← Tamarind BioCONTENT HISTORY

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.

WHAT CHANGED

Instructions updated for tamarind-mcp-binder-design

Full description — Now says: candidates for clearly benign research, diagnostic, or therapeutic discovery.

Observed in instructions or declared skills. Runtime behavior has not been tested.

Save Tamarind Bio and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Full description

Before

Sep 30, 2026 · 22:50 UTC

candidates.

After

Oct 27, 2026 · 00:11 UTC

candidates for clearly benign research, diagnostic, or therapeutic discovery.

Skill instructions

Before

Sep 30, 2026 · 22:50 UTC

candidates. Use for de novo generation when MCP is requested. Not for antibody CDR engineering, fixed-backbone inverse folding, docking an existing ligand, or predicting an existing structure. Rank on multiple signals: independent refold...

After

Oct 27, 2026 · 00:11 UTC

candidates for clearly benign research, diagnostic, or therapeutic discovery. Use for de novo generation when MCP is requested. Not for antibody CDR engineering, fixed-backbone inverse folding, docking an existing ligand, or predicting a...

Supporting files

Before

Sep 30, 2026 · 22:50 UTC

[]

After

Oct 27, 2026 · 00:11 UTC

[{"relative_path":"agents/openai.yaml","size_in_bytes":432}]

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -1,12 +1,20 @@
 ---
 name: tamarind-mcp-binder-design
-description: Design new protein, peptide, macrocycle, or small-molecule binders against a target with Tamarind Bio through MCP, then refold and rank candidates. Use for de novo generation when MCP is requested. Not for antibody CDR engineering, fixed-backbone inverse folding, docking an existing ligand, or predicting an existing structure.
+description: Design new protein, peptide, macrocycle, or small-molecule binders against a target with Tamarind Bio through MCP, then refold and rank candidates for clearly benign research, diagnostic, or therapeutic discovery. Use for de novo generation when MCP is requested. Not for antibody CDR engineering, fixed-backbone inverse folding, docking an existing ligand, or predicting an existing structure.
 ---
 
 # Design de novo binders through MCP
 
 Treat binder design as a generate-and-filter campaign, not a deterministic answer.
 
+## Confirm scope
+
+Before uploading data or calling generation tools, establish the target identity
+and intended application. Proceed only for clearly benign research, diagnostic,
+or therapeutic discovery. If either is missing or ambiguous, ask for clarification
+and do not call generation tools. Decline requests intended to cause harm or enable
+harmful biological activity.
+
 ## Define and select
 
 Clarify the target structure or sequence, target chains/site/hotspots, binder class, length or chemistry constraints, candidate count, and downstream filters. Use `tamarind-mcp-antibody` for antibody or VHH CDR workflows.
@@ -25,4 +33,4 @@
 
 For many generated sequences, use one bounded `submitBatch` rather than individual submissions. Use `fromJob` only when the downstream schema expects each generated sequence by itself in `sequenceField`. When refolding target-binder complexes that require a combined target and candidate per row, build explicit `settings` plus matching `jobNames` instead; a naive `fromJob` batch could fold the binder alone. Validate every final complex row, estimate the fan-out, and reconfirm scope when it materially expands.
 
-Rank on multiple signals: independent refold confidence, interface geometry, target-site satisfaction, liabilities, uniqueness, and diversity. Carry a diverse shortlist into wet-lab testing; never optimize on one metric alone.
+Rank on multiple signals: independent refold confidence, interface geometry, target-site satisfaction, liabilities, uniqueness, and diversity. Return a diverse shortlist for downstream experimental evaluation; never optimize on one metric alone.
Full technical diff · 3 changed fields

changed /description

BEFORE
"Design new protein, peptide, macrocycle, or small-molecule binders against a target with Tamarind Bio through MCP, then refold and rank candidates. Use for de novo generation when MCP is requested. Not for antibody CDR engineering, fixed-backbone inverse folding, docking an existing ligand, or predicting an existing structure."
AFTER
"Design new protein, peptide, macrocycle, or small-molecule binders against a target with Tamarind Bio through MCP, then refold and rank candidates for clearly benign research, diagnostic, or therapeutic discovery. Use for de novo generation when MCP is requested. Not for antibody CDR engineering, fixed-backbone inverse folding, docking an existing ligand, or predicting an existing structure."

