Update to Tamarind Bio
Snapshot Oct 27, 2026 · 00:11 UTC · version 2.0.1
Collection source: downloaded plugin package. These snapshots do not have a confirmed matching collection source. Differences in file lists alone do not establish changes to the package.
Instructions updated for tamarind-mcp-tool-discovery
Skill instructions — Now says: - A multi-method binder campaign ranked on a scoring method fixed in advance: use `tamarind-mcp-miniprotein-campaign`.
Observed in instructions or declared skills. Runtime behavior has not been tested.
Up to 3 plugins free · no card required.
All fields and original values.
Skill instructions
Sep 30, 2026 · 22:50 UTC
No removed lines (ordering may have changed)
Oct 27, 2026 · 00:11 UTC
- A multi-method binder campaign ranked on a scoring method fixed in advance: use `tamarind-mcp-miniprotein-campaign`.
Supporting files
Sep 30, 2026 · 22:50 UTC
[]
Oct 27, 2026 · 00:11 UTC
[{"relative_path":"agents/openai.yaml","size_in_bytes":438}]
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -30,5 +30,6 @@ - One known job: use the matching MCP domain skill plus `tamarind-mcp-submit-and-poll`. - One tool over many inputs: use `tamarind-mcp-batch`. - Dependent stages: use `tamarind-mcp-pipeline`. +- A multi-method binder campaign ranked on a scoring method fixed in advance: use `tamarind-mcp-miniprotein-campaign`. Compute trivial local properties locally when a standard library can answer them quickly. Reserve Tamarind for managed inference, durable artifacts, or platform workflows.
Full technical diff · 2 changed fields
changed /included_files
[]
[
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 438
}
]changed /skill_md_contents
"---\nname: tamarind-mcp-tool-discovery\ndescription: Choose a Tamarind Bio tool by querying the live MCP catalog and schema. Use when the user requests MCP, has not named a tool, several tools could fit, or availability and required inputs must be verified. Not for reconnecting OAuth or executing a tool that is already selected.\n---\n\n# Choose a live Tamarind tool\n\nNever recommend a tool from memory alone. The catalog is account-scoped and changes over time.\n\n## Narrow the catalog\n\n1. Identify the input already available: sequence, structure, receptor plus ligand, fixed backbone, labeled table, density map, or library.\n2. Identify the required output: structure, pose, affinity, designed sequence, generated molecule, embedding, property score, or ranked candidates.\n3. Call `listModalities` and `listTags` when the correct facet values are not known.\n4. Call `getAvailableTools` with `modality`, `function`, or a narrow `search`. Avoid an unfiltered catalog response.\n5. Inspect the strongest candidate with `getJobSchema(jobType=...)`.\n\nRecommend one primary tool and at most two conditional alternatives. Explain the input or scientific condition that changes the choice; avoid unsupported best-in-class claims.\n\n## Treat the schema as authority\n\nConfirm required fields, types, enum values, conditionals, defaults, file inputs, and account-visible variants. Do not copy settings between sibling models.\n\nFor a concrete proposed payload, call `validateJob` with a durable probe name. Require `valid: true` and no `mutatedFields` warning. Validation is free and does not authorize a paid run. If a file field fails because the file is absent, upload it with `uploadFile` or choose an exact `s3Path` from `listJobFiles`; do not guess a path.\n\nValidation checks schema and character constraints, not scientific identity. Confirm molecule type independently, especially when nucleotide letters could also be parsed as amino-acid codes.\n\n## Route execution\n\n- One known job: use the matching MCP domain skill plus `tamarind-mcp-submit-and-poll`.\n- One tool over many inputs: use `tamarind-mcp-batch`.\n- Dependent stages: use `tamarind-mcp-pipeline`.\n\nCompute trivial local properties locally when a standard library can answer them quickly. Reserve Tamarind for managed inference, durable artifacts, or platform workflows.\n"
"---\nname: tamarind-mcp-tool-discovery\ndescription: Choose a Tamarind Bio tool by querying the live MCP catalog and schema. Use when the user requests MCP, has not named a tool, several tools could fit, or availability and required inputs must be verified. Not for reconnecting OAuth or executing a tool that is already selected.\n---\n\n# Choose a live Tamarind tool\n\nNever recommend a tool from memory alone. The catalog is account-scoped and changes over time.\n\n## Narrow the catalog\n\n1. Identify the input already available: sequence, structure, receptor plus ligand, fixed backbone, labeled table, density map, or library.\n2. Identify the required output: structure, pose, affinity, designed sequence, generated molecule, embedding, property score, or ranked candidates.