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

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%

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

Highly actionable with executable examples and precise tool reference, but the single monolithic file could offload detail to bundle files and the showcased workflows lack validation feedback between steps.

Suggestions

Move the duplicated Tool Quick Reference table and/or the Programmatic Access GDC-API bulk code into a reference bundle file, keeping SKILL.md as an overview with one-level-deep links, to improve progressive disclosure and remove redundancy.

Add explicit validation/feedback steps to the example workflows (e.g., check the returned status field, handle empty data by re-confirming project_id, retry on truncation) so multi-step sequences have checkpoints.

Trim or fold the Synthesis Questions and advisory Reasoning Framework prose into the tool sections where they apply, reducing tokens that don't directly drive action.

Dimension	Reasoning	Score
Conciseness	Most content earns its place (tool signatures and return shapes Claude cannot know), but the Tool Quick Reference table duplicates the per-phase tool detail and the Synthesis Questions section is advisory padding. It is not 3 because of this redundancy, and not 1 because there is no concept-padding Claude already knows.	2 / 3
Actionability	Provides multiple complete, executable Python blocks (clinical data, mutations, CNV, survival, OncoKB) plus concrete parameter signatures and return-shape specs that are copy-paste ready. It is not 2 because the examples are real executable code rather than pseudocode.	3 / 3
Workflow Clarity	A clear 6-phase overview and explicit checkpoints (cohort-first, 'LOOK UP DON'T GUESS', pagination break-loop) exist, but the showcased example workflows (Workflow 1-3) are linear with no validation or feedback between steps. It is not 3 because error-recovery feedback loops between workflow steps are absent; not 1 because the sequence and some checkpoints are present.	2 / 3
Progressive Disclosure	Sections are well-organized, but the skill is a monolithic 328-line single file with no bundle-file references, and content that could be split (Programmatic Access GDC API bulk code, Reasoning Framework) is inline. It is not 3 because nothing is split into one-level-deep references; not 1 because organization is good, not a wall of text.	2 / 3
	Total	9 / 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.

A strong, third-person description that concisely states concrete capabilities, gives an explicit 'Use for' trigger clause, and scopes a clear cancer-genomics niche with a boundary against pan-cancer misuse.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'cohort construction, clinical metadata retrieval, somatic mutation frequencies, survival analysis, and multi-omics integration' — matching the anchor for specific concrete actions, not vague language.	3 / 3
Completeness	Explicitly answers both what (the action list) and when ('Use for TCGA-BRCA-style cohort studies, mutation prevalence by cancer type, survival-by-mutation analysis, and pan-cancer driver discovery'), with an explicit 'Use for' trigger clause. It is not 2 because the 'when' is stated explicitly, not merely implied.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — 'TCGA', 'GDC', 'cancer cohort', 'somatic mutation', 'survival analysis', 'mutation frequency', 'TCGA-BRCA-style' — with good breadth and common variations, matching the high-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Clear cancer-genomics niche with distinct triggers and an explicit boundary ('Always cancer-type-specific (don't use pan-cancer counts without cohort context)'), unlikely to trigger for the wrong skill. It is not 2 because the domain is narrowly scoped rather than broadly overlapping.	3 / 3
	Total	12 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-cancer-genomics-tcga/SKILL.md
Commit: 089eb8e

Reviewed: about 6 hours 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.