hmdb-database

Access the Human Metabolome Database (HMDB) to search metabolites by name/structure/ID and extract chemical/biological/clinical fields when you need metabolomics research data or automated HMDB XML mining.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/hmdb-database/SKILL.md

Quality

Content

61%Weight 40%Scale 1-5

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

A well-structured, runnable skill with verified bundle files, but it carries redundant prose between sections, over-claims a structure-search mode the parser does not implement, and lacks validation checkpoints for its batch XML-parsing workflow.

Suggestions

Merge the overlapping material in "Key Features" and "Implementation Details" (parsing approach, search behavior, integration) into one section and drop the speculative "Spectral analysis (conceptual)" subsection to reduce redundancy.

Add a validation/verification checkpoint to the download+parse workflow (e.g., confirm the XML download is complete, check an expected metabolite count, handle ET.ParseError) so the batch operation has a feedback loop.

Correct the capability claims: the parser only implements text and id search, so either implement structure (SMILES/InChI) search or remove the name/structure/ID framing and the "structure depends on implementation" hedge to avoid misleading the user.

Dimension	Reasoning	Score
Conciseness	The body is organized but redundantly covers parsing/search/integration in both "Key Features" and "Implementation Details", and the speculative "Spectral analysis (conceptual)" section plus hedging prose ("structure depends on implementation") add tokens that could be trimmed; it is mostly efficient but could be tightened.	3 / 5
Actionability	Section 2 gives copy-paste-ready, genuinely executable code (verified against scripts/hmdb_parser.py) plus a concrete download URL, but only demonstrates name search, leaves result handling vague ("structure depends on implementation"), and the advertised structure search is not actually implemented in the parser — minor-to-moderate gaps.	4 / 5
Workflow Clarity	Steps are sequenced (download XML -> search/extract -> field reference) but there are no validation/verification checkpoints for this bulk XML parsing batch operation; per the rubric's precedence rule a batch skill without validation is capped at 3.	3 / 5
Progressive Disclosure	The skill is an overview with one-level-deep, clearly signaled references ("see: references/hmdb_data_fields.md" and scripts.hmdb_parser in code), both verified to exist; the inline redundant detail and speculative section keep it just short of a 5.	4 / 5
	Total	14 / 20 Passed

Description

87%Weight 40%Scale 1-5

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 strong, concise description that clearly pairs concrete capabilities with explicit trigger conditions and occupies a distinctive niche. Minor room to itemize actions and add file-extension keywords.

Dimension	Reasoning	Score
Specificity	"search metabolites by name/structure/ID and extract chemical/biological/clinical fields" names the domain and lists several concrete actions (multi-mode search plus three field-category extraction); it stops short of the fully enumerated action list of a 5 because the verbs are grouped rather than individually itemized.	4 / 5
Completeness	It explicitly states both what ("search metabolites ... and extract chemical/biological/clinical fields") and when ("when you need metabolomics research data or automated HMDB XML mining") with concrete trigger phrases, matching the anchor for a clear dual answer.	5 / 5
Trigger Term Quality	Includes natural domain terms a metabolomics user would say ("metabolomics research data", "metabolites", "HMDB", "automated HMDB XML mining") plus name/structure/ID synonyms; a 5 would also cover file extensions like .xml, which are absent.	4 / 5
Distinctiveness Conflict Risk	"Access the Human Metabolome Database (HMDB)" carves out a clear niche (metabolomics/HMDB) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/hmdb-database/SKILL.md
Commit: 63c61d3

Reviewed: 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.