twwch

Next Chat Skills — AI skill for Claude Code

AI community

AI assistant application based on Next.js, supporting Dialog Management and external Skill (script/tool/rule) integration.

How to install Next Chat Skills

This entry records only its repository, not the path inside it, so there is no exact command to give. Open twwch/next-chat-skills and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Next Chat Skills does

AI assistant application based on Next.js, supporting Dialog Management and external Skill (script/tool/rule) integration. AI autonomously decides to invoke Skills, executes scripts in a Black box, installs dependencies, and generates files.

Alternatives in AI

  • AIHawk — Open-source AI browser agent: describe any task in plain language and it autonomously browses, clicks, types a 30.3k ★
  • Hexstrike AI — HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomousl 8.2k ★
  • Cursor Tools — by eastlondoner - Creates a versatile AI command interface supporting multiple providers and models with flexi 4.7k ★

README

Next-Chat-Skills

English | [中文](./README_CN.md)

An AI assistant application built with Next.js, featuring conversation management and external Skill (scripts/tools/rules) integration. The AI autonomously decides when to invoke Skills, executing scripts in a sandboxed environment, installing dependencies, and generating files.

Demo

![Demo](./images/20260204-115652.png)

![Demo](./images/20260204-145302.gif)

![Demo](./images/20260204-160514.gif)

Tech Stack

  • Framework: Next.js 16 (App Router) + React 19 + TypeScript 5
  • AI: Vercel AI SDK (@ai-sdk/openai)
  • UI: Tailwind CSS 4 + shadcn/ui (Radix UI)
  • Database: Drizzle ORM with SQLite and PostgreSQL backends
  • Skills: Loaded from local ~/.claude/skills directory, parsed from SKILL.md (YAML frontmatter)

Getting Started

1. Install Dependencies

npm install

2. Configure Environment Variables

Copy `.env.local.example` or create `.env.local` manually:

# AI Model Configuration
OPENAI_API_KEY=your-api-key
OPENAI_BASE_URL=https://api.openai.com/v1
OPENAI_MODEL=gpt-4o
SKILLS_DIR=~/.claude/skills

# Storage Configuration: 'sqlite' or 'postgresql'
STORAGE_TYPE=sqlite

# SQLite (used when STORAGE_TYPE=sqlite)
SQLITE_PATH=./data/chat-skills.db

# PostgreSQL (used when STORAGE_TYPE=postgresql)
# DATABASE_URL=postgresql://user:password@localhost:5432/chatskills

3. Start the Development Server

npm run dev

Open [http://localhost:3000](http://localhost:3000) to use the application.

Data Storage

The application supports two database backends through an abstract `StorageProvider` interface, switchable via the `STORAGE_TYPE` environment variable:

SQLite (Default)

  • Zero configuration, works out of the box
  • Data stored at ./data/chat-skills.db (customizable via SQLITE_PATH)
  • Database files are excluded in