[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74M7B20YK5RQ84C80PGPCDS":3,"skill-same:01M74M7B20YK5RQ84C80PGPCDS":63},{"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":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M74M7B20YK5RQ84C80PGPCDS","chai1",null,"Structure prediction for protein, nucleic-acid, and small-molecule complexes with the Chai-1 foundation model (Chai Discovery 2024, github.com\u002Fchaidiscovery\u002Fchai-lab). Reach for this skill to predict an antibody-antigen or protein-ligand complex from a single FASTA, to re-fold designed binders as an AlphaFold-multimer alternative, or to drive co-folding from Python for batched campaigns on a GPU.","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\u002Fchai1\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: chai1\ndescription: >\n  Structure prediction for protein, nucleic-acid, and small-molecule complexes\n  with the Chai-1 foundation model (Chai Discovery 2024,\n  github.com\u002Fchaidiscovery\u002Fchai-lab). Reach for this skill to predict an\n  antibody-antigen or protein-ligand complex from a single FASTA, to re-fold\n  designed binders as an AlphaFold-multimer alternative, or to drive\n  co-folding from Python for batched campaigns on a GPU.\nlicense: Apache-2.0\ncategory: biomodels\nrequirements: [gpu]\nmetadata:\n  display-name: Chai-1\n  # github.com\u002Fchaidiscovery\u002Fchai-lab\u002Fblob\u002Fmain\u002FLICENSE: Apache-2.0\n  # (relicensed at v0.4.0). verified 2026-06-30\n  third_party:\n    - kind: weights\n      name: Chai-1\n      provider: Chai Discovery\n      license: Apache-2.0\n      terms_url: https:\u002F\u002Fgithub.com\u002Fchaidiscovery\u002Fchai-lab\u002Fblob\u002Fmain\u002FLICENSE\n    # SKILL.md — `--use-msa-server` \u002F `use_msa_server=True` sends the sequence\n    # to the public ColabFold MMseqs2 server. No published ToS — wiki is the\n    # closest data-use reference.\n    - kind: service\n      name: ColabFold MSA server (api.colabfold.com)\n      provider: Steinegger Lab\n      info_url: https:\u002F\u002Fgithub.com\u002Fsokrypton\u002FColabFold\u002Fwiki\n---\n\n# Chai-1\n\nChai-1 is an all-atom diffusion co-folder in the same family as Boltz-2 and\nAlphaFold3: a multi-entity FASTA in, mmCIF plus pTM\u002FipTM\u002FpLDDT out, with\nprotein, RNA, DNA, and SMILES-ligand chains all first-class. It and `boltz`\ncover the same surface; running both and keeping designs that pass either is a\ncommon consensus filter, and Chai's Python entry point makes it the easier of\nthe two to embed in a loop. Code and weights are Apache-2.0 — commercial use\nincluding drug discovery is explicitly permitted\n(github.com\u002Fchaidiscovery\u002Fchai-lab).\n\n## Running it\n\n```python\nfrom pathlib import Path\nfrom chai_lab.chai1 import run_inference\n\nPath(\"complex.fasta\").write_text(\"\"\"\n>protein|name=target\nMVTPEGNVSLVDESLLVGVTDEDRAVRS...\n>protein|name=binder\nAIQRTPKIQVYSRHPAENG...\n>ligand|name=cofactor\nCCCCCCCCCCCCCC(=O)O\n\"\"\".strip())\n\ncandidates = run_inference(\n    fasta_file=Path(\"complex.fasta\"),\n    output_dir=Path(\"out\u002F\"),\n    num_trunk_recycles=3,\n    num_diffn_timesteps=200,\n    seed=42,\n    device=\"cuda:0\",\n    use_esm_embeddings=True,\n)\nprint([rd.aggregate_score.item() for rd in candidates.ranking_data])\n```\n\nThe FASTA header is `>{entity_type}|name={id}` with `entity_type` ∈\n{`protein`, `rna`, `dna`, `ligand`}; ligand records carry a SMILES string as\nthe sequence body, and modified residues are written inline as\n`...AAK(SEP)AAG...`. From the shell the same job is `chai-lab fold\ncomplex.fasta out\u002F --use-msa-server`. Without `--use-msa-server` (or\n`use_msa_server=True` in Python) the model runs on ESM embeddings alone, which\nis faster but typically a few ipTM points behind the MSA-backed run.