\n  github.com\u002Fgcorso\u002FDiffDock) — blind diffusion docking that places a ligand\n  into a protein pocket without a predefined search box and ranks the samples\n  with a learned confidence model. Reach for this skill to dock a\n  SMILES or SDF against a PDB, to generate ranked 3D poses for a small\n  fragment library, or to get a starting pose for downstream rescoring.\n  DiffDock predicts geometry, not affinity.\nlicense: Apache-2.0\ncategory: biomodels\nrequirements: [gpu]\nmetadata:\n  display-name: DiffDock\n  # github.com\u002Fgcorso\u002FDiffDock\u002Fblob\u002Fmain\u002FLICENSE: MIT (© 2022 Corso, Stärk,\n  # Jing). verified 2026-06-30\n  third_party:\n    - kind: weights\n      name: DiffDock-L\n      license: MIT\n      terms_url: https:\u002F\u002Fgithub.com\u002Fgcorso\u002FDiffDock\u002Fblob\u002Fmain\u002FLICENSE\n---\n\n# DiffDock-L\n\nDiffDock-L is a blind pose predictor: given a protein structure and a ligand,\nit samples ligand placements over the whole surface with a diffusion model and\nranks them with a separately trained confidence head. The confidence score\ncorrelates with pose correctness, not with binding free energy — DiffDock does\nnot predict whether or how tightly the ligand binds, so for hit triage you\nstill pair it with a scorer (GNINA, MM-GBSA) or with `boltz`'s affinity head.\nFor protein–protein and nucleic-acid co-folding, route to `boltz` or `chai1`.\nCode and weights are MIT (github.com\u002Fgcorso\u002FDiffDock).\n\n## Running it\n\n```bash\ncd $DIFFDOCK_REPO   # a clone of github.com\u002Fgcorso\u002FDiffDock\npython3 -m inference \\\n  --config default_inference_args.yaml \\\n  --protein_path target.pdb \\\n  --ligand_description \"COc1ccc(C#N)cc1\" \\\n  --out_dir out\n```\n\nFor more than one complex, give `--protein_ligand_csv batch.csv` instead of the\ntwo single-complex flags; the CSV has four columns — `complex_name`,\n`protein_path`, `ligand_description` (SMILES or an `.sdf`\u002F`.mol2` path), and\n`protein_sequence`. Leave `protein_path` empty and fill `protein_sequence` to\nhave DiffDock fold the receptor with ESMFold first; that path and a\nlarger-library screening recipe are in `references\u002Fworkflows.md`.\n\nUnder `--out_dir\u002F\u003Ccomplex_name>\u002F` each sample is written as\n`rank{N}_confidence{score}.sdf`, plus a copy of `rank1.sdf` for convenience.\nThe confidence value in the filename is a logit, so it is unbounded and can be\nnegative; among samples for the *same* complex higher is better, but values are\nnot comparable across different complexes or ligands.\n\n## The YAML config overwrites your CLI flags\n\n`inference.py` loads `--config default_inference_args.yaml` *after* argparse\nand replaces every key it finds, so passing `--samples_per_complex 40` or\n`--model_dir ...` on the command line is silently ignored if the same key sits\nin the YAML. To change sampling depth or any other key the YAML defines, copy\nthe YAML, edit the copy, and point `--config` at it.\n\n## The first run is silent for ~11 minutes and needs ≥32 GB host RAM\n\nBefore the first complex, DiffDock precomputes SO(3) and torus lookup tables.\nThat step is silent on stderr, takes ~11 minutes, and on the default Modal\ntier runs out of host memory and SIGKILLs mid-precompute. Set\n`provider_params.modal.memory: 65536` (or your provider's equivalent), and do\nnot assume a hang means a crash.\n\n## The README's `--ligand` works on the CLI by accident — use `--ligand_description`\n\nThe upstream README shows `--ligand`, which only works because argparse\nprefix-matches it to the real flag `--ligand_description`. That shortcut is\nCLI-only: as a CSV column header or YAML key, `ligand` matches nothing and the\nrow is silently treated as having no ligand. Spell the flag and the column\nheader out in full.\n\n## Errors worth recognizing\n\n| You see | It means \u002F do this |\n|---|---|\n| `ValueError: not allowed to raise maximum limit` at startup | `setrlimit(NOFILE, 64000)` exceeds the sandbox hard limit — `sed` the constant in `inference.py` to `min(64000, rlimit[1])`. |\n| Silent SIGKILL a few minutes into the SO(3) precompute | Host RAM exhausted — see the gotcha above. |\n| `python3: not found` | You are on the upstream `rbgcsail\u002Fdiffdock` image — that one runs from `\u002Fhome\u002Fappuser\u002FDiffDock` under `micromamba`. |\n\n---\n\n**Next:** rescore the `rank1.sdf` poses before ranking ligands against each\nother — `boltz`'s affinity head is the in-tree option — since the DiffDock\nconfidence head alone is not an affinity predictor.