[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74MDPATDM40AKB7PDGS8T3J":3,"skill-same:01M74MDPATDM40AKB7PDGS8T3J":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},"01M74MDPATDM40AKB7PDGS8T3J","openfold3",null,"Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab. Use this skill when predicting protein\u002Fnucleic-acid\u002Fligand complex structures with an Apache-2.0-licensed AF3 reimplementation.","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\u002Fopenfold3\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: openfold3\ndescription: >\n  Structure prediction using OpenFold3, an open-weights PyTorch reproduction of\n  AlphaFold3 from the AlQuraishi Lab.\n  Use this skill when predicting protein\u002Fnucleic-acid\u002Fligand complex\n  structures with an Apache-2.0-licensed AF3 reimplementation.\nlicense: Apache-2.0\ncategory: biomodels\nrequirements: [gpu]\nmetadata:\n  display-name: OpenFold3\n  # github.com\u002Faqlaboratory\u002Fopenfold-3\u002Fblob\u002Fmain\u002FLICENSE: Apache-2.0. HF model\n  # card and gated prompt confirm. verified 2026-06-30\n  third_party:\n    - kind: weights\n      name: OpenFold3\n      provider: OpenFold Consortium\n      license: Apache-2.0\n      terms_url: https:\u002F\u002Fgithub.com\u002Faqlaboratory\u002Fopenfold-3\u002Fblob\u002Fmain\u002FLICENSE\n    # SKILL.md — `--use-msa-server` DEFAULTS to true (MSA server is\n    # api.colabfold.com), so the sequence leaves the machine unless opted out.\n    # No published ToS — wiki is the 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# OpenFold3 Structure Prediction\n\n## Prerequisites\n\n| Requirement | Minimum | Recommended |\n| ----------- | ------- | ----------- |\n| Python      | 3.10+   | 3.11        |\n| CUDA        | 12.1+   | 12.4+       |\n| GPU VRAM    | 24GB    | 80GB (H100) |\n| RAM         | 32GB    | 64GB        |\n| Disk (weights) | 3GB  | -           |\n\n## How to run\n\n### Installation\n\n```bash\npip install 'openfold3[cuequivariance]==0.4.1'\n```\n\nThe default attention kernel is DeepSpeed `DS4Sci_EvoformerAttention`. If\nDeepSpeed is unavailable, switch to the cuEquivariance triangle kernels (no\nbuild-from-source) by overriding the eval memory settings in\n`model_config.py` (`use_deepspeed_evo_attention: False`,\n`use_cueq_triangle_kernels: True`). Some pre-built environments already ship\nthis override; check before re-patching.\n\n### Weights\n\nApache-2.0, ~2.3 GB from HF `OpenFold\u002FOpenFold3`. The repo is **gated** (auto-approval) — accept the access form on the HF model page and authenticate (`huggingface-cli login` or `HF_TOKEN`) before downloading:\n\n```bash\nexport OPENFOLD_CACHE=~\u002F.openfold3\nhuggingface-cli download OpenFold\u002FOpenFold3 checkpoints\u002Fof3-p2-155k.pt \\\n  --local-dir \"$OPENFOLD_CACHE\"\n```\n\n`run_openfold` will also auto-download to `$OPENFOLD_CACHE` on first run if\negress is open and HF credentials are available (either `HF_TOKEN` or a prior\n`huggingface-cli login`) with repo access granted. The interactive\n`setup_openfold` helper exists but prompts on stdin; prefer the explicit\ndownload above for non-interactive runs.\n\n### Running\n\n```bash\nexport OPENFOLD_CACHE=\u002Fpath\u002Fto\u002Fcache\nrun_openfold predict \\\n  --query_json=queries.json \\\n  --output-dir out\u002F \\\n  --use-msa-server false \\\n  --use-templates false\n```\n\n`run_openfold` discovers the checkpoint under `$OPENFOLD_CACHE` automatically.\nOnly pass `--inference-ckpt-path \u003Cfile.pt>` if you have a non-standard layout\nor multiple checkpoints and need to pin one explicitly.\n\nFor MSA + templates (slower, higher accuracy), drop the two `false` flags. The\nMSA server is `api.colabfold.com`; template chain-ID remap hits\n`data.rcsb.org` (GraphQL) — both must be reachable.