← Tamarind BioCONTENT HISTORY
WHAT CHANGED
changed
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.
Supporting file metadata differs
Supporting file metadata differs
Observed in package metadata. These changes alone do not establish a new customer-facing feature.
Save Tamarind Bio and check future changes in Following.
Up to 3 plugins free · no card required.
All fields and original values.
Supporting files
Before
Sep 30, 2026 · 22:50 UTC
[]
After
Oct 27, 2026 · 00:11 UTC
[{"relative_path":"agents/openai.yaml","size_in_bytes":424}]
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
No SKILL.md text changes between these observations.
Full technical diff · 1 changed fields
changed /included_files
BEFORE
[]
AFTER
[
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 424
}
]Full snapshot data
{
"description": "Run one Tamarind Bio tool across many independent inputs with one MCP submitBatch call, then monitor subjobs and rank completed results. Use for libraries, screens, generated-sequence refolding, or repeated inference. Not for one input, dependent tool stages, loops of submitJob, or CLI batches.",
"included_files": [
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 424
}
],
"name": "tamarind-mcp-batch",
"skill_md_contents": "---\nname: tamarind-mcp-batch\ndescription: Run one Tamarind Bio tool across many independent inputs with one MCP submitBatch call, then monitor subjobs and rank completed results. Use for libraries, screens, generated-sequence refolding, or repeated inference. Not for one input, dependent tool stages, loops of submitJob, or CLI batches.\n---\n\n# Run a Tamarind MCP batch\n\nA batch multiplies throughput and possible weighted-hour spend. Keep one tool and one scientific settings policy across the batch.\n\n## Choose one input mode\n\nInspect the tool with `getJobSchema`, then use exactly one `submitBatch` mode:\n\n1. `fromJob`: use a completed sequence-design job as the source when every downstream row consists of that generated sequence in one `sequenceField`.\n2. `fromFile`: use a workspace FASTA/CSV filename or an exact prior-job `s3Path`.\n3. `settings` plus matching `jobNames`: use explicit per-job settings when rows need full individual control.\n\nUse `topN` to bound generated-sequence fan-out and `sharedSettings` only for fields valid for every generated row. Do not call `submitJob` in a loop.\n\n`fromJob` and `fromFile` do not construct target-candidate complexes. If the downstream schema requires a combined target and candidate value such as `TARGET:BINDER`, build explicit per-row `settings` plus `jobNames`; otherwise the batch may fold or score the candidate alone.\n\n## Validate and estimate\n\nFor explicit mode, call `validateJob` for every final row when feasible and at least every distinct conditional shape for very large inputs. Require `valid: true` without `mutatedFields`. Check duplicate names, file availability, input count, sampling settings, and schema compatibility.\n\nFor `fromJob` or `fromFile`, inspect the source and validate a representative final settings object containing the intended sequence field and shared settings. Treat server-side expansion as consequential even when not all generated rows can be prevalidated client-side.\n\nCall `estimateTime` for each distinct settings shape. Multiply by the intended row count or use the returned expansion count. Surface the total count, wall-clock interpretation, and weighted hours when available.\n\nAuthorization for multiplied spend must come from the live user. If a numeric ceiling is specified, pass `weightedHoursBudget` to `submitBatch`; if the estimate cannot verify the ceiling, stop. A no-spend validation or setup request never authorizes the batch.\n\n## Submit once\n\nCall `submitBatch` exactly once with a unique `batchName`, one tool `type`, the chosen input mode, optional per-job timeout, and authorized budget.\n\nIf the result is ambiguous, do not call `submitBatch` again. Query `getJobs(batch=BATCH_NAME, includeSubjobs=true)` and the parent name first.\n\n## Monitor with a bound\n\nPoll `getJobs(batch=..., includeSubjobs=true)` at a moderate interval through the client's bounded wait/session mechanism. Track completed, active, failed, and stopped counts. Do not hide partial failures behind an aggregate status.\n\nStop after a finite deadline and report the batch as still active; never resubmit because a local wait ended. For failed subjobs, inspect a bounded number of representative logs with `getJobLogs` rather than flooding context.\n\nUse `cancelBatch` to stop the whole active batch after confirming its exact name. Do not fan out `cancelJob` calls.\n\n## Rank results\n\nRank only successful terminal subjobs. Keep incomplete, unknown-status, and unscored rows explicitly unranked. Confirm metric direction: affinity, energy, PAE, RMSD, Kd/Ki, and IC50 are commonly lower-better, while confidence scores are commonly higher-better.\n\nUse `listJobFiles` and targeted `getJobFile` calls for selected subjobs. Return the batch name, input mode, total and per-status counts, budget/weighted hours when present, ranking metric and direction, shortlisted artifacts, and limitations.\n"
}SHA-256 of public snapshot: ec717798b7b0df61143bed62f7f9bbf722087831868b050727287fc03cf77d18