drug-labels-search

Search FDA drug labels with natural language queries. Official drug information, indications, and safety data via Valyu.

Quality

61%

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/drug-labels-search/SKILL.md

Quality

Content

65%

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

The body is highly actionable with executable commands and a clear output contract, but it carries marketing fluff and inline integration examples that hurt token efficiency, and its workflows lack explicit validation checkpoints.

Suggestions

Remove or condense the 'Why This Skill is Powerful' marketing section and fold the Python/TypeScript SDK integration into a separate reference file to reduce inline padding.

Add an explicit validation step in the search workflow (e.g., check the JSON 'success' field and 'result_count' before presenting results, and retry or report on failure).

Ensure referenced bundle files (scripts/search, scripts/search.mjs) actually exist in the scripts/ directory, or correct the paths so references resolve.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable commands and output schema, but the 'Why This Skill is Powerful' marketing section and the full Python/TypeScript SDK integration add padding Claude does not need, and the 'Common Use Cases' section repeats near-identical commands.	2 / 3
Actionability	Provides fully executable copy-paste commands (e.g., 'scripts/search "ibuprofen warnings" 15'), a complete output JSON schema, exit codes, and jq recipes.	3 / 3
Workflow Clarity	The setup flow is sequenced (setup_required -> ask for key -> run setup -> retry), but the main search path lacks validation checkpoints such as confirming 'success: true' or 'result_count > 0' before reporting.	2 / 3
Progressive Disclosure	Single-file structure with clear sections, but it references scripts/search and scripts/search.mjs that are not present in the bundle, and inline content (SDK integration, use-case examples) that could be split out is kept in the main file.	2 / 3
	Total	9 / 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 is clear and distinct, naming the FDA drug-label search niche and primary action, but it omits an explicit 'when to use' trigger clause and offers only moderate keyword coverage.

Suggestions

Add an explicit 'Use when...' clause naming triggers users would say (e.g., 'Use when the user asks about FDA drug labels, indications, contraindications, dosing, or drug safety data').

Expand trigger terms to include common natural variants like 'prescribing information', 'contraindications', 'drug interactions', and 'adverse reactions'.

Lead with concrete verb actions (e.g., 'Search and retrieve') rather than the brand source 'via Valyu' to maximize natural-language trigger match.

Dimension	Reasoning	Score
Specificity	Names the domain and primary action ('Search FDA drug labels with natural language queries') plus data types ('indications, and safety data'), but does not enumerate multiple distinct concrete actions.	2 / 3
Completeness	Clearly states what the skill does but provides no explicit 'Use when...' trigger clause; per the rubric, a missing explicit when-guidance caps completeness at 2.	2 / 3
Trigger Term Quality	Includes natural terms a user might say ('FDA drug labels', 'indications', 'safety data'), but coverage of common variations is limited and 'via Valyu' is an internal/technical detail.	2 / 3
Distinctiveness Conflict Risk	The FDA drug-labels niche coupled with the Valyu source is a clear, narrow domain 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/drug-labels-search/SKILL.md
Commit: df37802

Reviewed: 3 minutes 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.