Agent Skills Hub

skill-code-review

Multi-LLM code review pipeline using consensus-based analysis to detect security, architectural, and quality issues.

typescript-pro

Advanced TypeScript development agent: implements complex types, generics, branded types, and tRPC integration for end-to-end type safety.

auth-patterns

Implement secure backend authentication (JWT, OAuth, Sessions) and authorization (RBAC, ABAC) patterns, including password hashing, MFA, and security best practices.

use-railway

Operate Railway infrastructure: manage projects, services, databases, object storage, deployments, environments, variables, logs, and performance metrics.

project-development

A framework for managing the end-to-end LLM project lifecycle, from evaluating task-model fit and pipeline architecture design to implementing structured output parsing and agent-assisted development.

read-file

Read and analyze any data file (CSV, JSON, Parquet, Avro, Excel, etc.) or remote URL (S3, HTTPS) using DuckDB. Automatically detect file formats and preview/profile datasets.

react-native-best-practices

React Native performance optimization guide covering FPS, TTI, bundle size, memory leaks, and profiling patterns based on Callstack's industry-standard expertise.

bear-notes

Manage and automate your Bear notes on macOS using the grizzly CLI tool.

writing-good-tests

Guidance for writing, reviewing, and refactoring software tests, focusing on integration strategies, condition-based waiting, and professional mocking patterns.

Vercel Deploying

Automated Vercel production deployment agent that fetches logs via MCP, identifies build errors, applies fixes, and retries until success.

writing-bundler-tests

Guides writing, debugging, and maintaining Bun bundler tests using itBundled and expectBundled to verify transpilation, minification, and code transformation.

debug-cuda-crash

Tutorial for identifying and resolving CUDA runtime crashes using FlashInfer's API logging framework.