[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74M64XFNDAABTE94G4Z937C":3,"skill-same:01M74M64XFNDAABTE94G4Z937C":64},{"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":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":46,"ownerHtmlUrl":47,"ownerBlogUrl":6,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M74M64XFNDAABTE94G4Z937C","alphafold2",null,"Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al. 2022, github.com\u002Fsokrypton\u002FColabFold; AlphaFold2 Jumper et al. 2021). Reach for this skill to fold a sequence or complex with the AF2\u002FAF2-Multimer evoformer, to validate designed sequences by self-consistency pLDDT, ipTM, and RMSD, or to run a quick MSA-backed prediction using the public MMseqs2 server.","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\u002Falphafold2\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: alphafold2\ndescription: >\n  Predict protein structure for monomers and multimers with AlphaFold2 via the\n  ColabFold runner (Mirdita et al. 2022, github.com\u002Fsokrypton\u002FColabFold;\n  AlphaFold2 Jumper et al. 2021). Reach for this skill to fold a sequence or\n  complex with the AF2\u002FAF2-Multimer evoformer, to validate designed sequences\n  by self-consistency pLDDT, ipTM, and RMSD, or to run a quick MSA-backed\n  prediction using the public MMseqs2 server.\nlicense: Apache-2.0\ncategory: biomodels\nrequirements: [gpu]\nmetadata:\n  display-name: AlphaFold2\n  # README #model-parameters-license: \"AlphaFold parameters … CC BY 4.0\".\n  # SKILL.md body: \"the public MMseqs2 server\" (api.colabfold.com — user's\n  # sequence is POSTed there for MSA). verified 2026-06-30\n  third_party:\n    - kind: weights\n      name: AlphaFold2\n      provider: Google DeepMind\n      license: CC-BY-4.0\n      terms_url: https:\u002F\u002Fgithub.com\u002Fgoogle-deepmind\u002Falphafold#model-parameters-license\n    # api.colabfold.com has no published ToS or privacy policy. The GitHub\n    # wiki is the closest data-use reference (info_url, not terms_url).\n    # Hostname in `name` so the user sees exactly where their sequence goes.\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# AlphaFold2 (ColabFold runner)\n\nThis skill wraps AlphaFold2 and AlphaFold2-Multimer through `colabfold_batch`,\nwhich replaces DeepMind's local-database MSA pipeline with a call to the public\nMMseqs2 server — so a prediction is one command and one FASTA, not a 2 TB\ndatabase mount. AF2 remains the reference monomer predictor and the multimer\nmodel is still a strong protein–protein validator, but it does not handle\nligands or nucleic acids; for those, route to `boltz`, `chai1`, or `openfold3`.\nThe ColabFold code is MIT (github.com\u002Fsokrypton\u002FColabFold) and the AlphaFold2\ncode is Apache-2.0 (github.com\u002Fgoogle-deepmind\u002Falphafold); the AF2 model\nparameters are CC-BY-4.0 with DeepMind's terms of use.\n\n## Running it\n\n```bash\ncolabfold_batch input.fasta out \\\n  --num-recycle 3 \\\n  --model-type alphafold2_multimer_v3\n```\n\nThe input is a plain FASTA. For a complex, put every chain on one sequence\nline separated by `:` — `colabfold_batch` builds a paired MSA per segment and\nruns the multimer model when it sees the colon (so the explicit `--model-type\nalphafold2_multimer_v3` above is belt-and-braces). For monomers omit\n`--model-type` and the colon. `--templates` and `--amber` add PDB templates\nand OpenMM relaxation respectively; both are off by default and both add\nminutes per model.\n\nColabFold runs all five AF2 model weights by default and ranks them by pLDDT\n(pTM\u002FipTM for multimer), so output per query lands in `out\u002F` as five ranked\nPDBs `\u003Cname>_unrelaxed_rank_00{1..5}_*.pdb` (b-factor column carries pLDDT)\nand a matching `\u003Cname>_scores_rank_00{N}_*.json` with `plddt`, `ptm`, and — for\nmultimer — `iptm` and the `pae` matrix. Rank-1 is the model to read first;\nipTM > 0.5 is the usual soft pass for an interface.