hmdb-database

Access Human Metabolome Database (220K+ metabolites). Search by name/ID/structure, retrieve chemical properties, biomarker data, NMR/MS spectra, pathways, for metabolomics and identification.

Install with Tessl CLI

npx tessl i github:K-Dense-AI/claude-scientific-skills --skill hmdb-database

What are skills?

1.17x

Quality

70%

Does it follow best practices?

Impact

89%

1.17x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/hmdb-database/SKILL.md

SKILL.md

Review

Evals

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, domain-specific description with excellent specificity and distinctive terminology that clearly identifies its niche in metabolomics research. The main weakness is the lack 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 metabolites, metabolomics analysis, compound identification, or needs to look up chemical/spectral data from HMDB.'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Search by name/ID/structure, retrieve chemical properties, biomarker data, NMR/MS spectra, pathways' - these are detailed, actionable capabilities.	3 / 3
Completeness	Clearly answers 'what' (access HMDB, search, retrieve various data types) but lacks an explicit 'Use when...' clause. The use cases are implied by listing 'for metabolomics and identification' but this is not explicit trigger guidance.	2 / 3
Trigger Term Quality	Includes strong natural keywords users would say: 'metabolites', 'metabolomics', 'NMR', 'MS spectra', 'biomarker', 'pathways', 'chemical properties', 'HMDB' (implied by Human Metabolome Database). Good coverage of domain-specific terms.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with clear niche - Human Metabolome Database is a specific resource, and terms like 'metabolites', 'NMR/MS spectra', 'metabolomics' are unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Implementation

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides a comprehensive overview of HMDB capabilities and is well-structured for navigation. However, it lacks concrete executable examples (no actual code for parsing XML, querying data, or using the R package beyond installation), and workflows describe processes conceptually without validation checkpoints. The content would benefit from being more concise and including copy-paste ready code snippets.

Suggestions

Add executable code examples for common tasks: parsing downloaded XML/CSV files, using the hmdbQuery R package to retrieve metabolite data, and processing spectral data.

Include validation checkpoints in workflows, e.g., 'Verify spectral match score > 0.8 before proceeding' or 'Confirm metabolite is expected in specimen type before reporting identification.'

Trim verbose sections like 'Database Contents' and 'Overview' - Claude doesn't need to be told what HMDB is or that it's 'comprehensive and freely available.'

Add a concrete example showing input (e.g., an HMDB ID or SMILES string) and expected output format for at least one common operation.

Dimension	Reasoning	Score
Conciseness	The content is reasonably organized but includes some unnecessary explanation (e.g., 'HMDB is a comprehensive, freely available resource') and could be tightened. The database contents section lists information Claude could infer, and some sections are verbose where bullet points would suffice.	2 / 3
Actionability	Provides general guidance and workflows but lacks concrete, executable code examples. The R package mention includes an install command but no usage example. Workflows describe steps conceptually rather than with specific commands or code snippets Claude could execute.	2 / 3
Workflow Clarity	Multi-step workflows are listed (e.g., Metabolite Identification, Biomarker Discovery) with numbered steps, but they lack validation checkpoints and feedback loops. Steps are descriptive rather than prescriptive with specific verification points.	2 / 3
Progressive Disclosure	Content is well-organized with clear sections and headers. References external documentation appropriately ('See references/hmdb_data_fields.md'). The structure allows for easy navigation without deeply nested references.	3 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	10 / 11 Passed

Reviewed: about 3 hours 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.