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

73%

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 ./skills/pharma/fda-database/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.

Highly actionable with extensive executable examples and a sensible overview-plus-references structure, but it is verbose for a SKILL.md and its progressive-disclosure references point to bundle files that are not present.

Suggestions

Trim sections that restate knowledge Claude already has (e.g. the generic response-structure block) and consolidate Best Practices/Troubleshooting to reduce the body length.

Either include the missing references/*.md and scripts/fda_query.py, scripts/fda_examples.py files in the bundle, or remove the dangling reference links so navigation resolves.

Add explicit validation/error-recovery checkpoints (e.g. check rate-limit and 'meta' presence before processing) to the multi-step query patterns to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	The ~510-line body is mostly efficient, executable code, but includes content Claude already knows (the meta/results response structure) and padded sections (Best Practices, Common Issues, Troubleshooting) that could be tightened; not the lean score-3 anchor but far from the padded score-1.	2 / 3
Actionability	Provides abundant copy-paste-ready executable code with concrete method calls (query_drug_events, count_by_field, query_device_510k, query_all) and specific search-syntax examples, matching the 'fully executable, copy-paste ready' anchor.	3 / 3
Workflow Clarity	Multi-step patterns (safety profile, temporal trends, comparative analysis) are sequenced as functions with light error guards, but there are no explicit validation checkpoints or validate→fix→retry feedback loops, fitting the 'sequence present but checkpoints implicit' score-2 anchor.	2 / 3
Progressive Disclosure	References are clearly signaled and one level deep ('See references/drugs.md for detailed documentation'), but the referenced references/.md and scripts/.py files are absent from the bundle, so navigation is asserted but not actually resolvable — the score-3 anchor requires verifiable one-level references.	2 / 3
	Total	9 / 12 Passed

Description

82%

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, well-trigger-keyworded description with a clear FDA niche, written in the correct voice. Its main gap is the absence of an explicit 'Use when…' trigger clause, which caps completeness at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when researching FDA adverse events, recalls, drug/device approvals, or substance identifiers (UNII).'

Consider mentioning the most common user phrasings verbatim (e.g. 'drug recalls', 'FDA approval lookup', 'side effect reports') to strengthen trigger-term naturalness.

Dimension	Reasoning	Score
Specificity	Enumerates concrete actions and endpoint families — 'drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII)' — matching the 'lists multiple specific concrete actions' anchor rather than the score-2 'some actions' level.	3 / 3
Completeness	Clearly answers 'what' but lacks any explicit 'Use when…' trigger clause; the trailing 'for FDA regulatory data analysis and safety research' only implies when, so per the guidelines completeness is capped at 2 rather than reaching the explicit-trigger score-3 anchor.	2 / 3
Trigger Term Quality	Uses natural terms a user would actually say ('adverse events', 'recalls', '510k', 'PMA', 'UNII', 'FDA regulatory data analysis and safety research'), giving good coverage; not the jargon-only score-1 or partial score-2 case.	3 / 3
Distinctiveness Conflict Risk	The openFDA/FDA-regulatory niche is distinct and unlikely to trigger the wrong skill, written in third person ('Query openFDA API…'); not the generic or overlapping score-1/2 anchors.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (518 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 16 missing	Warning

	Total	13 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/pharma/fda-database/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.