\n\n## Query JSON format\n\nOpenFold3 does **not** read FASTA. Queries are a JSON object validated by\n`InferenceQuerySet` (pydantic, `extra: forbid` — unknown keys reject):\n\n```json\n{\n  \"queries\": {\n    \"my_complex\": {\n      \"chains\": [\n        {\"molecule_type\": \"protein\", \"chain_ids\": [\"A\"], \"sequence\": \"MQIFVK…\"},\n        {\"molecule_type\": \"protein\", \"chain_ids\": [\"B\", \"C\"], \"sequence\": \"MVLSPA…\"},\n        {\"molecule_type\": \"ligand\",  \"chain_ids\": [\"L\"], \"smiles\": \"CC(=O)Oc1ccccc1C(=O)O\"}\n      ],\n      \"use_msas\": true\n    }\n  },\n  \"seeds\": [42]\n}\n```\n\n| `molecule_type` | required field |\n| -------- | ---- |\n| `protein` \u002F `dna` \u002F `rna` | `sequence` |\n| `ligand` | `smiles` **or** `ccd_codes: [\"HEM\"]` |\n\n`chain_ids` is a list — repeat the same sequence across multiple chain IDs\nfor homo-oligomers. Per-chain `paired_msa_file_paths` \u002F `main_msa_file_paths`\nlet you supply your own a3m instead of the server.\n\n## Key parameters\n\n| Flag | Default | Description |\n| ---- | ------- | ----------- |\n| `--num-diffusion-samples` | 5 | Structures per (query, seed) |\n| `--num-model-seeds` | 1 | Number of model seeds per query (multiplies output count alongside JSON `seeds` and diffusion samples) |\n| `--use-msa-server` | true | ColabFold MMseqs2 server for MSA |\n| `--use-templates` | true | ColabFold template search + RCSB remap |\n| `--inference-ckpt-path` | auto-discovered under `$OPENFOLD_CACHE` | Override only — for non-standard layouts or to pin a specific checkpoint file |\n\n## Output format\n\n```\nout\u002F\n├── summary.txt\n├── model_config.json \u002F experiment_config.json\n├── inference_query_set.json\n└── \u003Cquery_name>\u002Fseed_\u003CN>\u002F\n    ├── \u003Cquery>_seed_\u003CN>_sample_\u003Ck>_model.cif\n    ├── \u003Cquery>_seed_\u003CN>_sample_\u003Ck>_confidences.json           # full PAE\u002FpLDDT\n    ├── \u003Cquery>_seed_\u003CN>_sample_\u003Ck>_confidences_aggregated.json\n    └── timing.json\n```\n\n`*_confidences_aggregated.json` is the small one to read first:\n\n```json\n{\n  \"avg_plddt\": 78.96, \"ptm\": 0.667, \"iptm\": 0.0, \"gpde\": 0.73,\n  \"has_clash\": 0.0, \"sample_ranking_score\": 0.133,\n  \"chain_ptm\": {\"A\": 0.667}, \"chain_pair_iptm\": {}\n}\n```\n\n## What good output looks like\n\n- `summary.txt` shows `Successful Queries: N` matching your input count\n- avg_plddt > 70 (single-seq) \u002F > 80 (with MSA)\n- ptm > 0.6; for complexes, iptm > 0.5\n- `has_clash: 0.0`\n- `.cif` ~50-150 KB per sample for a small protein\n\n## Verify\n\n```bash\ngrep -E 'Successful|Failed' out\u002Fsummary.txt\nfind out -name '*_model.cif' | wc -l   # = queries x json_seeds x num-model-seeds x num-diffusion-samples\n```\n\n---\n\n## Troubleshooting\n\n| Error | Cause | Fix |\n| ----- | ----- | --- |\n| `_deepspeed_evo_attn requires that DeepSpeed be installed` | default eval kernel is DS4Sci on CUDA | install `deepspeed` (needs nvcc + CUTLASS), **or** in `model_config.py` eval block set `use_deepspeed_evo_attention: False` + `use_cueq_triangle_kernels: True` (cuEq path; no build) |\n| `CUTLASS_PATH ... not set ... cutlass_library is not installed` | cuEq path still needs the python `cutlass_library` shim | `pip install nvidia-cutlass` |\n| `libXrender.so.1: cannot open shared object file` | rdkit (via pdbeccdutils) needs X11 render libs | `apt-get install libxrender1 libxext6 libsm6` |\n| `ModuleNotFoundError: boto3` (or `awscrt`) | `openfold3.core.data.io.s3` is eager-imported even when weights are local | `pip install boto3 awscrt` |\n| `ValidationError: queries \u002F Field required` or `Input should be an object` | wrong JSON shape | top-level is `{\"queries\": {\"\u003Cname>\": {...