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.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/hmdb-database/SKILL.md

Quality

Content

50%

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

The body is well-organized and domain-rich but verbose, with inline reference-duplicating content and abstract workflows lacking validation checkpoints. Tightening inline field listings and adding verification steps would lift the weaker dimensions.

Suggestions

Move the inline 'Database Contents' and 'Accessing Metabolite Information' field category lists into references/hmdb_data_fields.md, keeping only a concise overview plus a clearly signaled link near the top.

Add validation/verification steps to the workflows — e.g. for Database Integration, validate parsed records against expected field completeness before loading, and for Metabolite Identification, verify candidate matches against multiple evidence types as an explicit checkpoint.

Replace abstract steps like 'Use HMDB spectral search tools' with concrete, actionable guidance (specific URL paths, R hmdbQuery function calls, or exact download filenames).

Dimension	Reasoning	Score
Conciseness	The ~185-line body is mostly efficient but padded; the inline 'Database Contents' and 'Accessing Metabolite Information' field listings duplicate material already in the reference file and could be tightened.	2 / 3
Actionability	It gives concrete URLs, formats, example IDs, and an R install command, but the search workflow steps are abstract ('Use HMDB spectral search tools to match') with no executable query method since no public API exists.	2 / 3
Workflow Clarity	Numbered workflows are present and sequenced, but none include validation/verification checkpoints; the batch Database Integration workflow in particular lacks a validate step, capping this at 2.	2 / 3
Progressive Disclosure	A real one-level reference exists and is linked, but it is signaled only once at the end and substantial field-category content that belongs in the reference is kept inline, so structure could be improved.	2 / 3
	Total	8 / 12 Passed

Description

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.

A specific, well-targeted description with strong action and keyword coverage, weakened only by the absence of an explicit 'Use when' trigger clause. Adding that clause would raise completeness to a 3.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about human metabolites, metabolomics, biomarker discovery, or metabolite identification by NMR/MS.'

Consider including common natural variants like 'metabolite database', 'HMDB lookup', or 'small molecule metabolites' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'Search by name/ID/structure, retrieve chemical properties, biomarker data, NMR/MS spectra, pathways' — matching the anchor for several specific actions rather than vague language.	3 / 3
Completeness	It clearly states what the skill does but lacks an explicit 'Use when...' trigger clause; the closing 'for metabolomics and identification' only implies when, so completeness is capped at 2 per the guidelines.	2 / 3
Trigger Term Quality	It covers natural domain terms a metabolomics user would say — 'metabolomics', 'NMR/MS spectra', 'biomarker data', 'pathways', 'metabolite identification' — giving good keyword coverage.	3 / 3
Distinctiveness Conflict Risk	The HMDB/metabolomics niche is specific with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/hmdb-database/SKILL.md
Commit: 52845c3

Reviewed: about 10 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.