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

57%

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

The skill is well-structured with genuine, well-signaled reference files and a clear overview, but the body leans on descriptive bullets rather than executable examples and its workflows lack validation checkpoints. A redundant reference recap section adds verbosity.

Suggestions

Replace the descriptive capability bullet lists with at least one small executable code snippet per capability, or point explicitly to the helper at scripts/drugbank_helper.py, which exists but is never referenced in the body.

Add validation/verification checkpoints to the workflows (e.g. confirm structures parsed via RDKit before similarity, or validate interaction counts before scoring polypharmacy risk).

Remove the final "Reference Documentation" section or fold it into inline references, since it duplicates what each capability section already states.

DimensionReasoningScore

Conciseness

The body is mostly efficient with organized sections, but it is padded with a redundant final "Reference Documentation" section that repeats the inline references already given in each capability, and time-sensitive database statistics ("~9,591 drug entries") that could be tightened.

2 / 3

Actionability

It gives concrete install commands and one executable version snippet, but the bulk of each capability section is a descriptive bullet list ("Calculate physicochemical properties", "Generate molecular fingerprints") without executable code or method signatures.

2 / 3

Workflow Clarity

Typical Workflows are numbered and sequenced, but none include validation or verification checkpoints, which matters for batch safety-critical operations like the polypharmacy interaction analysis.

2 / 3

Progressive Disclosure

The body is a clear overview with five well-signaled one-level-deep references (references/data-access.md, drug-queries.md, interactions.md, targets-pathways.md, chemical-analysis.md), all of which are real files, with content appropriately split out.

3 / 3

Total

9

/

12

Passed

Description

100%

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 specific, third-person, and clearly answers both what the skill does and when to use it with an explicit trigger clause. Trigger terms are natural and the DrugBank niche keeps conflict risk low.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities and data types such as "drug properties, interactions, targets, pathways, chemical structures, and pharmacology data" plus actions like access, analyze, "drug-drug interaction analysis", "chemical similarity searches", and "ADMET predictions", matching the multi-specific-action anchor.

3 / 3

Completeness

Clearly answers what ("Access and analyze comprehensive drug information from the DrugBank database including...") and when via the explicit "This skill should be used when working with..." trigger clause.

3 / 3

Trigger Term Quality

Covers natural terms a researcher would actually say, including "pharmaceutical data", "drug discovery research", "pharmacology studies", "drug-drug interaction analysis", "target identification", and "ADMET predictions".

3 / 3

Distinctiveness Conflict Risk

DrugBank is a specific named database niche with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.