Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mims-harvard/tooluniverse-cancer-classification
Translate free-text tumor descriptions to OncoTree codes and resolve cancer subtypes/tissue hierarchy. Cross-references UMLS/NCI vocabularies.
Passed 4 of 11 test cases with the skill, and 5 of 11 without it.
and 3 more in the full report
4 fixed5 passed either way9 still failing5 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
After executing a free-text search for 'pancreatic ductal adenocarcinoma' and receiving candidate codes, what mandatory verification step must be performed before passing a candidate code to downstream tools like OncoKB?
| Checked | Without skill | With skill |
|---|---|---|
| Requires validating candidate codes using OncoTree_get_type before downstream tool usage. | Missed | Passed |
The instructions your model reads when the skill loads.
Standardize cancer type nomenclature using the OncoTree ontology. Resolves free-text tumor descriptions to structured codes with UMLS/NCI cross-references, enabling downstream use in OncoKB variant annotation and GDC cohort selection.
Apply when researcher asks about:
| Tool | Purpose | Key Params |
|---|---|---|
OncoTree_search | Free-text search for cancer types | query (tumor name or description) |
OncoTree_get_type | Full details for a known OncoTree code | code (e.g., "LUAD", "AML") |
OncoTree_list_tissues | List all 32 tissue categories | (no params) |
OncoKB_annotate_variant | Variant annotation using OncoTree code | gene, variant, tumor_type |
GDC_get_mutation_frequency | Pan-cancer mutation frequency (TCGA) | gene_symbol |
Start with free-text search to find matching OncoTree codes:
OncoTree_search(query="breast cancer")
-> Returns list: code, name, main_type, tissue, parent, level, external_references
Key response fields:
code: OncoTree code (e.g., "BRCA", "IBC") — use this in OncoKB callstest cases passed, vs 5 / 11 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.