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

72%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/fda-database/SKILL.md

Quality

Content

75%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.

The body is highly actionable, with executable Python examples for every category, error handling, and pagination, and it makes good use of real one-level-deep reference files. Its main weaknesses are verbosity from duplicated capability/pattern content that belongs in the references or examples script, and validation that is shown as error-handling guidance rather than explicit workflow checkpoints.

Suggestions

Trim or remove the 'Key capabilities' bullet list (it duplicates 'When to Use This Skill' and the per-category endpoint lists) to cut token overhead.

Move the four 'Common Query Patterns' code blocks into the existing scripts/fda_examples.py or a reference file, keeping only one short pattern inline in SKILL.md.

Cut the 'Additional Resources' and 'Getting Help' sections (or fold the two most useful links into the existing API Reference section) — external browsing links add little actionable value.

Dimension	Reasoning	Score
Conciseness	The body mostly avoids explaining concepts Claude already knows, but has noticeable padding: the 'Key capabilities' list duplicates 'When to Use This Skill' and the per-category endpoint lists, the ~120-line 'Common Query Patterns' section duplicates scripts/fda_examples.py, and 'Additional Resources'/'Getting Help' sections add little. Fits anchor 3 ('mostly efficient but includes some unnecessary explanation or could be tightened') more than anchor 4, which allows only minor trimming.	3 / 5
Actionability	Fully executable, copy-paste-ready guidance throughout: Quick Start setup, per-category query snippets, pagination via fda.query_all, an explicit error-handling pattern ('if "error" in result'), and DO/DON'T best-practice examples. Matches anchor 5 ('fully executable; specific examples cover the common cases').	5 / 5
Workflow Clarity	The sequence (setup -> API key -> query -> handle results) is clear, and the Error Handling and Troubleshooting sections provide checkpoints for failure cases. Validation is implicit in the patterns rather than an explicit validate-step per workflow, matching anchor 4 ('most checkpoints present; minor validation gaps'); the destructive-operation cap does not apply since queries are read-only.	4 / 5
Progressive Disclosure	Good structure with well-signaled, verified one-level-deep references: each category ends with 'See references/<file>.md for detailed documentation', an API Reference section maps all six reference files, and both scripts are documented. However, the body still inlines endpoint lists and ~120 lines of query patterns that overlap the reference files, matching anchor 4 ('most content appropriately placed; minor organization gaps') rather than anchor 5.	4 / 5
	Total	16 / 20 Passed

Description

70%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.

The description is specific and clearly distinct within the FDA-regulatory-data niche, naming concrete endpoints and identifiers. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness, and some natural trigger-term synonyms are missing.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about FDA drug/device safety, adverse events, recalls, 510(k) clearances, PMA approvals, drug shortages, or UNII/CAS substance lookup.'

Include natural user phrasings such as 'side effects', 'drug labeling', 'drug shortages', and 'food recalls' to broaden trigger-term coverage to match the body's actual scope.

Mention the food and veterinary data domains covered by the skill so the description's scope matches the content.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Query openFDA API for... adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII)' — but coverage has gaps (no mention of labeling, NDC, food/veterinary data despite the body covering them). Fits anchor 4 ('several specific actions; minor gaps'), not 5 (not comprehensive) and not 3 (well more than 1-2 actions named).	4 / 5
Completeness	The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance — 'for FDA regulatory data analysis and safety research' is a purpose statement, only weakly implying 'when'. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains good natural keywords users would say: 'adverse events', 'recalls', 'drugs', 'devices', '510k', 'PMA', 'UNII', 'FDA'. A few natural terms are missing (e.g., 'side effects', 'drug shortages', 'food safety', 'labeling'), matching anchor 4 rather than 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	Terms like 'openFDA API', '510k', 'PMA', and 'UNII' pin a clear FDA-regulatory-data niche with distinct triggers and minimal overlap risk with other skills, matching anchor 5.	5 / 5
	Total	16 / 20 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 (524 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/fda-database/SKILL.md
Commit: 4082a2e

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.