CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

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.

The body is well organized with a genuinely runnable example that matches the bundled script, and the field reference is properly offloaded. Weaknesses are a hedged, partially redundant Implementation Details section, a workflow with no validation checkpoints for batch XML mining, and an example that covers only one of the parser's search modes.

Suggestions

Trim or remove the "Implementation Details" section (especially the conceptual spectral-analysis bullet) since the parser code and references/hmdb_data_fields.md already convey this information.

Extend the example to cover the parser's other mode — parser.search("HMDB0000001", search_type="id") — and show how to access specific extracted fields, so the common cases are covered copy-paste ready.

Add validation checkpoints to the workflow: verify the downloaded XML exists and parses before mining, and note the memory/time cost of the full HMDB dump with an error-recovery path.

DimensionReasoningScore

Conciseness

The body is mostly efficient (When to Use, a runnable example, a pointer to the field reference), but the "Implementation Details" section restates what the code and reference file already show in hedged prose ("typically matches", "as supported by the parser/search implementation"), and the "Spectral analysis (conceptual)" section is speculative padding ("can be extended... not guaranteed unless implemented").

3 / 5

Actionability

The Python example is real and matches the bundled parser ("parser.search(\"Caffeine\")" against scripts/hmdb_parser.py), and the download URL is given, so guidance is mostly executable. Minor gaps: only name search is shown — the parser's ID search (search_type="id") and extraction of chemical/biological/clinical fields beyond the five returned keys are not demonstrated.

4 / 5

Workflow Clarity

A rough sequence exists (download XML → save as data/hmdb_metabolites.xml → run parser), with only an implicit empty-results check as validation. The workflow involves batch processing of a very large XML dump with no verification checkpoints (confirm the file exists/is parseable, handle download or parse failures), which caps this at the anchor-3 level per the batch-operations guideline.

3 / 5

Progressive Disclosure

Good structure against the actual bundle: the field reference is clearly signaled and one level deep ("see: references/hmdb_data_fields.md", which exists), and the parser code lives in scripts/hmdb_parser.py as referenced by the import. Minor gaps: the parser script is never explicitly pointed to as a bundle file, and the inlined conceptual Implementation Details content duplicates what belongs in the reference.

4 / 5

Total

14

/

20

Passed

Description

82%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, mostly concrete description with a clear what/when structure and a distinctive niche. Its main weaknesses are second-person phrasing ("when you need") and trigger coverage that omits several natural terms users would say.

Suggestions

Rewrite in third person to avoid the second-person penalty, e.g., "Use when the user needs metabolomics research data or automated HMDB XML mining" instead of "when you need".

Add natural trigger terms such as "metabolite lookup", "biofluid concentrations", "pathway/enzyme annotations", or "HMDB ID" to broaden keyword coverage.

Mention the cross-database identifier mapping capability (KEGG, PubChem, ChEBI) explicitly, since it is a key feature of the skill body.

DimensionReasoningScore

Specificity

The description names the domain and several concrete actions — "search metabolites by name/structure/ID and extract chemical/biological/clinical fields" — but coverage has gaps (no mention of identifier mapping, pathway/enzyme annotations, or the XML parsing pipeline) and it uses second person ("when you need"), which the guidelines penalize by reducing the score by 1 from a base of 4.

3 / 5

Completeness

It explicitly answers both what ("Access the Human Metabolome Database (HMDB) to search metabolites by name/structure/ID 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 top anchor.

5 / 5

Trigger Term Quality

Good natural keyword coverage: "Human Metabolome Database (HMDB)", "metabolites", "metabolomics research data", "HMDB XML". A few natural terms users might say are missing (e.g., "metabolite lookup", "biofluid concentrations", "pathway annotations", "KEGG/PubChem mapping"), so it falls short of the comprehensive synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

HMDB is a clear niche with distinct triggers (HMDB IDs, metabolomics, HMDB XML); no plausible overlap with generic database or chemistry skills, matching the 'clear niche with minimal conflict risk' anchor.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

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.