tooluniverse-precision-oncology

Cancer treatment recommendations from molecular profile (mutations + cancer type + biomarkers) — FDA-approved + investigational therapies, resistance mechanisms, matching clinical trials, prognosis. Uses CIViC, ClinVar, OpenTargets, ClinicalTrials.gov. Use for tumor-board treatment recommendations, evidence-tiered actionability assessment, and FDA-precedent-driven therapy selection.

Quality

81%

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

71%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, highly actionable precision-oncology skill body with clear phased workflows and concrete tool guidance. Its main weakness is progressive disclosure: the detailed reference files it points to are missing from the bundle, and a fair amount of reference-grade content is inlined.

Suggestions

Ship the six referenced .md files (TOOLS_REFERENCE.md, API_USAGE_PATTERNS.md, TREATMENT_ALGORITHMS.md, REPORT_TEMPLATE.md, EXAMPLES.md, CHECKLIST.md) in the bundle so the navigation links resolve instead of dead-ending.

Move the per-phase 'Key Tools by Phase' listings and the biomarker-to-drug mapping tables into TOOLS_REFERENCE.md / TREATMENT_ALGORITHMS.md, keeping only a concise overview and the decision-time reasoning in SKILL.md.

Add an explicit validate-and-retry loop (e.g., re-query on empty CIViC results, confirm FAERS data was retrieved before report finalization) to push workflow_clarity to the top anchor.

Dimension	Reasoning	Score
Conciseness	Dense and information-rich, assuming Claude's competence (no explaining what CIViC or a mutation is); however the 'Domain Reasoning' and 'Resistance mechanism reasoning' prose sections, while high-value, could be tightened, so it sits just below the leanest anchor.	4 / 5
Actionability	Provides concrete tool names with parameters (e.g., `civic_search_evidence_items` with `molecular_profile="EGFR C797S"`), a WRONG/CORRECT param-correction table, and a copy-paste cross-skill command; minor gaps in that no full worked end-to-end call sequences are shown.	4 / 5
Workflow Clarity	A clearly sequenced Phase 0-6 workflow with explicit mandatory checkpoints (Phase 0 tool verification, MANDATORY FAERS in Phase 5.5, 'LOOK UP DON'T GUESS'); lacks an explicit validate-fix-retry feedback loop, keeping it just below the top anchor.	4 / 5
Progressive Disclosure	Good section structure and a clearly signaled one-level-deep References list, but the six referenced .md files (TOOLS_REFERENCE, API_USAGE_PATTERNS, TREATMENT_ALGORITHMS, REPORT_TEMPLATE, EXAMPLES, CHECKLIST) are absent from the bundle (dead links), and substantial tool-listing and biomarker-algorithm content that belongs in those files is inlined in SKILL.md.	3 / 5
	Total	15 / 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 high-quality, third-person description that concretely states capabilities and provides an explicit 'Use for' trigger clause tied to a well-scoped precision-oncology niche. Minor room to add a few more colloquial trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'FDA-approved + investigational therapies, resistance mechanisms, matching clinical trials, prognosis' — giving comprehensive coverage of the skill's capabilities, matching the top anchor.	5 / 5
Completeness	Explicitly answers 'what' (treatment recommendations from molecular profile using named databases) and 'when' via a concrete 'Use for tumor-board treatment recommendations, evidence-tiered actionability assessment, and FDA-precedent-driven therapy selection' trigger clause.	5 / 5
Trigger Term Quality	Strong natural terms ('tumor-board treatment recommendations', 'molecular profile', 'biomarkers', 'clinical trials') plus named data sources, but a few common variations a user might say ('drug options', 'what treatments') are absent, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	A clearly defined precision-oncology niche with distinct triggers (tumor-board, evidence-tiered actionability, FDA-precedent therapy selection) and named databases, giving minimal overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 6 missing	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-precision-oncology/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.