\n","# DiffDock-L\n\nDiffDock-L is a blind pose predictor: given a protein structure and a ligand,\nit samples ligand placements over the whole surface with a diffusion model and\nranks them with a separately trained confidence head. The confidence score\ncorrelates with pose correctness, not with binding free energy — DiffDock does\nnot predict whether or how tightly the ligand binds, so for hit triage you\nstill pair it with a scorer (GNINA, MM-GBSA) or with `boltz`'s affinity head.\nFor protein–protein and nucleic-acid co-folding, route to `boltz` or `chai1`.\nCode and weights are MIT (github.com\u002Fgcorso\u002FDiffDock).\n\n## Running it\n\n```bash\ncd $DIFFDOCK_REPO   # a clone of github.com\u002Fgcorso\u002FDiffDock\npython3 -m inference \\\n  --config default_inference_args.yaml \\\n  --protein_path target.pdb \\\n  --ligand_description \"COc1ccc(C#N)cc1\" \\\n  --out_dir out\n```\n\nFor more than one complex, give `--protein_ligand_csv batch.csv` instead of the\ntwo single-complex flags; the CSV has four columns — `complex_name`,\n`protein_path`, `ligand_description` (SMILES or an `.sdf`\u002F`.mol2` path), and\n`protein_sequence`. Leave `protein_path` empty and fill `protein_sequence` to\nhave DiffDock fold the receptor with ESMFold first; that path and a\nlarger-library screening recipe are in `references\u002Fworkflows.md`.\n\nUnder `--out_dir\u002F\u003Ccomplex_name>\u002F` each sample is written as\n`rank{N}_confidence{score}.sdf`, plus a copy of `rank1.sdf` for convenience.\nThe confidence value in the filename is a logit, so it is unbounded and can be\nnegative; among samples for the *same* complex higher is better, but values are\nnot comparable across different complexes or ligands.\n\n## The YAML config overwrites your CLI flags\n\n`inference.py` loads `--config default_inference_args.yaml` *after* argparse\nand replaces every key it finds, so passing `--samples_per_complex 40` or\n`--model_dir ...` on the command line is silently ignored if the same key sits\nin the YAML. To change sampling depth or any other key the YAML defines, copy\nthe YAML, edit the copy, and point `--config` at it.\n\n## The first run is silent for ~11 minutes and needs ≥32 GB host RAM\n\nBefore the first complex, DiffDock precomputes SO(3) and torus lookup tables.\nThat step is silent on stderr, takes ~11 minutes, and on the default Modal\ntier runs out of host memory and SIGKILLs mid-precompute. Set\n`provider_params.modal.memory: 65536` (or your provider's equivalent), and do\nnot assume a hang means a crash.\n\n## The README's `--ligand` works on the CLI by accident — use `--ligand_description`\n\nThe upstream README shows `--ligand`, which only works because argparse\nprefix-matches it to the real flag `--ligand_description`. That shortcut is\nCLI-only: as a CSV column header or YAML key, `ligand` matches nothing and the\nrow is silently treated as having no ligand. Spell the flag and the column\nheader out in full.\n\n## Errors worth recognizing\n\n| You see | It means \u002F do this |\n|---|---|\n| `ValueError: not allowed to raise maximum limit` at startup | `setrlimit(NOFILE, 64000)` exceeds the sandbox hard limit — `sed` the constant in `inference.py` to `min(64000, rlimit[1])`. |\n| Silent SIGKILL a few minutes into the SO(3) precompute | Host RAM exhausted — see the gotcha above. |\n| `python3: not found` | You are on the upstream `rbgcsail\u002Fdiffdock` image — that one runs from `\u002Fhome\u002Fappuser\u002FDiffDock` under `micromamba`. |\n\n---\n\n**Next:** rescore the `rank1.sdf` poses before ranking ligands against each\nother — `boltz`'s affinity head is the in-tree option — since the DiffDock\nconfidence head alone is not an affinity predictor.