tooluniverse-precision-oncology

Provide actionable treatment recommendations for cancer patients based on molecular profile. Interprets tumor mutations, identifies FDA-approved therapies, finds resistance mechanisms, matches clinical trials. Use when oncologist asks about treatment options for specific mutations (EGFR, KRAS, BRAF, etc.), therapy resistance, or clinical trial eligibility.

Quality

63%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/med/tooluniverse-precision-oncology/SKILL.md

Quality

Content

27%

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

The skill is thorough and domain-rich but far too verbose and self-contained for a SKILL.md, with illustrative/fabricated output blocks and a missing referenced file. Splitting detail into bundled reference files and trimming redundant explanations would substantially improve it.

Suggestions

Move per-database code examples and tool-summary tables into bundled reference files (e.g., references/databases.md) and keep SKILL.md as a concise workflow overview.

Remove fabricated sample output tables (e.g., COSMIC counts, DepMap effect scores) or clearly label them as illustrative templates rather than real data.

Complete partial functions such as model_resistance_mechanism so they return a value, and add an explicit validate-on-failure loop for Phase 0 tool parameter verification.

Dimension	Reasoning	Score
Conciseness	The ~1090-line body is padded with many duplicated tool-summary tables, illustrative output blocks with fabricated numbers, and verbose 'Why X matters' explanations that restate domain knowledge Claude already has.	1 / 3
Actionability	Code snippets are concrete and parameterized, but many are partial (e.g., model_resistance_mechanism ends with a comment instead of returning a result) and outputs contain placeholder/fabricated values rather than copy-paste-ready logic.	2 / 3
Workflow Clarity	Phases are clearly sequenced and a completeness checklist exists, but Phase 0 tool verification has no validation feedback loop and the early '2.4 Output Table' heading is mislabeled/duplicated, leaving some checkpoints implicit.	2 / 3
Progressive Disclosure	It is a monolithic SKILL.md that inlines every phase's code and tables; the only external pointer is TOOLS_REFERENCE.md, which does not exist in the bundle, so deep detail is not split out.	1 / 3
	Total	6 / 12 Passed

Description

100%

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

The description is concrete, well-scoped, and includes explicit trigger guidance with natural user phrasing. It clearly separates what the skill does from when to use it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Interprets tumor mutations, identifies FDA-approved therapies, finds resistance mechanisms, matches clinical trials') that map to specific capabilities.	3 / 3
Completeness	Explicitly answers what ('Provide actionable treatment recommendations') and when ('Use when oncologist asks about treatment options...') with an explicit 'Use when' clause.	3 / 3
Trigger Term Quality	Natural triggers an oncologist would say appear ('treatment options', 'therapy resistance', 'clinical trial eligibility') alongside gene/mutation names users mention.	3 / 3
Distinctiveness Conflict Risk	The precision-oncology niche, named databases (CIViC, ClinVar, ClinicalTrials.gov), and biomarker-specific triggers make it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1092 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/med/tooluniverse-precision-oncology/SKILL.md
Commit: df37802

Reviewed: 2 days 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.