Testing and QA

Always verifies against npm ground truth and GitHub commits.

Version : 3.0.0 (14 Known Issues Added) Package : @google/genai@1.35.0 (⚠️ NOT @google/generative-ai) Last Updated : 2026-01-21

Version : Production Ready ✅ Package : openai@6.16.0 Last Updated : 2026-01-20

Source details, install context, and public review data are available on the full page.

Source details, install context, and public review data are available on the full page.

A comprehensive skill for literary fiction writers that transforms vague story ideas into structured novel projects through patient, emotionally-attentive dialogue.

Status : Production Ready ✅ Last Updated : 2026-01-20 Dependencies : cloudflare-worker-base (for Worker setup) Latest Versions : wrangler@4.59.2, @cloudflare/workers-types@4.20260109.0, aws4fetch@1.0.20

Principle-based patterns for designing website sections that feel human-designed, not AI-generated. Each pattern teaches WHY and WHEN, not just templates to copy.

Pydantic is a great way to declare a source of truth for a batch job, especially for ML. You can declare something like:

Expert Product Marketing playbook for Series A+ startups expanding internationally with hybrid PLG/Sales-Led motion.

Source details, install context, and public review data are available on the full page.

The most popular framework for building LLM-powered applications.

Source details, install context, and public review data are available on the full page.

Advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.

Dogfood web apps by browsing them as a real user would — with their goals, their patience, and their context. Goes beyond "does it work?" to "is it good?" by tracking emotional friction (trust, anxiety, confusion), counting click efficiency, testing resilience, and asking the ultimate question: "would I come back?"...

Source details, install context, and public review data are available on the full page.

The Interactions API is a unified interface for interacting with Gemini models and agents. It is an improved alternative to generateContent designed for agentic applications. Key capabilities include:

Safely migrate Convex schemas and data when making breaking changes.

Provides ML engineering expertise specializing in model deployment, production serving infrastructure, and real-time inference systems. Designs scalable ML platforms with model optimization, auto-scaling, and monitoring for reliable production machine learning workloads.

Use this skill whenever the task involves server-side authentication or identity in a CloudBase project, and the code is running in Node.js , for example:

This skill is the base operating playbook for Grimoire.

Source details, install context, and public review data are available on the full page.

Provide a systematic checklist for conducting thorough code reviews. This skill helps reviewers ensure code quality, catch bugs, identify security issues, and maintain consistency across the codebase.

Use gh to locate failing PR checks, fetch GitHub Actions logs for actionable failures, summarize the failure snippet, then propose a fix plan and implement after explicit approval.