}}}` (a dict, not a list) |\n| `ValidationError ... settings \u002F Extra inputs are not permitted` | tried to override model config via `--runner-yaml` | `--runner-yaml` is `InferenceExperimentConfig` only; kernel\u002Fmemory settings live in `model_config.py` |\n| `Failed to fetch chain ID mappings from RCSB for N entries` | `data.rcsb.org` unreachable (allowlist\u002Foffline) | run with `--use-templates false`, or open egress to `data.rcsb.org` |\n| `CUDA out of memory` | large complex \u002F many samples | reduce `--num-diffusion-samples`; the `low_mem` preset (`model_setting_presets.yml`) offloads more aggressively |\n","# OpenFold3 Structure Prediction\n\n## Prerequisites\n\n| Requirement | Minimum | Recommended |\n| ----------- | ------- | ----------- |\n| Python      | 3.10+   | 3.11        |\n| CUDA        | 12.1+   | 12.4+       |\n| GPU VRAM    | 24GB    | 80GB (H100) |\n| RAM         | 32GB    | 64GB        |\n| Disk (weights) | 3GB  | -           |\n\n## How to run\n\n### Installation\n\n```bash\npip install 'openfold3[cuequivariance]==0.4.1'\n```\n\nThe default attention kernel is DeepSpeed `DS4Sci_EvoformerAttention`. If\nDeepSpeed is unavailable, switch to the cuEquivariance triangle kernels (no\nbuild-from-source) by overriding the eval memory settings in\n`model_config.py` (`use_deepspeed_evo_attention: False`,\n`use_cueq_triangle_kernels: True`). Some pre-built environments already ship\nthis override; check before re-patching.\n\n### Weights\n\nApache-2.0, ~2.3 GB from HF `OpenFold\u002FOpenFold3`. The repo is **gated** (auto-approval) — accept the access form on the HF model page and authenticate (`huggingface-cli login` or `HF_TOKEN`) before downloading:\n\n```bash\nexport OPENFOLD_CACHE=~\u002F.openfold3\nhuggingface-cli download OpenFold\u002FOpenFold3 checkpoints\u002Fof3-p2-155k.pt \\\n  --local-dir \"$OPENFOLD_CACHE\"\n```\n\n`run_openfold` will also auto-download to `$OPENFOLD_CACHE` on first run if\negress is open and HF credentials are available (either `HF_TOKEN` or a prior\n`huggingface-cli login`) with repo access granted. The interactive\n`setup_openfold` helper exists but prompts on stdin; prefer the explicit\ndownload above for non-interactive runs.\n\n### Running\n\n```bash\nexport OPENFOLD_CACHE=\u002Fpath\u002Fto\u002Fcache\nrun_openfold predict \\\n  --query_json=queries.json \\\n  --output-dir out\u002F \\\n  --use-msa-server false \\\n  --use-templates false\n```\n\n`run_openfold` discovers the checkpoint under `$OPENFOLD_CACHE` automatically.\nOnly pass `--inference-ckpt-path \u003Cfile.pt>` if you have a non-standard layout\nor multiple checkpoints and need to pin one explicitly.\n\nFor MSA + templates (slower, higher accuracy), drop the two `false` flags. The\nMSA server is `api.colabfold.com`; template chain-ID remap hits\n`data.rcsb.org` (GraphQL) — both must be reachable.\n\n## Query JSON format\n\nOpenFold3 does **not** read FASTA. Queries are a JSON object validated by\n`InferenceQuerySet` (pydantic, `extra: forbid` — unknown keys reject):\n\n```json\n{\n  \"queries\": {\n    \"my_complex\": {\n      \"chains\": [\n        {\"molecule_type\": \"protein\", \"chain_ids\": [\"A\"], \"sequence\": \"MQIFVK…\"},\n        {\"molecule_type\": \"protein\", \"chain_ids\": [\"B\", \"C\"], \"sequence\": \"MVLSPA…\"},\n        {\"molecule_type\": \"ligand\",  \"chain_ids\": [\"L\"], \"smiles\": \"CC(=O)Oc1ccccc1C(=O)O\"}\n      ],\n      \"use_msas\": true\n    }\n  },\n  \"seeds\": [42]\n}\n```\n\n| `molecule_type` | required field |\n| -------- | ---- |\n| `protein` \u002F `dna` \u002F `rna` | `sequence` |\n| `ligand` | `smiles` **or** `ccd_codes: [\"HEM\"]` |\n\n`chain_ids` is a list — repeat the same sequence across multiple chain IDs\nfor homo-oligomers. Per-chain `paired_msa_file_paths` \u002F `main_msa_file_paths`\nlet you supply your own a3m instead of the server.