fda-database

Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/fda-database/SKILL.md

Quality

Content

68%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 highly actionable, well-structured skill with executable examples and clean reference navigation, held back by some verbosity and the absence of explicit validation feedback loops for its batch query operations.

Suggestions

Tighten the Overview and Best Practices/Troubleshooting sections — assume Claude knows what openFDA is and what rate limiting entails.

Add an explicit validation checkpoint in batch/pagination workflows (e.g. check meta.results.total and error fields between batches, retry on failure).

Move more per-endpoint detail into the references/*.md files, leaving SKILL.md as a tighter overview that points outward.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with abundant code, but the ~500-line body includes some unnecessary explanation (the openFDA Overview, Best Practices DO/DON'T, and Troubleshooting padding) that could be trimmed.	3 / 5
Actionability	Provides extensive copy-paste-ready, executable Python tied to real bundled scripts, with concrete examples covering common cases across every endpoint category.	5 / 5
Workflow Clarity	Patterns and error-handling sections give a rough sequence, but batch operations (query_all, pagination) lack an explicit validate→fix→retry feedback loop, so the batch-operation cap of 3 applies.	3 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references to real references/*.md files per category, though a fair amount of endpoint detail still lives inline in SKILL.md rather than being fully deferred.	4 / 5
	Total	15 / 20 Passed

Description

75%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 specific, distinctive description that clearly states capabilities and targets a well-defined FDA-data niche, but it omits any explicit 'Use when...' trigger guidance, capping its completeness.

Suggestions

Append a 'Use when...' clause, e.g. 'Use when the user needs FDA regulatory data, adverse-event analysis, recall monitoring, or substance/UNII lookup.'

Add a few natural synonyms (e.g. 'side effects', 'FDA recalls', 'drug labels') to broaden trigger coverage.

Consider third-person verb consistency — 'Query' is fine, but pairing it with an explicit trigger phrase would round out completeness.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions and endpoint types — 'drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII)' — giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	The 'what' is clear ('Query openFDA API for...') but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('adverse events', 'recalls', 'regulatory submissions', 'safety research') but is missing some common synonyms and file/format variants, so not fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	Targets a clear FDA-specific niche with distinct triggers (openFDA, 510k, PMA, UNII), making overlap with other skills minimal.	5 / 5
	Total	17 / 20 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
skill_md_line_count	SKILL.md is long (516 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/fda-database/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.