fda-database

Query the openFDA API to retrieve FDA regulatory datasets (drugs, devices, adverse events, recalls, submissions, UNII) when you need programmatic safety/regulatory evidence for analysis or research.

Quality

76%

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 ./scientific-skills/Evidence Insight/fda-database/SKILL.md

Quality

Content

61%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 well-structured reference with a strong runnable example and clear separation of detail into real bundle files. It loses points on conciseness (soft hedges) and workflow clarity (no explicit validation checkpoints for batch/API operations).

Suggestions

Trim hedged phrases like 'typically accessed as', 'implementation-dependent', and the maintainer aside about pinning requirements to tighten token efficiency.

Add a short numbered workflow for a representative task with an explicit validation checkpoint (e.g., check meta.results.total and error objects before paginating with query_all).

Convert the enumerated reference file list into inline markdown links so the navigation is directly clickable rather than a plain list.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code and little concept-over-explanation, but several hedges and asides ('typically accessed as', 'implementation-dependent', 'the repository implementation', 'If you maintain this skill') could be trimmed without losing clarity.	3 / 5
Actionability	Provides a full, runnable Python example using real FDAQuery methods plus bash commands and query-syntax patterns covering common cases; minor gaps remain because exact method signatures are deferred to scripts/fda_query.py.	4 / 5
Workflow Clarity	The example functions imply a sequence, but there is no explicit numbered workflow and no validation/error-checkpoint guidance for batch retrieval (query_all) or API error handling beyond 'guard for missing results'.	3 / 5
Progressive Disclosure	The body is an overview that splits detailed endpoint/query material into one-level-deep reference files (references/*.md) and scripts, all of which exist; references are clearly signaled though listed as a plain enumeration rather than inline links.	4 / 5
	Total	14 / 20 Passed

Description

92%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 strong, specific description that clearly states what the skill does and when to use it, with a comprehensive enumeration of supported datasets. Minor trigger-term variations could be added but it is otherwise excellent.

Dimension	Reasoning	Score
Specificity	Names the concrete action ('Query the openFDA API to retrieve FDA regulatory datasets') and enumerates multiple specific dataset types (drugs, devices, adverse events, recalls, submissions, UNII), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (retrieve FDA regulatory datasets across the listed domains) and 'when' ('when you need programmatic safety/regulatory evidence for analysis or research') with a concrete trigger clause.	5 / 5
Trigger Term Quality	Includes natural terms users would say ('adverse events', 'recalls', 'submissions', 'UNII', 'safety/regulatory evidence'), but misses a few common variations such as '510(k)', 'drug labels', or file/format synonyms.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (openFDA regulatory/safety data) with distinct triggers (UNII, recalls, adverse events) and minimal overlap risk; uses proper third-person voice.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/fda-database/SKILL.md
Commit: 63c61d3

Reviewed: 6 hours 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.