\n\n## Key parameters\n\n| Flag | Default | Description |\n| ---- | ------- | ----------- |\n| `--num-diffusion-samples` | 5 | Structures per (query, seed) |\n| `--num-model-seeds` | 1 | Number of model seeds per query (multiplies output count alongside JSON `seeds` and diffusion samples) |\n| `--use-msa-server` | true | ColabFold MMseqs2 server for MSA |\n| `--use-templates` | true | ColabFold template search + RCSB remap |\n| `--inference-ckpt-path` | auto-discovered under `$OPENFOLD_CACHE` | Override only — for non-standard layouts or to pin a specific checkpoint file |\n\n## Output format\n\n```\nout\u002F\n├── summary.txt\n├── model_config.json \u002F experiment_config.json\n├── inference_query_set.json\n└── \u003Cquery_name>\u002Fseed_\u003CN>\u002F\n    ├── \u003Cquery>_seed_\u003CN>_sample_\u003Ck>_model.cif\n    ├── \u003Cquery>_seed_\u003CN>_sample_\u003Ck>_confidences.json           # full PAE\u002FpLDDT\n    ├── \u003Cquery>_seed_\u003CN>_sample_\u003Ck>_confidences_aggregated.json\n    └── timing.json\n```\n\n`*_confidences_aggregated.json` is the small one to read first:\n\n```json\n{\n  \"avg_plddt\": 78.96, \"ptm\": 0.667, \"iptm\": 0.0, \"gpde\": 0.73,\n  \"has_clash\": 0.0, \"sample_ranking_score\": 0.133,\n  \"chain_ptm\": {\"A\": 0.667}, \"chain_pair_iptm\": {}\n}\n```\n\n## What good output looks like\n\n- `summary.txt` shows `Successful Queries: N` matching your input count\n- avg_plddt > 70 (single-seq) \u002F > 80 (with MSA)\n- ptm > 0.6; for complexes, iptm > 0.5\n- `has_clash: 0.0`\n- `.cif` ~50-150 KB per sample for a small protein\n\n## Verify\n\n```bash\ngrep -E 'Successful|Failed' out\u002Fsummary.txt\nfind out -name '*_model.cif' | wc -l   # = queries x json_seeds x num-model-seeds x num-diffusion-samples\n```\n\n---\n\n## Troubleshooting\n\n| Error | Cause | Fix |\n| ----- | ----- | --- |\n| `_deepspeed_evo_attn requires that DeepSpeed be installed` | default eval kernel is DS4Sci on CUDA | install `deepspeed` (needs nvcc + CUTLASS), **or** in `model_config.py` eval block set `use_deepspeed_evo_attention: False` + `use_cueq_triangle_kernels: True` (cuEq path; no build) |\n| `CUTLASS_PATH ... not set ... cutlass_library is not installed` | cuEq path still needs the python `cutlass_library` shim | `pip install nvidia-cutlass` |\n| `libXrender.so.1: cannot open shared object file` | rdkit (via pdbeccdutils) needs X11 render libs | `apt-get install libxrender1 libxext6 libsm6` |\n| `ModuleNotFoundError: boto3` (or `awscrt`) | `openfold3.core.data.io.s3` is eager-imported even when weights are local | `pip install boto3 awscrt` |\n| `ValidationError: queries \u002F Field required` or `Input should be an object` | wrong JSON shape | top-level is `{\"queries\": {\"\u003Cname>\": {...}}}` (a dict, not a list) |\n| `ValidationError ... settings \u002F Extra inputs are not permitted` | tried to override model config via `--runner-yaml` | `--runner-yaml` is `InferenceExperimentConfig` only; kernel\u002Fmemory settings live in `model_config.py` |\n| `Failed to fetch chain ID mappings from RCSB for N entries` | `data.rcsb.org` unreachable (allowlist\u002Foffline) | run with `--use-templates false`, or open egress to `data.rcsb.org` |\n| `CUDA out of memory` | large complex \u002F many samples | reduce `--num-diffusion-samples`; the `low_mem` preset (`model_setting_presets.yml`) offloads more aggressively |\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","OpenFold3","OpenFold Consortium","https:\u002F\u002Fgithub.com\u002Faqlaboratory\u002Fopenfold-3\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 using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab. Use this skill when predicting protein\u002Fnucleic-acid\u002Fligand complex structures with an Apache-2.0-licensed AF3 reimplementation.\n",[39],"gpu","main","e71245365df78e06cd166602744bf2491f79910e","research-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Fopenfold3",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 openfold3",{"tool":55,"command":56},"bunx","bunx skills add pengqianhan\u002FAI-Human-Research-OS --skill openfold3",{"tool":58,"command":59},"pnpm","pnpm dlx skills add pengqianhan\u002FAI-Human-Research-OS --skill openfold3","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\u002Fopenfold3\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",[],[]]