CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

78%

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 ./backend/cli/skills/databases/drugbank-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.

A well-organized overview skill that uses progressive disclosure effectively to route the model to modular reference files. Its main weaknesses are thin in-body executable guidance and workflows that lack explicit validation checkpoints for database/analysis pipelines.

Suggestions

Add explicit validation/verification steps to the Typical Workflows (e.g., 'verify the parsed drug count matches expected ~9,591', 'validate RDKit parsed structures before similarity search') to lift workflow clarity above the batch-operation cap of 3.

Include one or two short, executable code snippets in the body for the most common operations (e.g., opening/parsing the XML and running a basic drug query) so the skill is actionable without immediately loading a reference.

Reference scripts/drugbank_helper.py from the body (e.g., a note in the Data Access section) so the provided helper script is discoverable rather than orphaned.

DimensionReasoningScore

Conciseness

The body is a lean overview with no padding about basic concepts, but the five 'Core Capabilities' subsections reproduce fairly long bullet lists of capabilities that largely duplicate content in the reference files, so a few sections could be tightened.

4 / 5

Actionability

Executable guidance in the body is limited to the `uv pip install` commands and a single `download_drugbank(version='5.1.10')` snippet; the bulk of concrete how-to (query functions, network analysis, similarity) is described rather than shown and deferred to references, leaving key details incomplete here.

3 / 5

Workflow Clarity

The four 'Typical Workflows' are clearly numbered and sequenced, but they perform database-query/batch analysis with no validation or verification checkpoints (e.g., confirming data loaded, validating structures), which the rubric caps at 3 for batch/database operations.

3 / 5

Progressive Disclosure

The body is a clear overview pointing to five one-level-deep reference files, each signposted with 'See references/X.md' and a description, and all referenced files exist; the gap is that the bundle file scripts/drugbank_helper.py is never referenced or signposted from the body.

4 / 5

Total

14

/

20

Passed

Description

95%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, well-structured description that clearly states both the capability set and explicit use-when triggers with good keyword coverage. The only minor weakness is that the action vocabulary is somewhat narrow (access/analyze) relative to the breadth of data types listed.

DimensionReasoningScore

Specificity

The description names the DrugBank domain and lists several concrete capability areas ('drug properties, interactions, targets, pathways, chemical structures, and pharmacology data'), but the actions reduce to two verbs ('Access and analyze') applied to a data-type list rather than many distinct verbs, leaving a minor coverage gap below the comprehensive anchor.

4 / 5

Completeness

It explicitly answers both 'what' ('Access and analyze comprehensive drug information…including…') and 'when' ('This skill should be used when working with pharmaceutical data…'), with concrete trigger phrases for the use-when clause.

5 / 5

Trigger Term Quality

It covers comprehensive natural trigger terms with synonyms — 'pharmaceutical data, drug discovery research, pharmacology studies, drug-drug interaction analysis, target identification, chemical similarity searches, ADMET predictions' — matching the kinds of phrases a user would actually say.

5 / 5

Distinctiveness Conflict Risk

The DrugBank database is named explicitly twice and the triggers are domain-specific (DDI analysis, ADMET predictions, chemical similarity), giving it a clear niche with minimal conflict risk against other skills.

5 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.