CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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).

Quality

83%

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

63%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 a well-organized, domain-rich reference with a clear phased workflow and concrete tool documentation. Its main weaknesses are token duplication (tool details appear twice), an internal p-value contradiction, missing ToolUniverse setup context for the examples, and no progressive disclosure of the API-reference material into bundle files.

Suggestions

Eliminate the duplication between the per-phase tool sections and the 'Tool Quick Reference' table — keep one (the table) and reference it from the phases, cutting roughly a quarter of the body's tokens.

Fix the p-value contradiction: Phase 5 correctly states the tool returns 'no log-rank p-value', but the Quick Reference says 'Kaplan-Meier donor array + pValue' and Workflow 1 step 3 promises a 'p-value' — align all three to Phase 5's accurate account.

Show the ToolUniverse setup (e.g., 'import tooluniverse as tu') once so the 'tu.tools.*' examples are copy-paste runnable, and move the per-tool API details and the 'Programmatic Access' section into a references/ file for progressive disclosure.

DimensionReasoningScore

Conciseness

The body is dense with domain-specific data Claude doesn't know (tool params, return shapes, NCIt codes), but it is noticeably redundant: every tool's params and returns appear both in the phase sections and again in the 'Tool Quick Reference' table, the example workflows re-state phase-level calls, and a 'verified 2026-09-21' date sits in a code comment. Mostly efficient but needs tightening matches the 3 anchor.

3 / 5

Actionability

Concrete tool signatures with parameter types, return-shape documentation, realistic Python examples, and a bulk GDC API script make the guidance mostly executable. Two gaps hold it below 5: the examples use 'tu.tools.*' with no setup/import shown anywhere, and the Tool Quick Reference and Workflow 1 claim a 'pValue'/'p-value' that Phase 5 explicitly says the tool does not return.

4 / 5

Workflow Clarity

A clear six-phase sequence with an ASCII overview, a confirm-first checkpoint ('LOOK UP DON'T GUESS', 'confirm a project exists... before deeper queries'), example workflows, and a limitations section. Checkpoints are present but implicit rather than explicit validate-and-recover loops, matching the 4 anchor; no destructive/batch cap applies since all operations are read-only queries.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so all material — per-tool API reference, reasoning framework, and programmatic bulk access — is inlined in a ~330-line single file. Sections are well-organized with clear headers, but API-reference content that would naturally live in a separate file is inline, matching the 3 anchor.

3 / 5

Total

14

/

20

Passed

Description

96%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 description: concrete, comprehensive action list with an explicit 'Use for...' clause and rich natural trigger terms including synonyms. The only weakness is that the precision-oncology boundary lives in the body rather than the description, leaving minor overlap risk.

DimensionReasoningScore

Specificity

The description lists five concrete actions ('cohort construction, clinical metadata retrieval, somatic mutation frequencies, survival analysis, and multi-omics integration') that comprehensively cover the analysis pipeline. This matches the anchor for multiple specific concrete actions with comprehensive coverage, not the 'minor gaps' of a 4.

5 / 5

Completeness

Both 'what' (cohort construction, clinical metadata retrieval, somatic mutation frequencies, survival analysis, multi-omics integration) and 'when' ('Use for TCGA-BRCA-style cohort studies, mutation prevalence by cancer type, survival-by-mutation analysis, and pan-cancer driver discovery') are explicitly stated with concrete trigger phrases, plus boundary guidance ('Always cancer-type-specific').

5 / 5

Trigger Term Quality

Trigger terms include natural user phrasings with synonyms: 'TCGA', 'GDC', 'cancer cohort', 'somatic mutation', 'Kaplan-Meier', 'survival analysis', 'CNV', 'copy number variation', 'mutation frequency', 'overall survival', plus patterns like 'TCGA-' and 'mutation frequency in'. Coverage is comprehensive including both abbreviations and full synonyms, matching the 5 anchor.

5 / 5

Distinctiveness Conflict Risk

The TCGA/GDC/Progenetix/OncoKB trigger vocabulary carves a clear niche, but the description itself omits the boundary with the closely related precision-oncology skill (stated only in the body's 'NOT for' section), and OncoKB variant annotation overlaps that skill's territory. Minor overlap risk with a closely related skill matches the 4 anchor.

4 / 5

Total

19

/

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.

Validation — 15 / 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

Path

plugins/tooluniverse/skills/tooluniverse-cancer-genomics-tcga/SKILL.md

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.