Agent Skills Hub

respond

Manually finalize and submit AI agent responses to Claude. Use when automatic synchronization fails or to manually curate findings.

glyphbox

A framework for an LLM-based NetHack agent that dynamically synthesizes Python code in a secure sandbox to perform complex dungeon exploration and gameplay actions via a high-level API.

bilibili-chapter-generator

Generate Bilibili-compatible video chapter lists from SRT subtitle files with strict format validation.

sast-configuration

Automate SAST configuration and security scanning. Supports Semgrep, SonarQube, and CodeQL for DevSecOps, quality gate management, and vulnerability detection.

debug

Debug package implementation guide for LobeHub. Provides standardized logging patterns, namespace conventions, and configuration for browser, Node.js, and Electron environments.

api-connector

Integrate with REST APIs to manage authentication, execute HTTP requests, and process JSON responses seamlessly within your development workflow.

ui-styling

Build accessible, consistent UIs using shadcn/ui and Tailwind CSS. Employs a component-first architecture for design systems, React Hook Form integration, and responsive mobile-first development.

solve-challenge

A CTF solver agent that performs triage on challenges, identifies the vulnerability category, and routes tasks to specialized skills for web, pwn, crypto, forensic, and reverse engineering analysis.

handoff-pack

Generates structured Handoff Pack prompts for delegating scoped coding tasks to Gemini with clear instructions, acceptance criteria, and output requirements.

wednesday-design

UI/UX design assistant that enforces component library usage, accessibility, and design tokens for React/Next.js projects. Ensures consistent visual output using shadcn/ui, Aceternity, and other approved libraries.

librarian

Fetch, index, and search developer documentation from GitHub and websites to provide AI agents with accurate, grounded, and version-specific code context.

youtube-rl-tracker

A reinforcement learning-inspired tracker for YouTube performance, using systematic logging to optimize thumbnails, titles, and hooks.