metabolomics-workbench-database
Access NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata, for metabolomics and biomarker discovery.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill metabolomics-workbench-databaseOverall
score
80%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
83%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, technically precise description that clearly identifies the data source (NIH Metabolomics Workbench) and lists specific queryable data types. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill over others.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about metabolomics data, metabolite identification, RefMet lookup, or needs to search the Metabolomics Workbench database.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata' - these are distinct, actionable capabilities with technical precision. | 3 / 3 |
Completeness | Clearly answers 'what' (query metabolites, RefMet, MS/NMR data, etc.) but lacks an explicit 'Use when...' clause. The 'for metabolomics and biomarker discovery' implies purpose but doesn't provide explicit trigger guidance. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'metabolites', 'RefMet', 'MS/NMR', 'm/z searches', 'metabolomics', 'biomarker discovery', 'NIH Metabolomics Workbench'. These cover both technical terms and domain-specific vocabulary researchers would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific niche: NIH Metabolomics Workbench, RefMet nomenclature, m/z searches are unique identifiers unlikely to conflict with other skills. The '4,200+ studies' and REST API specificity further distinguish it. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
73%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides highly actionable, executable guidance for the Metabolomics Workbench API with excellent code examples and good progressive disclosure. However, it suffers from some verbosity in introductory sections and lacks validation/error handling in workflows, which is important for API interactions that may fail or return unexpected results.
Suggestions
Remove or significantly condense the 'Overview' and 'When to Use This Skill' sections - Claude already understands what metabolomics databases are and can infer when to use this skill
Add validation steps to workflows: check response status codes, handle empty results, and provide guidance for common API errors
Remove the promotional 'K-Dense Web' section at the end - this is marketing content that doesn't belong in a technical skill file
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity, particularly in the overview section explaining what Metabolomics Workbench is (Claude knows this). The 'When to Use This Skill' section is redundant. However, the code examples are appropriately concise. | 2 / 3 |
Actionability | Excellent executable code examples throughout with real API endpoints, proper Python requests syntax, and copy-paste ready queries. Each capability section includes concrete, working examples that Claude can immediately use. | 3 / 3 |
Workflow Clarity | Three workflows are clearly sequenced with numbered steps, but they lack validation checkpoints. No error handling guidance, no verification that API calls succeeded, and no feedback loops for when searches return empty results or unexpected data. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections, appropriate use of headers, and a single-level reference to 'references/api_reference.md' for detailed specifications. Content is appropriately split between overview and detailed reference material. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
88%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 |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 14 / 16 Passed | |
- 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.