A hands-on Vibe Coding course that teaches non-programmers and developers to build real AI-assisted products from idea to launch.
LearnPrompt/LearnPrompt
A free, open-source Chinese AI course and collection of practical skills covering Claude Code, Codex, OpenClaw, Hermes, prompt engineering, and image, voice and music AI tools.
- Stars
- 2,713
- Forks
- 227
- Open issues
- 0
- Last commit
- 3 days ago
What is it?
LearnPrompt is a continuously maintained Chinese-language AI learning path. It covers prompt engineering, ChatGPT, RAG, agents, AI coding with Claude Code and Codex, Obsidian, Midjourney, Stable Diffusion, Runway, digital humans, AI voice and music, and open-source LLM fine-tuning.
Beyond the course content, the repository is the home of a set of installable Agent Skills built by the author. They include tools for turning working skills into shared assets, distilling content strategy, managing Obsidian inboxes, publishing Feishu documents to X Articles, and monitoring public AI information sources with daily snapshots and reports.
The project aims to shift from tool-by-tool tutorials toward real tasks such as writing, slide making, knowledge base maintenance, and running a personal AI workstation across ChatGPT, Claude Code, Codex, Hermes, OpenClaw and Obsidian.
Key features
- 01Chinese-language course modules covering prompt engineering, ChatGPT, Midjourney, Stable Diffusion and open-source LLMs
- 02Tutorials for Claude Code, Codex, OpenClaw, Hermes and Obsidian workflows
- 03Installable Agent Skills for writing, Obsidian inbox management and content publishing
- 04A set of Karpathy-inspired Agent Skills for research loops and coding guidelines
- 05Free and open source, with a companion website at learnprompt.pro
Use cases
- Someone starting to learn AI tools and prompt writing from scratch in Chinese
- Developers who want to set up Claude Code, Codex or OpenClaw workflows
- Writers and content creators building a personal AI-assisted publishing pipeline with Obsidian and Feishu
Things to know
- The license could not be identified, so reuse terms are unclear.
Topics
FAQ
- What is LearnPrompt?
- A free, open-source Chinese AI course and collection of practical skills covering Claude Code, Codex, OpenClaw, Hermes, prompt engineering, and image, voice and music AI tools. LearnPrompt is a continuously maintained Chinese-language AI learning path. It covers prompt engineering, ChatGPT, RAG, agents, AI coding with Claude Code and Codex, Obsidian, Midjourney, Stable Diffusion, Runway, digital humans, AI voice and music, and open-source LLM fine-tuning.
- Is LearnPrompt free to use? What license does it have?
- LearnPrompt is open source under the Other license. Check the license terms before using it in commercial products.
- Is LearnPrompt still maintained?
- Actively maintained. The last commit to LearnPrompt was on Oct 19, 2026.
- What can I use LearnPrompt for?
- Someone starting to learn AI tools and prompt writing from scratch in Chinese Developers who want to set up Claude Code, Codex or OpenClaw workflows Writers and content creators building a personal AI-assisted publishing pipeline with Obsidian and Feishu
- Where can I get LearnPrompt?
- The source code and installation instructions are on GitHub: https://github.com/LearnPrompt/LearnPrompt
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A Chinese-language tutorial series for installing, configuring and building your own OpenClaw AI assistant, from beginner setup to custom Skills development.
A non-official Chinese learning handbook for the Pi Coding Agent terminal harness, covering setup through Skills, Extensions, Subagents and long-running workflows.
A curated Chinese-language guide to ChatGPT and frontier LLMs, covering usage, prompting, app development, agents, and productivity tools.
A CLI that one-command sets up Claude Code and Codex with bilingual prompts, workflows, API provider presets and MCP configuration.
A 17-lesson Python tutorial that builds a Claude Code-like agent harness from scratch, starting with a single loop and bash.