changed /included_files

BEFORE
[]
AFTER
[
  {
    "relative_path": "agents/openai.yaml",
    "size_in_bytes": 432
  }
]

changed /skill_md_contents

BEFORE
"---\nname: tamarind-mcp-binder-design\ndescription: Design new protein, peptide, macrocycle, or small-molecule binders against a target with Tamarind Bio through MCP, then refold and rank candidates. Use for de novo generation when MCP is requested. Not for antibody CDR engineering, fixed-backbone inverse folding, docking an existing ligand, or predicting an existing structure.\n---\n\n# Design de novo binders through MCP\n\nTreat binder design as a generate-and-filter campaign, not a deterministic answer.\n\n## Define and select\n\nClarify the target structure or sequence, target chains/site/hotspots, binder class, length or chemistry constraints, candidate count, and downstream filters. Use `tamarind-mcp-antibody` for antibody or VHH CDR workflows.\n\nCall `getAvailableTools(function=\"binder-design\")`. For small-molecule generation, discover the exact current function with `listTags` before filtering. Inspect the chosen model with `getJobSchema`; do not assume a remembered name or field remains available.\n\n## Validate generation\n\nUpload the target with `uploadFile`, or use an accepted `s3Path` from `listJobFiles`. Build only fields supported by the live schema and call `validateJob`. Require `valid: true` with no mutation warning.\n\nCall `estimateTime`. Surface candidate count, sampling budget or steps, target site, scaffold or length range, refolding, filters, and estimated spend. Candidate count often dominates cost, so obtain explicit authorization for the validated scope.\n\n## Execute the funnel\n\nRun the generation stage with `tamarind-mcp-submit-and-poll`. Use `listJobFiles` to identify the actual sequence or structure outputs.\n\nFor many generated sequences, use one bounded `submitBatch` rather than individual submissions. Use `fromJob` only when the downstream schema expects each generated sequence by itself in `sequenceField`. When refolding target-binder complexes that require a combined target and candidate per row, build explicit `settings` plus matching `jobNames` instead; a naive `fromJob` batch could fold the binder alone. Validate every final complex row, estimate the fan-out, and reconfirm scope when it materially expands.\n\nRank on multiple signals: independent refold confidence, interface geometry, target-site satisfaction, liabilities, uniqueness, and diversity. Carry a diverse shortlist into wet-lab testing; never optimize on one metric alone.\n"
AFTER
"---\nname: tamarind-mcp-binder-design\ndescription: Design new protein, peptide, macrocycle, or small-molecule binders against a target with Tamarind Bio through MCP, then refold and rank candidates for clearly benign research, diagnostic, or therapeutic discovery. Use for de novo generation when MCP is requested. Not for antibody CDR engineering, fixed-backbone inverse folding, docking an existing ligand, or predicting an existing structure.\n---\n\n# Design de novo binders through MCP\n\nTreat binder design as a generate-and-filter campaign, not a deterministic answer.\n\n## Confirm scope\n\nBefore uploading data or calling generation tools, establish the target identity\nand intended application. Proceed only for clearly benign research, diagnostic,\nor therapeutic discovery. If either is missing or ambiguous, ask for clarification\nand do not call generation tools. Decline requests intended to cause harm or enable\nharmful biological activity.\n\n## Define and select\n\nClarify the target structure or sequence, target chains/site/hotspots, binder class, length or chemistry constraints, candidate count, and downstream filters. Use `tamarind-mcp-antibody` for antibody or VHH CDR workflows.\n\nCall `getAvailableTools(function=\"binder-design\")`. For small-molecule generation, discover the exact current function with `listTags` before filtering. Inspect the chosen model with `getJobSchema`; do not assume a remembered name or field remains available.\n\n## Validate generation\n\nUpload the target with `uploadFile`, or use an accepted `s3Path` from `listJobFiles`. Build only fields supported by the live schema and call `validateJob`. Require `valid: true` with no mutation warning.\n\nCall `estimateTime`. Surface candidate count, sampling budget or steps, target site, scaffold or length range, refolding, filters, and estimated spend. Candidate count often dominates cost, so obtain explicit authorization for the validated scope.