CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-cancer-genomics-tcga

TCGA/GDC cancer genomics analysis — cohort construction, clinical metadata retrieval, somatic mutation frequencies, survival analysis, and multi-omics integration. Use for TCGA-BRCA-style cohort studies, mutation prevalence by cancer type, survival-by-mutation analysis, and pan-cancer driver discovery. Always cancer-type-specific (don't use pan-cancer counts without cohort context).

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

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

SKILL.md
Quality
Evals
Security

Quality

Content

76%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.

The body is highly actionable and well-structured with executable examples across all phases, but lacks explicit validation/feedback checkpoints for its batch retrieval operations, and could split long reference-style sections into bundle files. It is concise overall with only mild redundancy.

Suggestions

Add explicit validation checkpoints in batch flows — e.g., for the pagination loop check `len(hits)` / response `status` before extending and abort on API errors, and for survival results verify `overallStats.pValue` exists before interpreting.

Factor the Programmatic Access bulk-pull patterns and the Reasoning Framework into bundle reference files (e.g., references/bulk-gdc-api.md) to move detail one level deep and tighten the SKILL.md overview.

Dedupe the pan-cancer-only caveat — state it once in Limitations and reference it from Phase 3 rather than repeating across the intro, Phase 3, and Reasoning Framework.

DimensionReasoningScore

Conciseness

Largely lean and reference-style with executable snippets and parameter schemas, but the pan-cancer-only caveat and a few cautions recur across the intro, Reasoning Framework, and Limitations, leaving minor trim opportunities.

4 / 5

Actionability

Copy-paste-ready Python calls with exact parameters, return-shape schemas, and concrete coordinates (e.g., chr7:55019017-55211628) cover the common cases across all six phases, plus a Quick Reference table.

5 / 5

Workflow Clarity

A clear six-phase sequence with end-to-end example workflows, but validation/checkpoint steps are absent for batch operations (pagination loops, bulk clinical pulls, demo-mode token handling), which the rubric caps at 3.

3 / 5

Progressive Disclosure

Well-organized with clear headers and signaled one-level-deep sibling-skill references, but the ~328-line body is monolithic with no split-out reference files and one non-link external reference, leaving minor organization gaps.

4 / 5

Total

16

/

20

Passed

Description

100%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.

The description is strong across all dimensions: concrete capabilities, natural trigger terms, explicit what/when guidance, and a distinct, well-bounded niche with conflict guardrails. No changes needed.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('cohort construction, clinical metadata retrieval, somatic mutation frequencies, survival analysis, and multi-omics integration'), matching the comprehensive-coverage anchor rather than the 4-anchor's 'minor gaps'.

5 / 5

Completeness

Explicitly states both what (the five analysis capabilities) and when ('Use for TCGA-BRCA-style cohort studies, mutation prevalence by cancer type, survival-by-mutation analysis, and pan-cancer driver discovery') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers natural user terms broadly — 'TCGA', 'GDC', 'cancer cohort', 'somatic mutation', 'Kaplan-Meier', 'survival analysis', 'CNV', 'mutation frequency' — including synonyms and format tokens, fitting the comprehensive anchor.

5 / 5

Distinctiveness Conflict Risk

A sharply scoped cancer-genomics niche with explicit guardrails ('Always cancer-type-specific (don't use pan-cancer counts without cohort context)') and named sibling skills, yielding minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

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.