{"id":57213,"plugin_id":"plugin_asdk_app_6a5fc156fad88191a3977b60131d7391","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-10-27T00:11:09.718Z","digest":"b6088706bbf6a77f0b8b14b2acfa136f253372dd9edbb937d5db587cf51d3251","against":7291,"payload":{"description":"Design, redesign, model, number, humanize, or search antibodies, nanobodies, VHHs, and TCRs with Tamarind Bio through MCP. Use for CDR-aware and repertoire-specific workflows when MCP is requested. Not for generic non-antibody binder design, ordinary complex folding, or developability scoring alone.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":435}],"name":"tamarind-mcp-antibody","skill_md_contents":"---\nname: tamarind-mcp-antibody\ndescription: Design, redesign, model, number, humanize, or search antibodies, nanobodies, VHHs, and TCRs with Tamarind Bio through MCP. Use for CDR-aware and repertoire-specific workflows when MCP is requested. Not for generic non-antibody binder design, ordinary complex folding, or developability scoring alone.\n---\n\n# Engineer antibodies through MCP\n\nClarify antibody versus VHH/nanobody/TCR and the goal: de novo CDR design, redesign, structure prediction, numbering, humanization, or repertoire/paratope search.\n\n## Select and inspect\n\nCall `getAvailableTools(modality=\"antibody\")`. Narrow with a live function such as antibody design or structure prediction, then call `getJobSchema` for the strongest fit.\n\nPrefer antibody-specific tools when chain pairing, CDR regions, framework numbering, epitope/hotspot steering, or humanization matters. Route generic co-folding to `tamarind-mcp-structure-prediction` and non-antibody binders to `tamarind-mcp-binder-design`.\n\n## Build and validate\n\nCapture the heavy/light or VHH sequence, framework, antigen structure and chain, epitope or hotspots, CDR regions and lengths, candidate count, and excluded residues required by the live schema. Upload structures with `uploadFile` and use the returned filename or an accepted prior-job `s3Path`.\n\nCall `validateJob`, require no mutation warning, and call `estimateTime`. Confirm chain identities, numbering scheme, CDR scope, candidate count, refolding plan, filters, and estimated spend before submission.\n\n## Execute and filter\n\nUse `tamarind-mcp-submit-and-poll`. For multiple independent candidates, use `tamarind-mcp-batch` rather than repeated `submitJob` calls.\n\nRank design outputs on interface confidence and geometry, then apply antibody-specific developability filters through `tamarind-mcp-developability`. Preserve sequence diversity and flag liabilities instead of selecting only the top scalar score. Predictions prioritize experiments; they do not replace binding and developability assays.\n"},"changes":[{"path":"/included_files","type":"changed","before":[],"after":[{"relative_path":"agents/openai.yaml","size_in_bytes":435}]}],"summary":"Fields changed: 1. /included_files.","summary_kind":"deterministic","summary_metadata":{}}