drugbank-search

Search DrugBank comprehensive drug database with natural language queries. Drug mechanisms, interactions, and safety data powered by Valyu.

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/pharma/drugbank-search/SKILL.md

Quality

Content

50%

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-sectioned and offers concrete commands and a clear setup feedback loop, but it is padded with marketing and third-party integration content, and its central path-resolution instruction contradicts the examples that follow. Tightening the body and reconciling the script-path guidance would improve all dimensions.

Suggestions

Remove the 'Why This Skill is Powerful' and 'Adding to Your Project' sections, or move them to a separate reference file, to reduce token overhead.

Make every example use the resolved $DRUGBANK_SCRIPT path so guidance is internally consistent with the 'CRITICAL' path-resolution section.

Add an explicit validation checkpoint in the main search workflow (e.g. check the success field and surface the error before retrying), and provide the missing scripts/ bundle files referenced in the body.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but the 'Why This Skill is Powerful' marketing section and the 'Adding to Your Project' Python/TypeScript integration examples add tokens that do not directly help Claude execute the core search task.	2 / 3
Actionability	Provides concrete executable commands and jq examples, but the 'CRITICAL: Script Path Resolution' section mandates using a full resolved path while every later example reverts to the relative 'scripts/search' form, leaving inconsistent, incomplete guidance.	2 / 3
Workflow Clarity	The API key setup flow is a clear sequenced feedback loop (setup_required -> ask -> setup -> retry), but the main search workflow lacks explicit validation checkpoints beyond inspecting the success field, and the path-resolution step is not carried through consistently.	2 / 3
Progressive Disclosure	Sections are organized, but all content is inline in one monolithic file and the referenced bundle files (scripts/search, scripts/search.mjs) are not present in the bundle, so there is no real one-level-deep reference structure to navigate.	2 / 3
	Total	8 / 12 Passed

Description

57%

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 clearly identifies a distinctive niche and some natural trigger terms, but it relies on a single action verb and lacks an explicit 'Use when' trigger clause. Adding concrete actions and trigger guidance would raise specificity and completeness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about drug mechanisms, interactions, side effects, or pharmacology data.'

List more concrete actions beyond 'search' (e.g. 'look up drug interactions, find mechanisms of action, retrieve safety data').

Include common user phrasings like 'side effects' and 'adverse reactions' as natural trigger terms.

Dimension	Reasoning	Score
Specificity	Names the domain (DrugBank drug database) and several data categories ('Drug mechanisms, interactions, and safety data') but only one concrete action ('Search'), so it does not list multiple specific concrete actions as required for a 3.	2 / 3
Completeness	Clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Includes relevant natural terms like 'drug database', 'mechanisms', 'interactions', and 'safety data', but misses common variations users would say such as 'side effects', 'adverse reactions', or 'drug targets'.	2 / 3
Distinctiveness Conflict Risk	The DrugBank niche with Valyu-powered semantic search is clearly distinct and unlikely to trigger for unrelated skills.	3 / 3
	Total	9 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 9 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/pharma/drugbank-search/SKILL.md
Commit: df37802

Reviewed: about 1 hour 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.