\n",{"name":5,"license":15,"category":24,"metadata":25,"description":33,"requirements":34},"biomodels",{"third_party":26,"display-name":32},[27],{"kind":28,"name":29,"license":30,"terms_url":31},"weights","DiffDock-L","MIT","https:\u002F\u002Fgithub.com\u002Fgcorso\u002FDiffDock\u002Fblob\u002Fmain\u002FLICENSE","DiffDock","Predict small-molecule binding poses with DiffDock-L (Corso et al. 2023\u002F2024, github.com\u002Fgcorso\u002FDiffDock) — blind diffusion docking that places a ligand into a protein pocket without a predefined search box and ranks the samples with a learned confidence model. Reach for this skill to dock a SMILES or SDF against a PDB, to generate ranked 3D poses for a small fragment library, or to get a starting pose for downstream rescoring. DiffDock predicts geometry, not affinity.\n",[35],"gpu","main","e71245365df78e06cd166602744bf2491f79910e","research-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Fdiffdock",0,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS","https:\u002F\u002Fpengqianhan.github.io\u002FAI-Human-Research-OS\u002F","https:\u002F\u002Fgithub.com\u002Fpengqianhan","Ph.D. candidate of The University of Auckland, New Zealand","2026-11-14 18:08:16",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add pengqianhan\u002FAI-Human-Research-OS --skill diffdock",{"tool":51,"command":52},"bunx","bunx skills add pengqianhan\u002FAI-Human-Research-OS --skill diffdock",{"tool":54,"command":55},"pnpm","pnpm dlx skills add pengqianhan\u002FAI-Human-Research-OS --skill diffdock","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Fdiffdock\u002FSKILL.md",true,[59],{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fworkflows.md","REFERENCE","参考文档",1984,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Fdiffdock\u002Freferences\u002Fworkflows.md",[66,73,80,87,94,101],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":30,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M74MWYTHT498SVMN823896T7","workflow-skill-creator","Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say \"make this a skill\", \"create a skill from what we just did\", \"package this workflow\" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fworkflow_skill_creator\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":30,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M74MWWVCFZ8HQS8840F1V1FT","uv","Checks whether the uv Python package manager is installed and installs it if missing. Ensures uv is on PATH. Use when another skill requires uv as a prerequisite.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fuv\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":30,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M74MWRH5BTSWZ2C5PCTD5FV9","uniprot-database","Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or retrieving functional annotations and publications. Don't use for sequence alignment, protein folding, or sequence similarity search (use specialized skills for those tasks).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Funiprot_database\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":30,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M74MWN1D3ER9F1FZPWH8HQC1","unibind-database","Queries the UniBind database for experimentally validated transcription factor (TF) binding sites. Use when retrieving direct TF-DNA interaction datasets, downloading binding site coordinates (BED\u002FFASTA) for local analysis, or listing available datasets by species, cell line, or TF name. Don't use to query specific intervals, locations, genes, motif models or expression data.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Funibind_database\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":30,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M74MWHHB5QZY3NR2FYA1EK4N","ucsc-conservation-and-tfbs","Fetch Evolutionary Conservation scores (phyloP, phastCons) and Transcription Factor Binding Sites (TFBS) from the UCSC Genome Browser. Use when analyzing whether genomic variants or regions are evolutionarily conserved, functionally important, or bounded by TF regulators across major projects (ENCODE, JASPAR, ReMap).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fucsc_conservation_and_tfbs\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":30,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M74MWERYHSY87P21FDMVE6BA","string-database","Query the STRING database for protein-protein interactions (PPIs), functional enrichment, and homology. Use when the user asks about interactions between specific proteins, interaction evidence, confidence scores, protein interaction partners, or pathway enrichments.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fstring_database\u002FSKILL.md",[],[]]