CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-cancer-classification

Translate free-text tumor descriptions to OncoTree codes and resolve cancer subtypes/tissue hierarchy. Cross-references UMLS/NCI vocabularies. Use for standardizing cancer-type nomenclature in EHR free-text, building cohorts in OncoKB or GDC, mapping tumor-board notes to ontology codes, and ensuring consistent terminology across cancer-genomics pipelines.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is tooluniverse-cancer-classification in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable and well-sequenced content with strong validation and fallback guidance, weakened by general oncology education that pads the context budget and by a monolithic single-file structure with no progressive disclosure to supporting reference files.

Suggestions

Trim or relocate the general oncology primers (staging vs grading, biomarker definitions, histological vs molecular basics) — Claude already knows these; keep only skill-specific interpretation guidance tied to the tools.

Extract the 'Common OncoTree Codes' table and the 'Tumor Classification Reasoning' framework into a reference file (e.g., references/oncotree-codes.md) referenced from SKILL.md to improve progressive disclosure.

Move the detailed biomarker interpretation strategy into a separate reference, keeping the SKILL.md body focused on tool invocation patterns and validation steps.

DimensionReasoningScore

Conciseness

Tool-specific guidance (param tables, code patterns, verified codes) is efficient, but the 'Tumor Classification Reasoning' section pads with general oncology education Claude already knows — e.g., TNM staging definitions, Grade 1-3 explanations, and biomarker primers (HER2, ER/PR, Ki67, TMB, MSI) — that could be trimmed without losing skill value.

3 / 5

Actionability

Provides copy-paste-ready code patterns with concrete params (e.g., OncoTree_search(query='pancreatic ductal adenocarcinoma')), a tool parameter reference with required/optional columns, a verified-working codes table, and example return payloads — fully executable and covering common cases.

5 / 5

Workflow Clarity

Four-phase workflow (Discovery → Validation → Tissue Exploration → Downstream Use) is clearly sequenced with explicit validation checkpoints ('Always validate via OncoTree_get_type before using in downstream tools', status-check before OncoKB) and a Fallback Chains table providing error-recovery feedback loops.

5 / 5

Progressive Disclosure

Sections are well-organized with clear headers, but ~200 lines are entirely inline with no external reference files; content like the detailed oncology reasoning framework and the common-codes table could be split into separate reference files for easier navigation, and no bundle files exist to offload it.

3 / 5

Total

16

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that explicitly covers both capability and trigger contexts with concrete, domain-specific language. Minor room to surface verbatim user query phrasings alongside the use-case framing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Translate free-text tumor descriptions to OncoTree codes', 'resolve cancer subtypes/tissue hierarchy', 'Cross-references UMLS/NCI vocabularies', 'mapping tumor-board notes to ontology codes' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Clearly answers 'what' (translate descriptions to OncoTree codes, resolve subtypes/tissue hierarchy, cross-reference UMLS/NCI) and explicitly answers 'when' via 'Use for standardizing cancer-type nomenclature in EHR free-text, building cohorts in OncoKB or GDC, mapping tumor-board notes...' with concrete trigger contexts.

5 / 5

Trigger Term Quality

Strong domain keyword coverage (OncoTree, OncoKB, GDC, UMLS/NCI, EHR free-text, tumor-board notes, cancer-genomics) that researchers would naturally use, though trigger phrasings are framed as use-cases rather than verbatim user queries, leaving a few natural variants uncovered.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (OncoTree cancer-type coding with UMLS/NCI cross-references and OncoKB/GDC integration) with domain-specific triggers that minimize overlap with other skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mims-harvard/ToolUniverse
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.