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.
84
77%
Does it follow best practices?
Impact
98%
2.33xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/cosmic-database/SKILL.mdQuality
Discovery
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.
This is a strong skill description with excellent specificity and domain-appropriate trigger terms that cancer researchers would naturally use. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The description effectively carves out a clear niche in cancer genomics databases.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about cancer mutations, needs to look up genes in COSMIC, or is doing cancer genomics research.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Query somatic mutations, Cancer Gene Census, mutational signatures, gene fusions' - these are distinct, concrete capabilities within the cancer genomics domain. | 3 / 3 |
Completeness | Clearly answers 'what' (access COSMIC database, query various mutation data types) but lacks an explicit 'Use when...' clause. The 'when' is only implied through the domain context of cancer research. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'COSMIC', 'cancer mutation', 'somatic mutations', 'Cancer Gene Census', 'mutational signatures', 'gene fusions', 'cancer research', 'precision oncology' - comprehensive coverage of domain terminology. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific database name (COSMIC) and specialized cancer genomics terminology. Unlikely to conflict with other skills due to the narrow, technical domain focus. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with excellent code examples and good progressive disclosure structure. The main weaknesses are verbosity in introductory sections that explain what COSMIC is (which Claude already knows) and missing validation steps for large file downloads. The skill would benefit from trimming explanatory content and adding download verification guidance.
Suggestions
Remove or significantly trim the 'Overview' and 'When to Use This Skill' sections - Claude doesn't need explanations of what COSMIC is or when to use it
Add validation steps after downloads: file size verification, checksum validation if available, and basic data integrity checks (e.g., verify expected columns exist)
Add error handling examples for common failure modes (network interruption during large downloads, authentication token expiration)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary explanatory content (e.g., 'COSMIC is the world's largest and most comprehensive database...') and verbose descriptions that Claude doesn't need. The 'When to Use This Skill' section is largely redundant. However, the code examples are reasonably efficient. | 2 / 3 |
Actionability | Provides fully executable Python code examples throughout, including specific file paths, command-line usage, and pandas operations for data analysis. Code is copy-paste ready with concrete examples for each data type. | 3 / 3 |
Workflow Clarity | The skill presents clear steps for downloading and using data, but lacks validation checkpoints. There's no guidance on verifying successful downloads, checking file integrity, or handling partial downloads for large files. For multi-GB file operations, explicit validation steps would be important. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from Quick Start to detailed data types. Appropriately references external file 'references/cosmic_data_reference.md' for comprehensive details, keeping the main skill focused on actionable content. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
71add64
- Reviewed
Table of Contents
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.