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

69%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/cosmic-database/SKILL.md

Quality

Content

68%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.

A highly actionable, well-bundled skill: executable code, real paths, a genuine one-level-deep reference, and a matching script. It loses points for repetition in the data-types section, inline time-sensitive version details, and the absence of post-download validation steps for large batch downloads.

Suggestions

Collapse the per-data-type download examples into one example plus a filepath/shortcut table (the content already exists in both the body and the reference).

Add an explicit verification step after download (e.g. gzip -t or check the first line is a TSV header, not a login page) before parsing.

Move the version/date detail ('v102, May 2025') into the reference or a release-notes section so the main flow stays evergreen.

Dimension	Reasoning	Score
Conciseness	The body is mostly functional but noticeably loose: the 'Available Data Types' section repeats the same download_cosmic_file call pattern ~7 times with only the filepath varying, the Overview and reference file restate the same COSMIC boilerplate, and time-sensitive details ('current version: v102, May 2025') sit in the main flow rather than a deprecated/notes section. Not a 2 because almost every section carries real, non-obvious information (file paths, shortcuts, column names).	3 / 5
Actionability	Guidance is fully executable: copy-paste Python calls with real file paths ('GRCh38/cosmic/latest/CosmicMutantExport.tsv.gz'), CLI invocations with flags (--data-type, --assembly, -o), install commands, helper-function signatures with return values, and runnable pandas/pysam analysis snippets. Specific examples cover the common cases (mutations, gene census, fusions, CNA, signatures).	5 / 5
Workflow Clarity	The Quick Start gives a coherent sequence (register → install → download → analyze) and Troubleshooting covers error categories, but there are no explicit validation checkpoints — e.g. verify the downloaded gzip is complete/valid before parsing, or confirm an HTML login-error page wasn't saved as the file. Since multi-GB batch downloads are the core operation, the missing validation/verification cap applies (cannot exceed 3).	3 / 5
Progressive Disclosure	Good structure: SKILL.md is a working overview, the bulk detail lives in a real one-level-deep reference (references/cosmic_data_reference.md, confirmed present) that is clearly signaled with an explicit 'Use this reference when...' list, and scripts/download_cosmic.py exists with the documented functions. Not a 5 because the data-type catalog and file-path lists are duplicated between the body and the reference, so the split is not fully clean.	4 / 5
	Total	15 / 20 Passed

Description

70%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.

A strong, third-person description with concrete data-domain actions and excellent distinctiveness. Its main weaknesses are the absence of an explicit 'Use when...' trigger clause and the omission of 'download' vocabulary, which both limits trigger coverage and understates the skill's primary capability.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions COSMIC, cancer mutations, somatic mutation data, the Cancer Gene Census, or mutational signatures.'

Include 'download' (and 'COSMIC data files') as keywords, since downloading datasets is the skill's dominant action and a word users will naturally say.

Optionally mention analysis guidance (filtering by gene/cancer type) to round out the capability coverage.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — 'Access COSMIC cancer mutation database. Query somatic mutations, Cancer Gene Census, mutational signatures, gene fusions' — naming specific data domains rather than generic language. It stops short of a 5 because the primary capability shown in the body (downloading data files) is only implied by 'Access', and coverage of what the skill actually does is incomplete.	4 / 5
Completeness	The 'what' is clearly stated (query COSMIC data across several data types), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. The context 'for cancer research and precision oncology' weakly implies when, but is not explicit trigger phrasing.	3 / 5
Trigger Term Quality	Natural user phrases like 'COSMIC', 'cancer mutation database', 'somatic mutations', 'gene fusions', 'cancer research', and 'precision oncology' give good keyword coverage. A few natural terms are missing — most notably 'download', which is the skill's main action and the word a user would most likely say.	4 / 5
Distinctiveness Conflict Risk	COSMIC is a specific named database with distinct domain triggers (Cancer Gene Census, mutational signatures, gene fusions); the description occupies a clear niche with minimal conflict risk against generic data-analysis skills.	5 / 5
	Total	16 / 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: 4082a2e

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.