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

68%

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

Quality

Content

67%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 skill body with executable, verified code and a clear workflow, weakened mainly by verbosity — repeated download examples, duplicated data-type lists, padded sections, and inline time-sensitive version info. Progressive disclosure is solid but the overview carries detail that belongs in the reference file.

Suggestions

Collapse the six near-identical download_cosmic_file examples into one example plus a table of filepaths, and remove the duplicated data-type/shortcut list (keep it in one place or move it to the reference).

Remove or trim padding: the 'Integration with Other Tools' list, the K-Dense Web promotional section, and the repeated pysam VCF snippet add tokens without operational value.

Move time-sensitive version information ('v102, May 2025') out of the main body into the reference or a dedicated versioning section to avoid stale-specificity penalties, and add a simple post-download validation step (e.g., verify file size/row count) to strengthen workflow checkpoints.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose across ~330 lines: six near-identical download_cosmic_file examples that differ only in filepath, the data-type list duplicated between 'Available Data Types' and the 'Helper Functions' shortcuts (same 10 items twice), the pysam VCF example repeated, plus padded sections ('Integration with Other Tools', the K-Dense Web promo). Time-sensitive version info ('current version: v102, May 2025') appears outside any deprecated/versioned section, which the guidelines penalize. Not 3 because the redundancy is substantial rather than incidental; not 1 because most sections still convey operational facts rather than explaining concepts Claude already knows.	2 / 5
Actionability	Fully executable guidance throughout: copy-paste-ready Python and CLI examples with exact file paths, and the code matches the actual bundle (download_cosmic_file, get_common_file_path, and the --data-type/--assembly/-o CLI flags all exist in scripts/download_cosmic.py), plus concrete pandas/pysam analysis patterns covering the common cases. Minor omission of list_available_files does not reduce coverage of common use cases.	5 / 5
Workflow Clarity	Clear sequence — prerequisites (account registration, dependency install) → download (script/CLI) → parse and analyze — with a Troubleshooting section providing error-recovery guidance for authentication, file-not-found, and large downloads. Not 5 because there is no explicit validation step before using downloaded data (e.g., checking file integrity or row counts for multi-GB downloads); not 3 because checkpoints are largely present via troubleshooting and progress reporting.	4 / 5
Progressive Disclosure	Good structure: SKILL.md serves as an overview, and the single reference (references/cosmic_data_reference.md, verified to exist) is clearly signaled with its contents and 'Use this reference when' conditions, one level deep. Not 5 because detailed per-datatype file listings and field-level detail are duplicated inline in SKILL.md when they belong solely in the reference, making the overview heavier than needed.	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 specific, well-targeted description with concrete named capabilities and a distinct niche. Its main weakness is the missing explicit 'Use when...' trigger clause — the usage context is only weakly implied by 'for cancer research and precision oncology'.

Suggestions

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

Broaden trigger coverage with common user phrasings such as 'download COSMIC data', 'drug resistance mutations', and 'copy number alterations' to improve trigger term quality.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Query somatic mutations, Cancer Gene Census, mutational signatures, gene fusions' — naming the domain and specific capabilities. Not 5 because coverage has gaps: copy number alterations, resistance mutations, and structural variants from the skill body are absent.	4 / 5
Completeness	The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance — 'for cancer research and precision oncology' only weakly implies when to use it, capping this at 3. Not 4 because the when-context is a purpose statement, not an explicit trigger.	3 / 5
Trigger Term Quality	Good natural keyword coverage ('cancer mutation database', 'somatic mutations', 'gene fusions', 'mutational signatures', 'precision oncology') that users in this domain would say. Not 5 because common variations like 'download COSMIC data', 'drug resistance', or 'copy number' are missing.	4 / 5
Distinctiveness Conflict Risk	Names the specific database (COSMIC) with domain-specific entities (Cancer Gene Census, mutational signatures), giving it a clear niche with minimal conflict risk against other skills.	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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: googolme/run0204
Path: scientific-skills/cosmic-database/SKILL.md
Commit: 4902409

Reviewed: 6 days 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.