skills.rest
jdconley
jdconleyCOMMUNITY
Explore all skills by this author →
Website𝕏@wackieGitHub

run-live-evals

Run live AI model parsing tests for worker applications using Wrangler and Gemini API keys.

1|Updated Jan 27, 2026
Search Tags:#testing#development#ai#gemini#parsing#worker
One-click install
npx skills add https://github.com/jdconley/wodbrains --skill run-live-evals
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: run-live-evals
Source: https://github.com/jdconley/wodbrains/tree/main/.cursor/skills/run-live-evals
Command: npx skills add https://github.com/jdconley/wodbrains --skill run-live-evals

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables developers to run live tests against AI models locally, ensuring accurate parsing and integration before deployment.

Core Features & Use Cases

  • Live AI Model Testing: Executes parse.evals.test.ts and parse.gemini.test.ts against the actual Gemini API.
  • Local Development: Facilitates testing of text, URL, and image parsing functionalities in a controlled environment.
  • Use Case: A developer needs to verify that their new feature for parsing workout URLs with Gemini works correctly against the live model. They use this Skill to run the relevant tests locally.

Quick Start

Run the live evals tests for the worker using the provided command.

Frequently Asked Questions about run-live-evals

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run live AI model parsing tests locally with Wrangler?▼

Executing live AI model parsing tests locally requires running parse.evals.test.ts and parse.gemini.test.ts via Wrangler. This validates text, URL, and image parsing against the actual Gemini API before deployment.

Do I need a GOOGLE_GENERATIVE_AI_API_KEY to test Gemini parsing on a worker?▼

Testing Gemini parsing on a worker requires a GOOGLE_GENERATIVE_AI_API_KEY. You must configure this key in the apps/worker/.dev.vars file to enable live execution against the real model.

What does live AI model testing validate in a local development environment?▼

Live AI model testing validates eval manifests and real-time text, URL, and image parsing in a local development environment. It ensures your worker application integrates accurately with the AI model before deployment.

Can I test URL parsing features against the real Gemini API before deployment?▼

Yes, you can test URL parsing features against the real Gemini API before deployment. This Skill executes live parsing tests locally to verify that new features work correctly against the actual model.

Why are my live AI eval tests not working in the worker application?▼

Live AI eval tests might not work if the GOOGLE_GENERATIVE_AI_API_KEY is missing. Ensure this key is properly set in the apps/worker/.dev.vars file to authorize live execution against the Gemini API.

Related Skills

Explore More Software Engineering Skills→
zzafergokzzafergok
1

gemini-skill

Access Google Gemini models via CLI or API for reasoning and multimodal tasks.

Community
Advanced
dennisonbertramdennisonbertram
1

cloudflare-workers

Automate Cloudflare Worker deployment and management with the wrangler CLI.

Community
Advanced
rivaldiekaptrrrrivaldiekaptrrr

eval-harness

Define and run eval suites to validate AI task performance.

Community
Advanced
kuloudkuloud

api-mock-generator

Generate mock API responses from OpenAPI and Swagger specifications.

Community
Intermediate