[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AWSN9X7RVNWGGWPWZ6SC1C":3,"skill-same:01M7AWSN9X7RVNWGGWPWZ6SC1C":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":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M7AWSN9X7RVNWGGWPWZ6SC1C","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.","flyme2bluemoon\u002Fskills","flyme2bluemoon","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F37197710?v=4","01M7AWSKCXRPGZSNS26MTB5YR4","Matthew Shen","01M7AWSKE11G83QK1885PSGJ3K",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fflyme2bluemoon\u002Fskills\u002Fblob\u002Fmain\u002Fskills-examples\u002Fclaude-science-skills\u002Falphafold2\u002FSKILL.md",[],[],"2026-11-15 14:19:17",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\nmetadata:\n  category: biomodels\n  requirements: [gpu]\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,"metadata":24,"description":40},{"category":25,"third_party":26,"display-name":29,"requirements":38},"biomodels",[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",[39],"gpu","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","main","9a28ca56870fad42cc4efa04a1d487c07a561ab1","skills-examples\u002Fclaude-science-skills\u002Falphafold2","https:\u002F\u002Fgithub.com\u002Fflyme2bluemoon\u002Fskills","https:\u002F\u002Fgithub.com\u002Fflyme2bluemoon","https:\u002F\u002Fflyme2bluemoon.github.io","Computer Science and Biology @ McGill University | making computer do cool thing","2026-10-31 13:32:13",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add flyme2bluemoon\u002Fskills --skill alphafold2",{"tool":55,"command":56},"bunx","bunx skills add flyme2bluemoon\u002Fskills --skill alphafold2",{"tool":58,"command":59},"pnpm","pnpm dlx skills add flyme2bluemoon\u002Fskills --skill alphafold2","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fflyme2bluemoon\u002Fskills\u002Fblob\u002Fmain\u002Fskills-examples\u002Fclaude-science-skills\u002Falphafold2\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},"01M7AWZ83KYJ9YSB4E5VQJ1K9B","unslop","Edit substantive human-facing prose to remove AI writing patterns while preserving meaning and tone.","MIT","https:\u002F\u002Fgithub.com\u002Fflyme2bluemoon\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Funslop\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},"01M7AWZ4FJPVNRMFFJC6JSHHKQ","pstack-principle-type-system-discipline","Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.","https:\u002F\u002Fgithub.com\u002Fflyme2bluemoon\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fpstack-principle-type-system-discipline\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},"01M7AWZ11K4KET3ASESNABPE52","pstack-principle-test-behavior-not-implementation","Apply when you write, change, or keep a test. Call the code the way its users do and assert the result they observe against a literal expected value. If the test would still pass when every imported function returns undefined, rewrite the assertion or delete the test.","https:\u002F\u002Fgithub.com\u002Fflyme2bluemoon\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fpstack-principle-test-behavior-not-implementation\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},"01M7AWYWT47M5JG7XV6ZK6QSSX","pstack-principle-subtract-before-you-add","Apply when sequencing an addition, refactor, or rewrite. Remove dead weight, redundant validators, and stub references first, then build on the simpler base.","https:\u002F\u002Fgithub.com\u002Fflyme2bluemoon\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fpstack-principle-subtract-before-you-add\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},"01M7AWYTNNHNGHB583NEV888BB","pstack-principle-sequence-verifiable-units","Sequence migrations or dependent changes around meaningful verification boundaries.","https:\u002F\u002Fgithub.com\u002Fflyme2bluemoon\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fpstack-principle-sequence-verifiable-units\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},"01M7AWYQ2C15PV2W2V6ZVMK3ZM","pstack-principle-separate-before-serializing-shared-state","Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.","https:\u002F\u002Fgithub.com\u002Fflyme2bluemoon\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fpstack-principle-separate-before-serializing-shared-state\u002FSKILL.md",[],[]]