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.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

73%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.

A well-structured, actionable skill with strong workflow sequencing and validation feedback loops. The main weakness is conciseness: it teaches general oncology concepts Claude already knows alongside the tool-specific guidance.

Suggestions

Trim general-knowledge explanations (TNM staging definitions, grade definitions, TMB/MSI thresholds) and keep only tool-relevant framing to improve token efficiency.

Consider moving the 'Tumor Classification Reasoning' and 'Evidence Grading' teaching content into a separate reference file, keeping SKILL.md as a lean overview with tool workflows.

Verify or annotate response-shape accessors in code patterns (e.g. results["data"][0]["code"]) so examples are guaranteed executable against actual tool responses.

Dimension	Reasoning	Score
Conciseness	Mostly efficient tool guidance, but several sections explain general oncology knowledge Claude already has (TNM staging 'T=tumor size, N=lymph nodes, M=metastasis', grade definitions, TMB/MSI thresholds) that could be trimmed without loss.	3 / 5
Actionability	Provides concrete, copy-ready tool invocations and code patterns covering common cases (OncoTree_search, OncoKB_annotate_variant, validation patterns), with minor gaps where response-shape accessors are illustrative rather than verified.	4 / 5
Workflow Clarity	A clear four-phase sequence (Discovery -> Validation -> Tissue Exploration -> Downstream Use) with explicit validation checkpoints ('Always validate via OncoTree_get_type before downstream use') and a fallback-chains table providing error-recovery feedback loops.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and no nested references (self-contained, no bundle files), though the substantial biomarker/staging/evidence-grading teaching content could arguably be externalized into a reference file.	4 / 5
	Total	16 / 20 Passed

Description

87%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, specific description that clearly states both capabilities and trigger conditions for a well-scoped oncology ontology skill. Minor improvement possible by converting some 'Use for' use-cases into capability verbs.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Translate free-text tumor descriptions to OncoTree codes', 'resolve cancer subtypes/tissue hierarchy', 'Cross-references UMLS/NCI vocabularies'), though the trailing 'Use for' clause enumerates use cases rather than additional capabilities, leaving minor gaps.	4 / 5
Completeness	Explicitly answers both 'what' (translate/resolve/cross-reference) and 'when' via a concrete 'Use for ...' clause listing specific trigger scenarios, matching the anchor for clearly answering both.	5 / 5
Trigger Term Quality	Good coverage of natural domain terms users would say ('OncoTree code', 'cancer subtypes', 'tumor-board notes', 'OncoKB', 'GDC', 'EHR free-text'), with a few common phrasings missing; not the exhaustive synonym/extension coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (OncoTree cancer classification with UMLS/NCI cross-references) with distinct, specialized triggers unlikely to fire for unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-cancer-classification/SKILL.md
Commit: 1b02920

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.