cosmic-database

Access COSMIC to download mutation datasets, query Cancer Gene Census, and retrieve mutational signatures when your genomic analysis requires curated somatic mutation resources.

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/cosmic-database/SKILL.md

Quality

Content

46%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 content offers a concrete example and a real one-level reference, but suffers from duplicated boilerplate sections, a non-functional script stub, and missing validation in a batch download workflow. Dependency statements also conflict (Python 3.10+ vs 3.9+).

Suggestions

Remove the duplicated generic boilerplate sections (first When to Use/Key Features/Dependencies/Example Usage/Implementation Details block) and keep only the real, domain-specific content.

Add a validation checkpoint to the download workflow (verify HTTP status, confirm GZIP integrity/decompression, retry on auth failure) so the batch operation clears the workflow-clarity cap.

Resolve the conflicting Python version requirements and make the download script functional (or clearly mark it as illustrative) so the example is genuinely executable.

Dimension	Reasoning	Score
Conciseness	The body duplicates entire sections (When to Use, Key Features, Dependencies, Example Usage, Implementation Details) as generic boilerplate alongside the real content, creating substantial redundancy and padding.	2 / 5
Actionability	A concrete Python example is provided, but the underlying script is a non-functional stub whose own comments admit the auth approach is generalized and may not match the real COSMIC API, so the example is not genuinely executable end-to-end.	3 / 5
Workflow Clarity	Steps are listed, but this batch download workflow has no validation checkpoint (no checksum/integrity verification, no auth-failure retry) — per the rubric cap, a batch operation without validation cannot score above 3.	3 / 5
Progressive Disclosure	references/cosmic_data_reference.md is a real file, clearly signaled one level deep, and the overview points to it; structure is good despite the inlined duplicate sections.	4 / 5
	Total	12 / 20 Passed

Description

67%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 concrete and domain-specific with both a clear what and when, though trigger-term coverage misses common synonyms and file extensions. It is well-distinguished from other skills.

Suggestions

Add natural file-format keywords (TSV, VCF, SBS, DBS, ID) and the CGC acronym to broaden trigger-term coverage.

Tighten the 'when' clause to reference concrete user phrasing (e.g. 'when you need curated somatic mutation datasets for cohort analysis').

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('download mutation datasets', 'query Cancer Gene Census', 'retrieve mutational signatures') but stays at a high level without naming file formats or dataset types, leaving minor gaps in coverage.	4 / 5
Completeness	Explicitly states both what it does (download/query/retrieve) and when to use it ('when your genomic analysis requires curated somatic mutation resources'), with the 'when' clause present but only moderately specific.	4 / 5
Trigger Term Quality	Includes relevant domain keywords (Cancer Gene Census, mutational signatures) but omits common synonyms and file extensions users would naturally say (TSV/VCF, SBS/DBS, CGC).	3 / 5
Distinctiveness Conflict Risk	The COSMIC-specific niche with distinct, specialized triggers makes it clearly distinguishable from other skills with minimal conflict risk.	5 / 5
	Total	16 / 20 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: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/cosmic-database/SKILL.md
Commit: 63c61d3

Reviewed: 3 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.