reactome-database
Query Reactome REST API for pathway analysis, enrichment, gene-pathway mapping, disease pathways, molecular interactions, expression analysis, for systems biology studies.
69
61%
Does it follow best practices?
Impact
77%
1.10xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/reactome-database/SKILL.mdQuality
Discovery
50%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description effectively communicates specific bioinformatics capabilities and targets a clear niche (Reactome database queries). However, it critically lacks explicit trigger guidance ('Use when...'), which would help Claude know when to select this skill. The technical terminology is appropriate for the domain but may miss some natural language variations users might employ.
Suggestions
Add a 'Use when...' clause specifying triggers like 'Use when the user asks about biological pathways, Reactome database, pathway enrichment analysis, or gene-to-pathway relationships'
Include natural language variations users might say, such as 'biological pathways', 'pathway database', 'what pathways involve gene X', or 'pathway enrichment'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'pathway analysis, enrichment, gene-pathway mapping, disease pathways, molecular interactions, expression analysis' - these are distinct, concrete bioinformatics operations. | 3 / 3 |
Completeness | Describes what the skill does (query Reactome API for various analyses) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes domain-specific terms like 'Reactome', 'pathway analysis', 'enrichment', 'gene-pathway mapping' that experts would use, but missing common variations like 'biological pathways', 'pathway database', or file format mentions. Terms are somewhat technical. | 2 / 3 |
Distinctiveness Conflict Risk | 'Reactome REST API' is highly specific and distinctive - this clearly targets a specific bioinformatics database and would not conflict with general data analysis or other pathway tools. | 3 / 3 |
Total | 9 / 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 skill provides solid, actionable guidance for using Reactome APIs with executable Python examples and good progressive disclosure through external references. However, it could be more concise by removing explanatory content Claude already knows, and workflow clarity would benefit from explicit validation steps and error handling patterns for API interactions.
Suggestions
Remove the 'When to Use This Skill' section and the introductory explanation of what Reactome is - Claude can infer appropriate use cases from the capabilities described.
Add validation checkpoints to API workflows: check response.status_code before parsing JSON, validate input format before submission, and include error handling examples.
Trim redundant descriptions like 'Python client library that wraps Reactome API calls for easier programmatic access' - the code examples demonstrate this clearly.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary explanations (e.g., 'Reactome is a free, open-source, curated pathway database') and verbose sections that could be tightened. The 'When to Use This Skill' section lists obvious use cases Claude could infer, and some API descriptions are redundant. | 2 / 3 |
Actionability | Provides fully executable Python code examples with proper imports, specific API endpoints, and copy-paste ready snippets. Examples cover querying, analysis submission, token retrieval, and visualization URL construction with concrete identifiers. | 3 / 3 |
Workflow Clarity | Multi-step processes like analysis submission are shown but lack explicit validation checkpoints. No error handling or verification steps are included (e.g., checking response status codes, validating input format before submission, handling failed analyses). | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections, appropriate references to external files (references/api_reference.md, scripts/reactome_query.py), and external documentation links. Content is organized from overview to specific operations without deep nesting. | 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.