CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-cancer-variant-interpretation

Clinical interpretation of somatic cancer mutations for precision oncology. Transforms a gene + variant + cancer-type input into an actionable report: clinical evidence tier (CIViC, OncoKB), therapeutic options (FDA-approved + investigational), resistance mechanisms, prognosis, and matching clinical trials. Use for tumor-board variant calls, somatic-mutation actionability assessment, and treatment selection. Always cancer-type-specific.

68

Quality

81%

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

SKILL.md
Quality
Evals
Security

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, actionable clinical workflow with strong tool-parameter verification and reasoning guidance. The main defect is a broken progressive-disclosure reference: ANALYSIS_DETAILS.md is cited but not shipped, leaving the detailed code snippets it promises unavailable.

Suggestions

Ship the missing ANALYSIS_DETAILS.md (or place it under references/) so the 'detailed code snippets and API call patterns for each phase' reference resolves; alternatively inline the few key code snippets and drop the reference.

Add explicit validation checkpoints between phases (e.g., 'before Phase 4, confirm a CIViC variant match exists; if not, run the PubMed fallback') rather than only the upfront Phase 0 check and the trailing fallback list.

Tighten the Clinical Reasoning Strategies prose — convert explanatory sentences like 'Not every mutation in a tumor is driving the cancer' into directive bullets to recover token budget.

DimensionReasoningScore

Conciseness

Mostly efficient with dense, useful tool tables and lean principle statements, though the Clinical Reasoning Strategies section carries prose ('Not every mutation in a tumor is driving the cancer') that could be trimmed.

4 / 5

Actionability

Highly concrete tool/parameter guidance — verified WRONG-vs-CORRECT parameter tables, response key fields, and fallback rules — but no inline executable code snippets; those are deferred to the missing ANALYSIS_DETAILS.md, a minor gap.

4 / 5

Workflow Clarity

Eight clearly sequenced phases with a CRITICAL Phase 0 parameter-verification checkpoint and a Fallback Strategy error-recovery loop, but lacks explicit per-phase validation checkpoints and the completeness checklist mentioned in Phase 8 is not actually provided.

4 / 5

Progressive Disclosure

Well-sectioned structure with a clearly signaled one-level reference ('see ANALYSIS_DETAILS.md'), but that file is absent from the bundle (no references/ directory exists), so the promised detailed code snippets are unreachable — a broken reference rather than a minor gap.

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 strong, third-person description that clearly states both capability and use-cases with concrete actions and natural trigger phrases. Minor synonym coverage gaps in trigger terms keep it just below a perfect profile.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'clinical evidence tier (CIViC, OncoKB)', 'therapeutic options (FDA-approved + investigational)', 'resistance mechanisms', 'prognosis', 'matching clinical trials' — giving comprehensive coverage of what the skill produces.

5 / 5

Completeness

Explicitly answers both 'what' ('Transforms a gene + variant + cancer-type input into an actionable report: ...') and 'when' with a concrete 'Use for ...' trigger clause, satisfying the top anchor.

5 / 5

Trigger Term Quality

Good natural trigger coverage with 'tumor-board variant calls', 'somatic-mutation actionability assessment', and 'treatment selection', but misses common synonyms a user might say such as 'is this mutation targetable' or 'interpret this mutation'.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — clinical interpretation of somatic cancer mutations for precision oncology — with distinct, domain-specific triggers and minimal overlap risk 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.