CtrlK
BlogDocsLog inGet started
Tessl Logo

hmdb-skill

Submit compact HMDB search requests for metabolites, proteins, diseases, and pathways. Use when a user wants concise HMDB summaries

72

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-3

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

The body is a concise, fully actionable, well-organized guide for a simple single-task REST skill, with a real bundle file and a clear input/output contract. It earns top marks across all content dimensions.

DimensionReasoningScore

Conciseness

The body is lean and operational (e.g., "Use `base_url=https://hmdb.ca`", "per_page=10 and max_items=10"), avoids explaining concepts Claude already knows, and every line earns its place, matching anchor 3.

3 / 3

Actionability

It provides a complete, copy-paste-ready executable bash command with a full JSON payload plus explicit required/optional input fields and concrete patterns, satisfying anchor 3.

3 / 3

Workflow Clarity

This is a simple single-task skill (run the script with a JSON input) whose single action is unambiguous and paired with a clear success/failure output contract, so it qualifies for anchor 3 under the simple-skills note.

3 / 3

Progressive Disclosure

Under 50 lines with well-organized sections and a single real bundle reference (scripts/rest_request.py, confirmed present), the structure is appropriately split and easy to navigate, matching anchor 3 for a simple skill.

3 / 3

Total

12

/

12

Passed

Description

75%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is HMDB-specific and provides an explicit "Use when..." trigger, giving strong completeness and distinctiveness. It is held back only by naming a single action and somewhat limited trigger-term coverage.

Suggestions

Add one or two more concrete actions beyond search (e.g., "retrieve compound spectra" or "look up pathway entries") to lift specificity to anchor 3.

Broaden trigger terms with common user phrasings like "compounds", "spectra", or "biochemical lookups".

Consider trimming the category list slightly and replacing it with the higher-variability natural terms users actually say.

DimensionReasoningScore

Specificity

It names one concrete action ("Submit compact HMDB search requests") across several categories (metabolites, proteins, diseases, pathways), but does not enumerate multiple distinct actions, matching anchor 2 rather than the multi-action anchor 3.

2 / 3

Completeness

Both what ("Submit compact HMDB search requests...") and an explicit when ("Use when a user wants concise HMDB summaries") are clearly present, satisfying the anchor 3 requirement for an explicit "Use when..." trigger.

3 / 3

Trigger Term Quality

"HMDB", "metabolites, proteins, diseases, and pathways", and "concise HMDB summaries" give some natural keywords, but common variations a user might say (compounds, spectra, reactions, concentrations) are missing, fitting anchor 2.

2 / 3

Distinctiveness Conflict Risk

The description targets a specific database niche (HMDB) with distinct triggers, making it unlikely to fire for unrelated skills, matching anchor 3.

3 / 3

Total

10

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
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.