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 ./skills/bio/cosmic-database/SKILL.md

Quality

Content

65%

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 but is verbose with redundant download blocks, lacks validation checkpoints in its download workflow, and references bundle files (scripts/download_cosmic.py, references/cosmic_data_reference.md) that are not present.

Suggestions

Trim the marketing prose in the Overview and collapse the repeated download_cosmic_file blocks into one parameterized example plus a table of data-type file paths.

Add an explicit post-download verification checkpoint (e.g., confirm file is non-empty / gz is valid before reading with pandas) to lift workflow_clarity above 2.

Either ship the referenced references/cosmic_data_reference.md and scripts/download_cosmic.py or remove the dangling references so progressive disclosure reflects the actual bundle.

Dimension	Reasoning	Score
Conciseness	Mostly actionable, but includes padded marketing prose ('world's largest and most comprehensive database... millions of mutations across thousands of cancer types') and repeats the same download_cosmic_file block with placeholder email/password many times; not score 3 because the redundancy and fluff could be tightened, and not score 1 because it does not lecture on concepts Claude already knows.	2 / 3
Actionability	Provides copy-paste-ready Python (download_cosmic_file, pandas filtering, pysam VCF fetch) and concrete CLI commands with real flags and file paths; not score 2 because the examples are executable and complete rather than pseudocode.	3 / 3
Workflow Clarity	Sequenced quick-start steps exist, but the download-then-analyze workflow has no validation/verification checkpoints and the script's success is never confirmed before downstream pandas use; per the rubric, missing validation in batch/download workflows caps this at 2, and it is not 1 because a sequence is present.	2 / 3
Progressive Disclosure	The body signals a one-level reference ('see references/cosmic_data_reference.md') and a script, but those bundle files do not exist in references/ or scripts/, and the long data-types/file-format catalog is inlined in SKILL.md rather than split out; not score 3 because references are broken and content that should be separate is inline, not score 1 because there is section structure and the reference is only one level deep.	2 / 3
	Total	9 / 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, third-person description with strong trigger-term coverage and a clear niche, but it omits an explicit 'Use when...' trigger clause, which caps completeness at 2.

Suggestions

Append an explicit trigger clause such as 'Use when downloading or querying COSMIC cancer mutation data, the Cancer Gene Census, mutational signatures, or gene fusions.' to satisfy the completeness 'when' requirement.

Consider adding the common user phrasings 'COSMIC download' and 'cancer genomics data' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'Access COSMIC cancer mutation database. Query somatic mutations, Cancer Gene Census, mutational signatures, gene fusions' — multiple concrete, named actions matching the score-3 anchor; not score 2 because it goes beyond naming a domain plus a few actions to a comprehensive action list.	3 / 3
Completeness	Clearly states what it does but lacks any 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 2; not score 3 because the 'when' is entirely missing rather than explicitly stated.	2 / 3
Trigger Term Quality	Contains natural terms a precision-oncology user would say — 'COSMIC', 'cancer mutation database', 'somatic mutations', 'Cancer Gene Census', 'mutational signatures', 'gene fusions' — giving good coverage; not score 2 because it spans several common phrasings rather than a single keyword.	3 / 3
Distinctiveness Conflict Risk	The COSMIC cancer-mutation niche with its specific data-type triggers is clearly distinct and unlikely to fire for unrelated skills; not score 2 because it is not merely a generic 'database' or 'data file' description that would overlap others.	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
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/cosmic-database/SKILL.md
Commit: df37802

Reviewed: about 1 hour 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.