\n\n## Unified-memory defaults loop forever under gVisor — the env patches them out\n\n`colabfold\u002Fbatch.py` hard-sets `TF_FORCE_UNIFIED_MEMORY=1` and\n`XLA_PYTHON_CLIENT_MEM_FRACTION=4.0` on import. Under a gVisor sandbox unified\nmemory is unsupported, so JAX's `device_put` loops indefinitely allocating\nhost RAM during AF2 parameter load — the job appears hung, never errors.\nOverride both before the import (`TF_FORCE_UNIFIED_MEMORY=0`, fraction\n`0.95`), or `sed`-patch the two assignments out of `batch.py` in the image\nbuild, or the first fold never starts.\n\n## The MSA server is the wall-clock bottleneck, and it is shared\n\n`colabfold_batch` defaults to `--msa-mode mmseqs2_uniref_env`, which posts your\nsequence to `api.colabfold.com`. That server is a public, rate-limited\nresource: the wait dominates short folds and occasionally times out under load.\nFor campaigns, run the MSA stage once with `--msa-only`, keep the resulting\n`.a3m` files, and feed the directory back as the input on subsequent runs — the\nGPU stage then starts immediately and the server is not hit again.\n\n## Errors worth recognizing\n\n| You see | It means \u002F do this |\n|---|---|\n| Job hangs silently during \"Running model_1\" with host RAM climbing | Unified-memory loop under gVisor — see the gotcha above; override or patch `batch.py`. |\n| `RESOURCE_EXHAUSTED` \u002F OOM during XLA compile | `XLA_PYTHON_CLIENT_MEM_FRACTION` too high for the GPU — drop below the `0.95` default to `0.9` or so. |\n| MSA stage hangs at `Submitting job` | Public MMseqs2 server is rate-limiting — wait, or pre-compute with `--msa-only` and re-run from the cached `.a3m`. |\n\n---\n\n**Next:** for designed-sequence validation, superpose the rank-1 model onto\nthe design backbone with US-align and gate on pLDDT\u002FipTM thresholds; for\nligand-bearing complexes, hand the same chains to `boltz` or `chai1`.\n","# AlphaFold2 (ColabFold runner)\n\nThis skill wraps AlphaFold2 and AlphaFold2-Multimer through `colabfold_batch`,\nwhich replaces DeepMind's local-database MSA pipeline with a call to the public\nMMseqs2 server — so a prediction is one command and one FASTA, not a 2 TB\ndatabase mount. AF2 remains the reference monomer predictor and the multimer\nmodel is still a strong protein–protein validator, but it does not handle\nligands or nucleic acids; for those, route to `boltz`, `chai1`, or `openfold3`.\nThe ColabFold code is MIT (github.com\u002Fsokrypton\u002FColabFold) and the AlphaFold2\ncode is Apache-2.0 (github.com\u002Fgoogle-deepmind\u002Falphafold); the AF2 model\nparameters are CC-BY-4.0 with DeepMind's terms of use.\n\n## Running it\n\n```bash\ncolabfold_batch input.fasta out \\\n  --num-recycle 3 \\\n  --model-type alphafold2_multimer_v3\n```\n\nThe input is a plain FASTA. For a complex, put every chain on one sequence\nline separated by `:` — `colabfold_batch` builds a paired MSA per segment and\nruns the multimer model when it sees the colon (so the explicit `--model-type\nalphafold2_multimer_v3` above is belt-and-braces). For monomers omit\n`--model-type` and the colon. `--templates` and `--amber` add PDB templates\nand OpenMM relaxation respectively; both are off by default and both add\nminutes per model.\n\nColabFold runs all five AF2 model weights by default and ranks them by pLDDT\n(pTM\u002FipTM for multimer), so output per query lands in `out\u002F` as five ranked\nPDBs `\u003Cname>_unrelaxed_rank_00{1..5}_*.pdb` (b-factor column carries pLDDT)\nand a matching `\u003Cname>_scores_rank_00{N}_*.json` with `plddt`, `ptm`, and — for\nmultimer — `iptm` and the `pae` matrix. Rank-1 is the model to read first;\nipTM > 0.5 is the usual soft pass for an interface.