\n\n`output_dir` receives `pred.model_idx_{0..4}.cif` plus a matching\n`scores.model_idx_{N}.npz` per sample with `aggregate_score`, `ptm`, `iptm`,\n`per_chain_ptm`, and clash flags. Rank by `aggregate_score`; treat `iptm` >\n0.5 as a soft pass for an interface. The function refuses a non-empty `output_dir`, so\nclear or rotate it between calls.\n\n## Unset `CHAI_DOWNLOADS_DIR` fails mid-run with PermissionError on a read-only image\n\nChai downloads ~5 GB on the first inference call (not at install time),\nincluding its own traced ESM2-3B for the embedding path. If\n`CHAI_DOWNLOADS_DIR` is unset, the default is inside `site-packages`: on a\nread-only image that fails with a confusing `PermissionError` mid-run, and on\na writable one it silently re-downloads ~5 GB into the container on every cold\nstart. Export the variable to a persisted volume so the download happens once.\n\n## No-MSA mode still loads a 3 B-parameter ESM — same VRAM, not less\n\n`use_esm_embeddings=True` without an MSA still loads a 3-billion-parameter\nlanguage model into GPU memory alongside the trunk; it removes the MSA-server\nround-trip, not the VRAM cost. If you OOM, drop `num_diffn_timesteps` or fold\nfewer chains per call rather than expecting the no-MSA mode to fit a smaller\ncard.\n\n## Errors worth recognizing\n\n| You see | It means \u002F do this |\n|---|---|\n| `PermissionError` under `site-packages\u002Fchai_lab\u002F...` | `CHAI_DOWNLOADS_DIR` not set on a read-only image — export it to a writable path or the pre-populated mount. |\n| `RuntimeError: CUDA out of memory` during ESM embedding | The traced ESM2-3B is loading alongside the trunk — use an 80 GB tier or split chains across calls. |\n\n---\n\n**Next:** filter survivors on confidence\u002Fclash metrics or feed them back to\n`proteinmpnn` for the next design round.\n","# Chai-1\n\nChai-1 is an all-atom diffusion co-folder in the same family as Boltz-2 and\nAlphaFold3: a multi-entity FASTA in, mmCIF plus pTM\u002FipTM\u002FpLDDT out, with\nprotein, RNA, DNA, and SMILES-ligand chains all first-class. It and `boltz`\ncover the same surface; running both and keeping designs that pass either is a\ncommon consensus filter, and Chai's Python entry point makes it the easier of\nthe two to embed in a loop. Code and weights are Apache-2.0 — commercial use\nincluding drug discovery is explicitly permitted\n(github.com\u002Fchaidiscovery\u002Fchai-lab).\n\n## Running it\n\n```python\nfrom pathlib import Path\nfrom chai_lab.chai1 import run_inference\n\nPath(\"complex.fasta\").write_text(\"\"\"\n>protein|name=target\nMVTPEGNVSLVDESLLVGVTDEDRAVRS...\n>protein|name=binder\nAIQRTPKIQVYSRHPAENG...\n>ligand|name=cofactor\nCCCCCCCCCCCCCC(=O)O\n\"\"\".strip())\n\ncandidates = run_inference(\n    fasta_file=Path(\"complex.fasta\"),\n    output_dir=Path(\"out\u002F\"),\n    num_trunk_recycles=3,\n    num_diffn_timesteps=200,\n    seed=42,\n    device=\"cuda:0\",\n    use_esm_embeddings=True,\n)\nprint([rd.aggregate_score.item() for rd in candidates.ranking_data])\n```\n\nThe FASTA header is `>{entity_type}|name={id}` with `entity_type` ∈\n{`protein`, `rna`, `dna`, `ligand`}; ligand records carry a SMILES string as\nthe sequence body, and modified residues are written inline as\n`...AAK(SEP)AAG...`. From the shell the same job is `chai-lab fold\ncomplex.fasta out\u002F --use-msa-server`. Without `--use-msa-server` (or\n`use_msa_server=True` in Python) the model runs on ESM embeddings alone, which\nis faster but typically a few ipTM points behind the MSA-backed run.