← 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-developability

Full description — Now says: MCP for clearly benign research, diagnostic, or therapeutic development.

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

MCP.

After

Oct 27, 2026 · 00:11 UTC

MCP for clearly benign research, diagnostic, or therapeutic development.

Skill instructions

Before

Sep 30, 2026 · 22:50 UTC

MCP. Use as a post-design filter. Not for generating molecules, folding structures, or measuring binding alone. Upload structures with `uploadFile` or use an accepted prior-job `s3Path`. Call `validateJob` and `estimateTime` for each pla...

After

Oct 27, 2026 · 00:11 UTC

MCP for clearly benign research, diagnostic, or therapeutic development. Use as a post-design filter. Not for generating molecules, folding structures, or measuring binding alone. ## Confirm scope Before uploading data or calling scoring...

Supporting files

Before

Sep 30, 2026 · 22:50 UTC

[]

After

Oct 27, 2026 · 00:11 UTC

[{"relative_path":"agents/openai.yaml","size_in_bytes":437}]

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -1,19 +1,27 @@
 ---
 name: tamarind-mcp-developability
-description: Score protein or antibody candidates for stability, aggregation, solubility, viscosity, polyreactivity, glycosylation, immunogenicity, and related developability risks with Tamarind Bio through MCP. Use as a post-design filter. Not for generating molecules, folding structures, or measuring binding alone.
+description: Score protein or antibody candidates for stability, aggregation, solubility, viscosity, polyreactivity, glycosylation, immunogenicity, and related developability risks with Tamarind Bio through MCP for clearly benign research, diagnostic, or therapeutic development. Use as a post-design filter. Not for generating molecules, folding structures, or measuring binding alone.
 ---
 
 # Filter candidates for developability
 
 Treat developability as a panel of orthogonal risks, not one universal score.
 
+## Confirm scope
+
+Before uploading data or calling scoring tools, establish the candidates and
+intended application. Proceed only for clearly benign research, diagnostic,
+or therapeutic development. If either is missing or ambiguous, ask for clarification
+before running the tools. Decline requests intended to cause harm or enable
+harmful biological activity.
+
 ## Select the panel
 
 Call `listTags` to obtain current function values, then use filtered `getAvailableTools` calls for developability, stability, aggregation, solubility, immunogenicity, or another relevant axis. Inspect each selected tool with `getJobSchema`.
 
 Match the input type and modality. Sequence-only, structure-based, paired-antibody, and nanobody-specific tools are not interchangeable.
 
-Upload structures with `uploadFile` or use an accepted prior-job `s3Path`. Call `validateJob` and `estimateTime` for each planned tool. For a candidate list, use `tamarind-mcp-batch` so one settings policy is applied consistently; validate every distinct conditional payload shape before multiplying the run.
+Upload structures with `uploadFile` or use an accepted prior-job `s3Path`. Call `validateJob` and `estimateTime` for each planned tool. For a candidate list, use `tamarind-mcp-batch` so one settings policy is applied consistently; validate the whole row set in one `validateJob` call before multiplying the run.
 
 ## Execute and interpret
 
Full technical diff · 3 changed fields

changed /description

BEFORE
"Score protein or antibody candidates for stability, aggregation, solubility, viscosity, polyreactivity, glycosylation, immunogenicity, and related developability risks with Tamarind Bio through MCP. Use as a post-design filter. Not for generating molecules, folding structures, or measuring binding alone."
AFTER
"Score protein or antibody candidates for stability, aggregation, solubility, viscosity, polyreactivity, glycosylation, immunogenicity, and related developability risks with Tamarind Bio through MCP for clearly benign research, diagnostic, or therapeutic development. Use as a post-design filter. Not for generating molecules, folding structures, or measuring binding alone."

changed /included_files

BEFORE
[]
AFTER
[
  {
    "relative_path": "agents/openai.yaml",
    "size_in_bytes": 437
  }
]

