{"id":57219,"plugin_id":"plugin_asdk_app_6a5fc156fad88191a3977b60131d7391","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-10-27T00:11:09.905Z","digest":"a7885b6f9d7786f5ad9236fb8c38a5b91b6ea2c760ef9084101a085ca80da40d","against":7342,"payload":{"description":"Dock or screen known ligands against a receptor, perform protein-protein docking, or score existing poses and complexes with Tamarind Bio through MCP. Use for pocket-based or blind docking and pose ranking. Not for sequence co-folding, generating a new ligand or binder, or general structure prediction.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":423}],"name":"tamarind-mcp-docking","skill_md_contents":"---\nname: tamarind-mcp-docking\ndescription: Dock or screen known ligands against a receptor, perform protein-protein docking, or score existing poses and complexes with Tamarind Bio through MCP. Use for pocket-based or blind docking and pose ranking. Not for sequence co-folding, generating a new ligand or binder, or general structure prediction.\n---\n\n# Dock and score through MCP\n\nStart from the input the user actually has: receptor structure, ligand or SMILES/library, known pocket box, or an existing complex.\n\n## Select the method\n\nCall `listTags` when needed, then query `getAvailableTools` for protein-ligand docking, protein-protein docking, or binding affinity. Inspect the exact candidate with `getJobSchema`.\n\n- Prefer box-based physics docking when pocket coordinates are known.\n- Prefer blind methods only when the live schema supports the available inputs.\n- Prefer score-only tools for a pose or complex that already exists.\n- Fold sequence-only inputs before sending them to structure-only docking fields.\n\nClosely related tools use different receptor, ligand, box, exhaustiveness, and scoring fields. Never transfer a sibling payload without schema inspection.\n\n## Prepare and run\n\nUpload receptor or ligand files with `uploadFile`, or use exact accepted `s3Path` values from successful upstream jobs. Keep receptor and ligand separate when required.\n\nCall `validateJob` and `estimateTime`. Confirm blind versus box docking, pocket definition, ligand count, pose count, exhaustiveness or sampling, rescoring, and estimated spend. Route a library to `tamarind-mcp-batch` or a schema-supported file batch instead of looping `submitJob`.\n\nUse `tamarind-mcp-submit-and-poll`. Retrieve poses and score tables by calling `listJobFiles` before targeted `getJobFile` calls.\n\nReport whether lower energy/affinity or higher model confidence is better. Check pose geometry and interactions; docking scores prioritize candidates but do not prove experimental binding.\n"},"changes":[{"path":"/included_files","type":"changed","before":[],"after":[{"relative_path":"agents/openai.yaml","size_in_bytes":423}]}],"summary":"Fields changed: 1. /included_files.","summary_kind":"deterministic","summary_metadata":{}}