CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

openfda-database

Query, search, and download data from the openFDA API for drugs, devices, foods, tobacco, cosmetics, animal and veterinary products, substances, and transparency data. Use for FDA adverse events, recalls, labeling, approvals, shortages, 510(k) clearances, NDC lookups, and any FDA safety or regulatory data query across all 28 API endpoints.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

80%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, highly actionable skill body with excellent progressive disclosure and copy-paste-ready commands. Its main weakness is the Workflow section, which lacks explicit validation checkpoints for its batch download operation, and some repeated rate-limit warnings.

Suggestions

Add an explicit validation/verification checkpoint to the Workflow (e.g., after `download`, verify the output file's record count against `total_matching` before analyzing), and an error-recovery loop for rate-limit or partial-fetch failures.

De-duplicate the rate-limit / API-key guidance: keep it once in Prerequisites (or Core Rules) and reference it rather than restating the same 1,000/day warning in three places.

Consider mentioning the `count` subcommand as a first Workflow step for exploratory analysis before committing to a large `download`, to reinforce the validation-friendly ordering.

DimensionReasoningScore

Conciseness

The body is mostly lean commands and executable examples, but the rate-limit / API-key warning recurs three times (Prerequisites, Core Rules, and the Warning callout), creating minor redundancy that could be trimmed; matches anchor 4 rather than 5.

4 / 5

Actionability

Copy-paste-ready `uv run scripts/openfda_query.py {search,count,download}` commands with real flags, stdout summaries, and documented options cover the common cases across search/count/download, matching the top anchor.

5 / 5

Workflow Clarity

The closing Workflow section lists a clear 5-step sequence, but it drives a batch operation (`download --all_results` with a 25,000-record cap) with no validation/verification checkpoints or error-recovery feedback loops, so the batch-operation cap holds it at 3.

3 / 5

Progressive Disclosure

The body is an overview that keeps essential quick-start inline while offloading bulk detail to verified one-level-deep references (api_endpoints.md, recipes.md) with clearly signaled markdown links; matches the top anchor.

5 / 5

Total

17

/

20

Passed

Description

95%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 the skill's actions and explicit use-when triggers with rich natural keywords. It is highly distinct and unlikely to conflict with other skills.

DimensionReasoningScore

Specificity

Names three concrete actions ("Query, search, and download data from the openFDA API") and enumerates the product domains, matching the anchor for several specific actions with minor gaps; not a 5 because the action verbs are limited (no count/aggregate/paginate) despite broad domain coverage.

4 / 5

Completeness

Explicitly answers both what ("Query, search, and download data from the openFDA API...") and when ("Use for FDA adverse events, recalls...") with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Dense natural trigger terms users would actually say ("adverse events, recalls, labeling, approvals, shortages, 510(k) clearances, NDC lookups") give comprehensive coverage of synonyms and domain phrasings, matching the top anchor.

5 / 5

Distinctiveness Conflict Risk

"openFDA API" and "all 28 API endpoints" carve a clear niche with distinct, FDA-specific triggers and minimal overlap risk with other skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

google-deepmind/science-skills

Path

skills/openfda_database/SKILL.md

Revision

4de6786

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill