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

Evaluation results

77%

34%

Metabolite Property Lookup Tool in R

R programmatic HMDB access

Criteria

Without context

With context

Uses hmdbQuery package

15%

BiocManager install instruction

100%

No REST API calls

80%

No web scraping

53%

80%

Correct HMDB ID format

100%

Results saved to CSV

100%

README documents package install

100%

Retrieves multiple metabolites

100%

Without context: $0.3772 · 1m 29s · 22 turns · 28 in / 5,876 out tokens

With context: $0.8179 · 2m 57s · 30 turns · 3,835 in / 10,840 out tokens

100%

Local HMDB Integration for Metabolomics Platform

HMDB dataset download and format selection

Criteria

Without context

With context

XML for comprehensive data

100%

SDF for cheminformatics

100%

CSV/TSV for pipeline

100%

Download over repeated queries

100%

Downloads URL

100%

Version tracking

100%

Cross-database IDs

100%

Python plan script

100%

Format justifications

100%

Without context: $0.2668 · 1m 39s · 11 turns · 16 in / 5,250 out tokens

With context: $0.5885 · 2m 27s · 24 turns · 3,672 in / 7,524 out tokens

92%

Unknown Metabolite Identification from LC-MS Data

Metabolite identification workflow

Criteria

Without context

With context

Spectral search tools

100%

75%

Multiple evidence types

100%

MW check

100%

Retention time check

100%

75%

MS-MS fragmentation check

100%

Biological plausibility

100%

93%

SMPDB for pathways

83%

Worked example applied

100%

Experimental vs predicted data

75%

100%

Biofluid/specimen filter

100%

Without context: $0.7567 · 5m 15s · 15 turns · 20 in / 18,450 out tokens

With context: $3.6355 · 17m 9s · 44 turns · 2,497 in / 59,747 out tokens

Evaluated: 2 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Metabolite Property Lookup Tool in R Local HMDB Integration for Metabolomics Platform Unknown Metabolite Identification from LC-MS Data

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.