Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →clawbio/omics-target-evidence-mapper
Aggregate public target-level evidence across omics and translational sources for research triage.
Passed 15 of 18 test cases with the skill, and 4 of 18 without it.
and 14 more in the full report
13 fixed5 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
Compose the exact CLI execution command to map evidence for gene CDK4 and disease breast cancer, saving to directory cdk4_eval, limiting PubMed papers to 8 and trials to 3.
| Checked | Without skill | With skill |
|---|---|---|
| uses --gene CDK4 | Passed | Passed |
| uses --disease "breast cancer" | Passed | Passed |
| uses --max-papers 8 | Missed | Passed |
| uses --max-trials 3 | Passed | Passed |
The instructions your model reads when the skill loads.
Researchers often need a quick first-pass view of whether a gene or protein target has evidence across multiple public sources. In practice, this usually means checking several websites manually and informally combining results. This skill makes that process reproducible by retrieving and organising public evidence into one structured output.
This skill is for research triage only. It does not infer causality, rank therapeutic value, or make clinical recommendations.
| Argument | Required | Example | Notes |
|---|---|---|---|
--gene | Yes, unless --demo is used | IL6R | Gene or target symbol |
--disease | No | coronary artery disease | Optional disease context |
--output | Yes | demo_out | Output directory |
--max-papers | No | 5 | Number of PubMed hits to include |
--max-trials | No | 5 | Number of trial records to include |
--demo | No | --demo | Runs the built-in demo query |
reproducibility/checksums.sha256 — SHA-256 hashes of all output filesreproducibility/environment.yml — pinned Conda/pip environmentro-crate-metadata.json — RO-Crate 1.1 provenance record (run params, outputs, script)test cases passed, vs 4 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.