auth-patterns
About
This Claude Skill provides Better-auth integration patterns for implementing authentication features like login, registration, and protected routes. It includes guarded queries/forms for protected endpoints and handles email verification requirements. Key principles include using `getRequestEvent()` for cookie access and placing redirects outside try/catch blocks since they throw errors.
Documentation
Auth Patterns
Quick Pattern
// Login form
export const login = form(schema, async ({ email, password }) => {
const event = getRequestEvent();
await auth.api.signInEmail({
body: { email, password },
headers: event.request.headers,
});
redirect(303, '/dashboard'); // Outside try/catch
});
// Protected query
export const get_data = guarded_query(() => {
return { message: 'Protected data' };
});
Core Principles
- Use
getRequestEvent()for headers (cookie access) - Redirect MUST be outside try/catch (throws error)
- Use
guarded_query/form/commandfor protected endpoints - Email verification required before login
- Commands cannot redirect - use client-side
goto()
Reference Files
- auth-setup.md - Complete better-auth configuration
- auth-usage.md - All auth patterns and examples
- email-verification.md - Email verification flow
Quick Install
/plugin add https://github.com/spences10/devhub-crm/tree/main/auth-patternsCopy and paste this command in Claude Code to install this skill
GitHub 仓库
Related Skills
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
llamaguard
OtherLlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.
evaluating-llms-harness
TestingThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
langchain
MetaLangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.