drugbank-database

Access and analyze comprehensive drug information from the DrugBank database including drug properties, interactions, targets, pathways, chemical structures, and pharmacology data. This skill should be used when working with pharmaceutical data, drug discovery research, pharmacology studies, drug-drug interaction analysis, target identification, chemical similarity searches, ADMET predictions, or any task requiring detailed drug and drug target information from DrugBank.

Quality

83%

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

Quality

Content

78%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.

Well-structured content with verified one-level-deep progressive disclosure, executable setup guidance, and clearly sequenced workflows. The main improvements are removing the duplicated reference summary and adding light verification checkpoints to the workflow steps.

Suggestions

Drop the final "Reference Documentation" section or the per-section "Reference" lines (they enumerate the same five files twice) to save tokens without losing navigation.

Add a verification step to the workflows, e.g., after looking up patient medications confirm get_drug_info() returned a record before proceeding to pairwise interaction checks.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no padding with what DrugBank or XML are) and uses compact capability bullets, but the long per-section capability lists plus the final "Reference Documentation" section partially duplicate the inline "Reference" pointers, so it could be tightened; this fits efficient-with-minor-trimmings rather than lean-every-token-earns-its-place.	4 / 5
Actionability	It provides a copy-paste-ready helper example (DrugBankHelper with xml_path, DRUGBANK_XML_PATH, root), exact `uv pip install` commands, and pointers to real reference files, but most capability sections are descriptive bullets deferring actual query code to the references, which is a minor gap rather than fully executable coverage in the body.	4 / 5
Workflow Clarity	Four numbered workflows (drug discovery, polypharmacy safety, repurposing, pharmacology) each map every step to a specific reference file, giving a clear sequence; however, no explicit validation or verification checkpoints appear (e.g., confirming a drug ID resolved before scoring interactions), so it sits below the feedback-loop anchor.	4 / 5
Progressive Disclosure	The body is a clean overview: each capability section signals its reference with a "See references/<file>.md for ..." line, the five referenced files and scripts/drugbank_helper.py all exist in the bundle, and the references are one level deep (they link only to external URLs, never to further .md files), matching the well-signaled, easy-navigation anchor.	5 / 5
	Total	17 / 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 description with an explicit use-when clause, natural trigger terms, and a clearly named database niche. Its only limitation is reliance on two generic verbs (access/analyze) to cover an otherwise comprehensive list of data domains.

Dimension	Reasoning	Score
Specificity	The description enumerates a comprehensive set of data objects ("drug properties, interactions, targets, pathways, chemical structures, and pharmacology data") but relies on only two verbs ("Access and analyze"), so it lists several specifics with minor gaps rather than the multiple distinct concrete actions of a 5.	4 / 5
Completeness	It explicitly answers both what ("Access and analyze comprehensive drug information from the DrugBank database including...") and when ("This skill should be used when working with pharmaceutical data, drug discovery research...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural phrases like "drug discovery research", "drug-drug interaction analysis", "ADMET predictions", and "target identification" are exactly what a user would say, matching the good-coverage anchor; a few natural synonyms (e.g., drug repurposing, polypharmacy) are missing, keeping it below comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	It names the DrugBank database explicitly in both the what and when clauses, establishing a clear niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	18 / 20 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/drugbank-database/SKILL.md
Commit: 4082a2e

Reviewed: 1 day 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.