\n\n## Execute the funnel\n\nRun the generation stage with `tamarind-mcp-submit-and-poll`. Use `listJobFiles` to identify the actual sequence or structure outputs.\n\nFor many generated sequences, use one bounded `submitBatch` rather than individual submissions. Use `fromJob` only when the downstream schema expects each generated sequence by itself in `sequenceField`. When refolding target-binder complexes that require a combined target and candidate per row, build explicit `settings` plus matching `jobNames` instead; a naive `fromJob` batch could fold the binder alone. Validate every final complex row, estimate the fan-out, and reconfirm scope when it materially expands.\n\nRank on multiple signals: independent refold confidence, interface geometry, target-site satisfaction, liabilities, uniqueness, and diversity. Return a diverse shortlist for downstream experimental evaluation; never optimize on one metric alone.\n"
Full snapshot data
{
  "description": "Design new protein, peptide, macrocycle, or small-molecule binders against a target with Tamarind Bio through MCP, then refold and rank candidates for clearly benign research, diagnostic, or therapeutic discovery. Use for de novo generation when MCP is requested. Not for antibody CDR engineering, fixed-backbone inverse folding, docking an existing ligand, or predicting an existing structure.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 432
    }
  ],
  "name": "tamarind-mcp-binder-design",
  "skill_md_contents": "---\nname: tamarind-mcp-binder-design\ndescription: Design new protein, peptide, macrocycle, or small-molecule binders against a target with Tamarind Bio through MCP, then refold and rank candidates for clearly benign research, diagnostic, or therapeutic discovery. Use for de novo generation when MCP is requested. Not for antibody CDR engineering, fixed-backbone inverse folding, docking an existing ligand, or predicting an existing structure.\n---\n\n# Design de novo binders through MCP\n\nTreat binder design as a generate-and-filter campaign, not a deterministic answer.\n\n## Confirm scope\n\nBefore uploading data or calling generation tools, establish the target identity\nand intended application. Proceed only for clearly benign research, diagnostic,\nor therapeutic discovery. If either is missing or ambiguous, ask for clarification\nand do not call generation tools. Decline requests intended to cause harm or enable\nharmful biological activity.\n\n## Define and select\n\nClarify the target structure or sequence, target chains/site/hotspots, binder class, length or chemistry constraints, candidate count, and downstream filters. Use `tamarind-mcp-antibody` for antibody or VHH CDR workflows.\n\nCall `getAvailableTools(function=\"binder-design\")`. For small-molecule generation, discover the exact current function with `listTags` before filtering. Inspect the chosen model with `getJobSchema`; do not assume a remembered name or field remains available.\n\n## Validate generation\n\nUpload the target with `uploadFile`, or use an accepted `s3Path` from `listJobFiles`. Build only fields supported by the live schema and call `validateJob`. Require `valid: true` with no mutation warning.\n\nCall `estimateTime`. Surface candidate count, sampling budget or steps, target site, scaffold or length range, refolding, filters, and estimated spend. Candidate count often dominates cost, so obtain explicit authorization for the validated scope.\n\n## Execute the funnel\n\nRun the generation stage with `tamarind-mcp-submit-and-poll`. Use `listJobFiles` to identify the actual sequence or structure outputs.\n\nFor many generated sequences, use one bounded `submitBatch` rather than individual submissions. Use `fromJob` only when the downstream schema expects each generated sequence by itself in `sequenceField`. When refolding target-binder complexes that require a combined target and candidate per row, build explicit `settings` plus matching `jobNames` instead; a naive `fromJob` batch could fold the binder alone. Validate every final complex row, estimate the fan-out, and reconfirm scope when it materially expands.\n\nRank on multiple signals: independent refold confidence, interface geometry, target-site satisfaction, liabilities, uniqueness, and diversity. Return a diverse shortlist for downstream experimental evaluation; never optimize on one metric alone.\n"
}

SHA-256 of public snapshot: 311cf476cad72eca9d9829583c57361dc46cdcd909b4a1872ba76f98ce5db573