\n3. Call `listModalities` and `listTags` when the correct facet values are not known.\n4. Call `getAvailableTools` with `modality`, `function`, or a narrow `search`. Avoid an unfiltered catalog response.\n5. Inspect the strongest candidate with `getJobSchema(jobType=...)`.\n\nRecommend one primary tool and at most two conditional alternatives. Explain the input or scientific condition that changes the choice; avoid unsupported best-in-class claims.\n\n## Treat the schema as authority\n\nConfirm required fields, types, enum values, conditionals, defaults, file inputs, and account-visible variants. Do not copy settings between sibling models.\n\nFor a concrete proposed payload, call `validateJob` with a durable probe name. Require `valid: true` and no `mutatedFields` warning. Validation is free and does not authorize a paid run. If a file field fails because the file is absent, upload it with `uploadFile` or choose an exact `s3Path` from `listJobFiles`; do not guess a path.\n\nValidation checks schema and character constraints, not scientific identity. Confirm molecule type independently, especially when nucleotide letters could also be parsed as amino-acid codes.\n\n## Route execution\n\n- One known job: use the matching MCP domain skill plus `tamarind-mcp-submit-and-poll`.\n- One tool over many inputs: use `tamarind-mcp-batch`.\n- Dependent stages: use `tamarind-mcp-pipeline`.\n- A multi-method binder campaign ranked on a scoring method fixed in advance: use `tamarind-mcp-miniprotein-campaign`.\n\nCompute trivial local properties locally when a standard library can answer them quickly. Reserve Tamarind for managed inference, durable artifacts, or platform workflows.\n"
Full snapshot data
{
"description": "Choose a Tamarind Bio tool by querying the live MCP catalog and schema. Use when the user requests MCP, has not named a tool, several tools could fit, or availability and required inputs must be verified. Not for reconnecting OAuth or executing a tool that is already selected.",
"included_files": [
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 438
}
],
"name": "tamarind-mcp-tool-discovery",
"skill_md_contents": "---\nname: tamarind-mcp-tool-discovery\ndescription: Choose a Tamarind Bio tool by querying the live MCP catalog and schema. Use when the user requests MCP, has not named a tool, several tools could fit, or availability and required inputs must be verified. Not for reconnecting OAuth or executing a tool that is already selected.\n---\n\n# Choose a live Tamarind tool\n\nNever recommend a tool from memory alone. The catalog is account-scoped and changes over time.\n\n## Narrow the catalog\n\n1. Identify the input already available: sequence, structure, receptor plus ligand, fixed backbone, labeled table, density map, or library.\n2. Identify the required output: structure, pose, affinity, designed sequence, generated molecule, embedding, property score, or ranked candidates.\n3. Call `listModalities` and `listTags` when the correct facet values are not known.\n4. Call `getAvailableTools` with `modality`, `function`, or a narrow `search`. Avoid an unfiltered catalog response.\n5. Inspect the strongest candidate with `getJobSchema(jobType=...)`.\n\nRecommend one primary tool and at most two conditional alternatives. Explain the input or scientific condition that changes the choice; avoid unsupported best-in-class claims.\n\n## Treat the schema as authority\n\nConfirm required fields, types, enum values, conditionals, defaults, file inputs, and account-visible variants. Do not copy settings between sibling models.\n\nFor a concrete proposed payload, call `validateJob` with a durable probe name. Require `valid: true` and no `mutatedFields` warning. Validation is free and does not authorize a paid run. If a file field fails because the file is absent, upload it with `uploadFile` or choose an exact `s3Path` from `listJobFiles`; do not guess a path.\n\nValidation checks schema and character constraints, not scientific identity. Confirm molecule type independently, especially when nucleotide letters could also be parsed as amino-acid codes.\n\n## Route execution\n\n- One known job: use the matching MCP domain skill plus `tamarind-mcp-submit-and-poll`.\n- One tool over many inputs: use `tamarind-mcp-batch`.\n- Dependent stages: use `tamarind-mcp-pipeline`.\n- A multi-method binder campaign ranked on a scoring method fixed in advance: use `tamarind-mcp-miniprotein-campaign`.\n\nCompute trivial local properties locally when a standard library can answer them quickly. Reserve Tamarind for managed inference, durable artifacts, or platform workflows.\n"
}SHA-256 of public snapshot: 3a473082ff97a7f8e744c5b4802b427162b07b07a82477a1684f88317c0337f5