changed /skill_md_contents

BEFORE
"---\nname: tamarind-mcp-developability\ndescription: Score protein or antibody candidates for stability, aggregation, solubility, viscosity, polyreactivity, glycosylation, immunogenicity, and related developability risks with Tamarind Bio through MCP. Use as a post-design filter. Not for generating molecules, folding structures, or measuring binding alone.\n---\n\n# Filter candidates for developability\n\nTreat developability as a panel of orthogonal risks, not one universal score.\n\n## Select the panel\n\nCall `listTags` to obtain current function values, then use filtered `getAvailableTools` calls for developability, stability, aggregation, solubility, immunogenicity, or another relevant axis. Inspect each selected tool with `getJobSchema`.\n\nMatch the input type and modality. Sequence-only, structure-based, paired-antibody, and nanobody-specific tools are not interchangeable.\n\nUpload structures with `uploadFile` or use an accepted prior-job `s3Path`. Call `validateJob` and `estimateTime` for each planned tool. For a candidate list, use `tamarind-mcp-batch` so one settings policy is applied consistently; validate every distinct conditional payload shape before multiplying the run.\n\n## Execute and interpret\n\nUse `tamarind-mcp-submit-and-poll` for a single candidate and `tamarind-mcp-batch` for many independent candidates.\n\nReport every risk axis separately with the tool, units, direction, and threshold rationale. Preserve a Pareto set when candidates trade affinity against solubility, stability, or immunogenicity. Computational predictions prioritize assays and formulation work; they do not replace them.\n"
AFTER
"---\nname: tamarind-mcp-developability\ndescription: Score protein or antibody candidates for stability, aggregation, solubility, viscosity, polyreactivity, glycosylation, immunogenicity, and related developability risks with Tamarind Bio through MCP for clearly benign research, diagnostic, or therapeutic development. Use as a post-design filter. Not for generating molecules, folding structures, or measuring binding alone.\n---\n\n# Filter candidates for developability\n\nTreat developability as a panel of orthogonal risks, not one universal score.\n\n## Confirm scope\n\nBefore uploading data or calling scoring tools, establish the candidates and\nintended application. Proceed only for clearly benign research, diagnostic,\nor therapeutic development. If either is missing or ambiguous, ask for clarification\nbefore running the tools. Decline requests intended to cause harm or enable\nharmful biological activity.\n\n## Select the panel\n\nCall `listTags` to obtain current function values, then use filtered `getAvailableTools` calls for developability, stability, aggregation, solubility, immunogenicity, or another relevant axis. Inspect each selected tool with `getJobSchema`.\n\nMatch the input type and modality. Sequence-only, structure-based, paired-antibody, and nanobody-specific tools are not interchangeable.\n\nUpload structures with `uploadFile` or use an accepted prior-job `s3Path`. Call `validateJob` and `estimateTime` for each planned tool. For a candidate list, use `tamarind-mcp-batch` so one settings policy is applied consistently; validate the whole row set in one `validateJob` call before multiplying the run.\n\n## Execute and interpret\n\nUse `tamarind-mcp-submit-and-poll` for a single candidate and `tamarind-mcp-batch` for many independent candidates.\n\nReport every risk axis separately with the tool, units, direction, and threshold rationale. Preserve a Pareto set when candidates trade affinity against solubility, stability, or immunogenicity. Computational predictions prioritize assays and formulation work; they do not replace them.\n"
Full snapshot data
{
  "description": "Score protein or antibody candidates for stability, aggregation, solubility, viscosity, polyreactivity, glycosylation, immunogenicity, and related developability risks with Tamarind Bio through MCP for clearly benign research, diagnostic, or therapeutic development. Use as a post-design filter. Not for generating molecules, folding structures, or measuring binding alone.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 437
    }
  ],
  "name": "tamarind-mcp-developability",
  "skill_md_contents": "---\nname: tamarind-mcp-developability\ndescription: Score protein or antibody candidates for stability, aggregation, solubility, viscosity, polyreactivity, glycosylation, immunogenicity, and related developability risks with Tamarind Bio through MCP for clearly benign research, diagnostic, or therapeutic development. Use as a post-design filter. Not for generating molecules, folding structures, or measuring binding alone.\n---\n\n# Filter candidates for developability\n\nTreat developability as a panel of orthogonal risks, not one universal score.\n\n## Confirm scope\n\nBefore uploading data or calling scoring tools, establish the candidates and\nintended application. Proceed only for clearly benign research, diagnostic,\nor therapeutic development. If either is missing or ambiguous, ask for clarification\nbefore running the tools. Decline requests intended to cause harm or enable\nharmful biological activity.\n\n## Select the panel\n\nCall `listTags` to obtain current function values, then use filtered `getAvailableTools` calls for developability, stability, aggregation, solubility, immunogenicity, or another relevant axis. Inspect each selected tool with `getJobSchema`.\n\nMatch the input type and modality. Sequence-only, structure-based, paired-antibody, and nanobody-specific tools are not interchangeable.\n\nUpload structures with `uploadFile` or use an accepted prior-job `s3Path`. Call `validateJob` and `estimateTime` for each planned tool. For a candidate list, use `tamarind-mcp-batch` so one settings policy is applied consistently; validate the whole row set in one `validateJob` call before multiplying the run.\n\n## Execute and interpret\n\nUse `tamarind-mcp-submit-and-poll` for a single candidate and `tamarind-mcp-batch` for many independent candidates.\n\nReport every risk axis separately with the tool, units, direction, and threshold rationale. Preserve a Pareto set when candidates trade affinity against solubility, stability, or immunogenicity. Computational predictions prioritize assays and formulation work; they do not replace them.\n"
}

SHA-256 of public snapshot: 0802808cfb7b48c0b8d393c654aaa638c038951fb852fcd06833934ec3886d9b