\n\n`output_dir` receives `pred.model_idx_{0..4}.cif` plus a matching\n`scores.model_idx_{N}.npz` per sample with `aggregate_score`, `ptm`, `iptm`,\n`per_chain_ptm`, and clash flags. Rank by `aggregate_score`; treat `iptm` >\n0.5 as a soft pass for an interface. The function refuses a non-empty `output_dir`, so\nclear or rotate it between calls.\n\n## Unset `CHAI_DOWNLOADS_DIR` fails mid-run with PermissionError on a read-only image\n\nChai downloads ~5 GB on the first inference call (not at install time),\nincluding its own traced ESM2-3B for the embedding path. If\n`CHAI_DOWNLOADS_DIR` is unset, the default is inside `site-packages`: on a\nread-only image that fails with a confusing `PermissionError` mid-run, and on\na writable one it silently re-downloads ~5 GB into the container on every cold\nstart. Export the variable to a persisted volume so the download happens once.\n\n## No-MSA mode still loads a 3 B-parameter ESM — same VRAM, not less\n\n`use_esm_embeddings=True` without an MSA still loads a 3-billion-parameter\nlanguage model into GPU memory alongside the trunk; it removes the MSA-server\nround-trip, not the VRAM cost. If you OOM, drop `num_diffn_timesteps` or fold\nfewer chains per call rather than expecting the no-MSA mode to fit a smaller\ncard.\n\n## Errors worth recognizing\n\n| You see | It means \u002F do this |\n|---|---|\n| `PermissionError` under `site-packages\u002Fchai_lab\u002F...` | `CHAI_DOWNLOADS_DIR` not set on a read-only image — export it to a writable path or the pre-populated mount. |\n| `RuntimeError: CUDA out of memory` during ESM embedding | The traced ESM2-3B is loading alongside the trunk — use an 80 GB tier or split chains across calls. |\n\n---\n\n**Next:** filter survivors on confidence\u002Fclash metrics or feed them back to\n`proteinmpnn` for the next design round.\n",{"name":5,"license":15,"category":24,"metadata":25,"description":37,"requirements":38},"biomodels",{"third_party":26,"display-name":29},[27,32],{"kind":28,"name":29,"license":15,"provider":30,"terms_url":31},"weights","Chai-1","Chai Discovery","https:\u002F\u002Fgithub.com\u002Fchaidiscovery\u002Fchai-lab\u002Fblob\u002Fmain\u002FLICENSE",{"kind":33,"name":34,"info_url":35,"provider":36},"service","ColabFold MSA server (api.colabfold.com)","https:\u002F\u002Fgithub.com\u002Fsokrypton\u002FColabFold\u002Fwiki","Steinegger Lab","Structure prediction for protein, nucleic-acid, and small-molecule complexes with the Chai-1 foundation model (Chai Discovery 2024, github.com\u002Fchaidiscovery\u002Fchai-lab). Reach for this skill to predict an antibody-antigen or protein-ligand complex from a single FASTA, to re-fold designed binders as an AlphaFold-multimer alternative, or to drive co-folding from Python for batched campaigns on a GPU.\n",[39],"gpu","main","e71245365df78e06cd166602744bf2491f79910e","research-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Fchai1",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":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add pengqianhan\u002FAI-Human-Research-OS --skill chai1",{"tool":55,"command":56},"bunx","bunx skills add pengqianhan\u002FAI-Human-Research-OS --skill chai1",{"tool":58,"command":59},"pnpm","pnpm dlx skills add pengqianhan\u002FAI-Human-Research-OS --skill chai1","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\u002Fchai1\u002FSKILL.md",true,[],[64,72,79,86,93,100],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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).","MIT","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fworkflow_skill_creator\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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",[],[]]