{"id":7439,"plugin_id":"plugin_asdk_app_6a5fc156fad88191a3977b60131d7391","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T22:50:37.641Z","digest":"7d83c222663ff79aaa94398b7f842380a7d77d458075ad449b0d64daf125dd3e","against":null,"payload":{"name":"tamarind-mcp-structure-prediction","description":"Predict or co-fold proteins, peptides, nucleic acids, ligands, or biomolecular complexes with Tamarind Bio through MCP. Use for live AlphaFold-, Boltz-, Chai-, ESMFold-, or Protenix-style structure workflows when MCP is requested. Not for de novo binder generation, antibody-specific modeling, or docking into a known pocket.","included_files":[],"skill_md_contents":"---\nname: tamarind-mcp-structure-prediction\ndescription: Predict or co-fold proteins, peptides, nucleic acids, ligands, or biomolecular complexes with Tamarind Bio through MCP. Use for live AlphaFold-, Boltz-, Chai-, ESMFold-, or Protenix-style structure workflows when MCP is requested. Not for de novo binder generation, antibody-specific modeling, or docking into a known pocket.\n---\n\n# Predict biomolecular structures through MCP\n\nUse the live catalog and schema; model availability and settings change.\n\n## Choose the model family\n\nCall `getAvailableTools(function=\"structure-prediction\")`, then inspect candidates with `getJobSchema`.\n\n- Prefer a live co-folding model for multi-chain, ligand, or nucleic-acid complexes when its schema supports every component.\n- Prefer a fast single-sequence model when one protein fold and low latency are sufficient.\n- Route Fv, VHH, or TCR-specific work to `tamarind-mcp-antibody`.\n- Route known-receptor pocket or pose work to `tamarind-mcp-docking`.\n\nDo not copy payloads between model families.\n\n## Build and validate\n\nRepresent every molecule in the exact field and format required by the live schema. Upload file inputs with `uploadFile` and use the returned bare filename, or use an exact prior-job `s3Path` accepted by the schema.\n\nCall `validateJob`. Require `valid: true` with no `mutatedFields`. Validation does not identify molecule type: confirm that DNA/RNA is routed to nucleotide inputs rather than a protein sequence field.\n\nCall `estimateTime`, then surface consequential settings such as sample/model count, MSA, recycles, model/version, templates or restraints, affinity calculation, and output format. Keep tuned defaults unless the user intentionally changes them. A production canary should minimize input size and independent samples without forcing quality parameters to unsafe minima.\n\n## Execute and interpret\n\nUse `tamarind-mcp-submit-and-poll` for authorization, one submission, bounded status polling, and targeted output retrieval.\n\nReport local confidence, global fold confidence, and interface confidence separately. High pLDDT alone does not prove a correct complex interface; inspect pTM, ipTM, ipSAE, pDockQ, or model-specific fields when present. Treat confidence as model evidence, not experimental validation, and require geometry inspection before recommending a structure.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}