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

77%

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%

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

A highly actionable, well-organized skill with real executable code and properly offloaded reference material. Its main weakness is verbosity from a conceptual overview and repeated boilerplate download snippets, plus the absence of explicit validation checkpoints in the download workflow.

Suggestions

Collapse the repeated per-data-type download_cosmic_file snippets into one canonical example plus a table of filepaths, removing the redundant email/password boilerplate.

Trim the conceptual Overview paragraph (COSMIC's scope is context Claude already has) and fold essential facts into the reference file.

Add an explicit post-download validation step (e.g., verify file integrity/row count against expected size, with a retry-on-failure loop) to give the workflow a clear checkpoint.

Dimension	Reasoning	Score
Conciseness	Content is structured and actionable, but the conceptual Overview ('world's largest and most comprehensive database…') and ~6 near-identical download_cosmic_file boilerplate snippets with repeated email/password padding add unnecessary tokens.	2 / 3
Actionability	Provides fully executable download_cosmic_file calls with real arguments, concrete CLI usage, pandas/pysam reading examples, and the get_common_file_path helper — copy-paste ready throughout.	3 / 3
Workflow Clarity	Prerequisites → Quick Start → Data Types → Working with Data → Troubleshooting is sequenced, but there is no explicit validate→fix→retry checkpoint within the workflow; error recovery is reactive (Troubleshooting) rather than an inline feedback loop.	2 / 3
Progressive Disclosure	SKILL.md is an overview that signals a real one-level-deep reference (references/cosmic_data_reference.md) and real script (scripts/download_cosmic.py), both verified to exist, with clear 'Use this reference when:' navigation guidance.	3 / 3
	Total	10 / 12 Passed

Description

82%

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 specific, well-targeted description with concrete actions and natural domain trigger terms. Its main weakness is the missing explicit 'Use when…' trigger guidance, which leaves the 'when to use' intent implied rather than stated.

Suggestions

Add an explicit 'Use when…' clause naming the user requests that should trigger this skill (e.g., 'Use when downloading COSMIC data, querying the Cancer Gene Census, or retrieving mutational signatures for cancer research').

Consider including common surface variations users might say, such as 'cancer mutations', 'tumor mutation data', or 'COSMIC TSV/VCF downloads', to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Access COSMIC cancer mutation database', 'Query somatic mutations, Cancer Gene Census, mutational signatures, gene fusions' — matching the highest anchor.	3 / 3
Completeness	Clearly states what the skill does, but 'when' is only implied via 'for cancer research and precision oncology' with no explicit 'Use when…' trigger clause, which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Uses natural domain terms a user would say — 'cancer mutation database', 'somatic mutations', 'Cancer Gene Census', 'mutational signatures', 'gene fusions', 'precision oncology' — with good coverage.	3 / 3
Distinctiveness Conflict Risk	'COSMIC cancer mutation database' names a clear niche with distinct triggers, making it unlikely to fire for the wrong skill.	3 / 3
	Total	11 / 12 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: 52845c3

Reviewed: about 10 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.