CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

81

2.17x
Quality

77%

Does it follow best practices?

Impact

85%

2.17x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/fda-database/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

49%

Drug Safety Profile Report

Drug safety profile analysis

Criteria
Without context
With context

FDAQuery class import

0%

100%

Environment variable for API key

0%

100%

FDAQuery instantiation

0%

100%

Total count from meta

100%

100%

count_by_field for reactions

0%

100%

Exact match for reaction counting

100%

100%

Serious events filter

100%

100%

Specific field search

100%

100%

Error response handling

37%

100%

Recall query uses helper method

0%

100%

Output written to JSON file

100%

100%

85%

38%

Insulin Pump Regulatory Intelligence Report

Medical device cross-database surveillance

Criteria
Without context
With context

FDAQuery class import

0%

58%

Environment variable for API key

0%

100%

Device events helper method

0%

0%

510k clearances helper method

0%

100%

Multiple device endpoints queried

100%

100%

Caching not disabled

0%

100%

Error response handling

50%

100%

Specific field search

100%

100%

Total count from meta

100%

100%

Results written to JSON

100%

100%

Run log written

100%

100%

70%

49%

Food Allergen Recall Trend Dashboard

Temporal trend analysis and food safety monitoring

Criteria
Without context
With context

FDAQuery class import

0%

100%

Environment variable for API key

0%

100%

query_all() for pagination

0%

100%

YYYYMMDD date format

0%

0%

Date range syntax

0%

0%

Food recall helper method

0%

0%

Specific recall reason search

62%

100%

Sort parameter syntax

0%

100%

AND operator syntax

0%

100%

Error response handling

100%

100%

Results written to JSON

100%

100%

Repository
K-Dense-AI/claude-scientific-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

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.