\n\n## Unified-memory defaults loop forever under gVisor — the env patches them out\n\n`colabfold\u002Fbatch.py` hard-sets `TF_FORCE_UNIFIED_MEMORY=1` and\n`XLA_PYTHON_CLIENT_MEM_FRACTION=4.0` on import. Under a gVisor sandbox unified\nmemory is unsupported, so JAX's `device_put` loops indefinitely allocating\nhost RAM during AF2 parameter load — the job appears hung, never errors.\nOverride both before the import (`TF_FORCE_UNIFIED_MEMORY=0`, fraction\n`0.95`), or `sed`-patch the two assignments out of `batch.py` in the image\nbuild, or the first fold never starts.\n\n## The MSA server is the wall-clock bottleneck, and it is shared\n\n`colabfold_batch` defaults to `--msa-mode mmseqs2_uniref_env`, which posts your\nsequence to `api.colabfold.com`. That server is a public, rate-limited\nresource: the wait dominates short folds and occasionally times out under load.\nFor campaigns, run the MSA stage once with `--msa-only`, keep the resulting\n`.a3m` files, and feed the directory back as the input on subsequent runs — the\nGPU stage then starts immediately and the server is not hit again.\n\n## Errors worth recognizing\n\n| You see | It means \u002F do this |\n|---|---|\n| Job hangs silently during \"Running model_1\" with host RAM climbing | Unified-memory loop under gVisor — see the gotcha above; override or patch `batch.py`. |\n| `RESOURCE_EXHAUSTED` \u002F OOM during XLA compile | `XLA_PYTHON_CLIENT_MEM_FRACTION` too high for the GPU — drop below the `0.95` default to `0.9` or so. |\n| MSA stage hangs at `Submitting job` | Public MMseqs2 server is rate-limiting — wait, or pre-compute with `--msa-only` and re-run from the cached `.a3m`. |\n\n---\n\n**Next:** for designed-sequence validation, superpose the rank-1 model onto\nthe design backbone with US-align and gate on pLDDT\u002FipTM thresholds; for\nligand-bearing complexes, hand the same chains to `boltz` or `chai1`.\n",{"name":5,"license":15,"category":24,"metadata":25,"description":38,"requirements":39},"biomodels",{"third_party":26,"display-name":29},[27,33],{"kind":28,"name":29,"license":30,"provider":31,"terms_url":32},"weights","AlphaFold2","CC-BY-4.0","Google DeepMind","https:\u002F\u002Fgithub.com\u002Fgoogle-deepmind\u002Falphafold#model-parameters-license",{"kind":34,"name":35,"info_url":36,"provider":37},"service","ColabFold MSA server (api.colabfold.com)","https:\u002F\u002Fgithub.com\u002Fsokrypton\u002FColabFold\u002Fwiki","Steinegger Lab","Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al. 2022, github.com\u002Fsokrypton\u002FColabFold; AlphaFold2 Jumper et al. 2021). Reach for this skill to fold a sequence or complex with the AF2\u002FAF2-Multimer evoformer, to validate designed sequences by self-consistency pLDDT, ipTM, and RMSD, or to run a quick MSA-backed prediction using the public MMseqs2 server.\n",[40],"gpu","main","e71245365df78e06cd166602744bf2491f79910e","research-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Falphafold2",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":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add pengqianhan\u002FAI-Human-Research-OS --skill alphafold2",{"tool":56,"command":57},"bunx","bunx skills add pengqianhan\u002FAI-Human-Research-OS --skill alphafold2",{"tool":59,"command":60},"pnpm","pnpm dlx skills add pengqianhan\u002FAI-Human-Research-OS --skill alphafold2","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\u002Falphafold2\u002FSKILL.md",true,[],[65,73,80,87,94,101],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"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).","MIT","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":69,"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":69,"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":69,"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":69,"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":69,"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",[],[]]