cosmic-database

Access COSMIC cancer mutation database. Query somatic mutations, Cancer Gene Census, mutational signatures, gene fusions, for cancer research and precision oncology. Requires authentication.

Quality

73%

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 ./backend/cli/skills/databases/cosmic-database/SKILL.md

Quality

Content

72%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 with executable examples and good progressive disclosure via a real reference file and script, but it carries some explanatory padding and time-sensitive version info that hurt conciseness, and the download workflow lacks explicit validation checkpoints.

Suggestions

Trim or move concept explanations (COSMIC overview, "Integration with Other Tools") that Claude already knows, and relocate the v102/May 2025 version info into a versioning or deprecated section.

Add explicit validation checkpoints to the download workflow (e.g., verify authentication succeeded before bulk download, confirm file integrity/size after download).

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code, but padded sections (Overview explaining what COSMIC is, "Integration with Other Tools") and time-sensitive info ("v102, May 2025") outside a deprecated section add unnecessary tokens.	3 / 5
Actionability	Fully executable, copy-paste-ready code across download, CLI, pandas filtering, and pysam VCF examples covers the common cases comprehensively.	5 / 5
Workflow Clarity	Quick Start provides a numbered sequence, but this batch/large-download workflow lacks explicit validation checkpoints (auth success, download integrity) before proceeding, capping clarity at 3.	3 / 5
Progressive Disclosure	Clear overview with a well-signaled one-level-deep reference (references/cosmic_data_reference.md, a real file) and a real script, both clearly navigated and appropriately split.	5 / 5
	Total	16 / 20 Passed

Description

75%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 specific and distinct, listing concrete query actions against a named cancer database, but it omits any explicit when-to-use trigger guidance, which caps its completeness. Third-person voice is used correctly throughout.

Suggestions

Add an explicit "Use when..." clause naming the trigger phrases (e.g., querying somatic mutations, downloading Cancer Gene Census data, mutational signature analysis) to lift completeness.

Include a few natural synonym/variant triggers (e.g., "cancer genomics", "tumor mutations") to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	Names concrete actions ("Access", "Query somatic mutations, Cancer Gene Census, mutational signatures, gene fusions") covering multiple specific data types, matching the comprehensive-coverage anchor.	5 / 5
Completeness	Has a clear "what" but no explicit "Use when..." trigger guidance, so the missing-when clause caps completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	Strong natural keywords ("cancer mutation", "somatic mutations", "gene fusions", "Cancer Gene Census") users would say, but a few common synonyms/variants are missing.	4 / 5
Distinctiveness Conflict Risk	COSMIC is a distinct named database with clear niche triggers, so conflict risk with other skills is minimal.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/cosmic-database/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day 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.