openfda-database

Query, search, and download data from the openFDA API for drugs, devices, foods, tobacco, cosmetics, animal and veterinary products, substances, and transparency data. Use for FDA adverse events, recalls, labeling, approvals, shortages, 510(k) clearances, NDC lookups, and any FDA safety or regulatory data query across all 28 API endpoints.

Quality

86%

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

72%Weight 40%Scale 1-3

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

A highly actionable, well-structured skill body with executable commands and good progressive disclosure. It is slightly verbose in spots and lacks an explicit validation checkpoint for its batch download workflow.

Suggestions

Trim the redundant category enumeration in the Recipes intro and rely on the reference link instead of restating the skill's full scope.

Add an explicit validate/verify step to the Workflow for batch downloads (e.g., check record count and handle partial/failed pages before analyzing).

Either remove the inlined 28-endpoint mapping or drop the pointer to api_endpoints.md to avoid duplicating the same listing in two places.

Dimension	Reasoning	Score
Conciseness	Largely lean and operational, but the Recipes intro re-enumerates every category already named in the description, and the full 28-endpoint mapping is inlined while also pointing to api_endpoints.md — could be tightened.	2 / 3
Actionability	Provides fully executable bash commands with real flags, query strings, and output paths for search/count/download, copy-paste ready.	3 / 3
Workflow Clarity	A clear 5-step Workflow sequence exists, but the batch download path (--all_results up to 25,000 records) has no explicit validate/feedback checkpoint, which caps workflow clarity.	2 / 3
Progressive Disclosure	SKILL.md is a clear overview with one-level-deep, well-signaled references to real files (api_endpoints.md, recipes.md); detail is appropriately split out.	3 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, specific, third-person description with concrete actions and explicit trigger guidance covering natural user terms. It clearly distinguishes the openFDA regulatory-data niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Query, search, and download data") plus enumerated product categories and use cases in third-person voice, matching the multi-action anchor.	3 / 3
Completeness	Answers both what (query/search/download from openFDA API) and when via the explicit "Use for..." trigger clause, which is equivalent to a "Use when" trigger.	3 / 3
Trigger Term Quality	Covers natural terms users would say — "FDA adverse events, recalls, labeling, approvals, shortages, 510(k) clearances, NDC lookups" — giving good trigger coverage.	3 / 3
Distinctiveness Conflict Risk	Targets a clear openFDA niche with distinct regulatory-data triggers, unlikely to collide with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: google-deepmind/science-skills
Path: skills/openfda_database/SKILL.md
Commit: 0b42509

Reviewed: 7 days 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.