LearnPrompt: Free & Open-Source AI Practical Tutorials
A permanently free Chinese AI tutorial covering Claude Code, Codex, ChatGPT, Midjourney, and more, guiding you from basics to building your own AI workspace.
- Source repo
- LearnPrompt/LearnPrompt
- Stars
- ★ 2.7k
- Last updated
- 6d ago
- License
- NOASSERTION
- Primary language
- MDX
- FA score
- 0/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformChatGPT · Codex · Claude Code · OpenAI API · Claude API
- Cost
- Free, no paid service needed
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- AI beginners who want to learn prompt engineering, ChatGPT, Midjourney, etc., can start with LearnPrompt.
- Not a fit if
- Readers wanting a single-tool quick tutorial rather than real-task practice
- Learners who need a fully offline path with no external AI tools
- Teams needing content that stays fixed and never tracks tool updates
- Source review
- 0/100 · Major gaps 8 safety controls not found
What does this agent do, and when should you use it?
LearnPrompt is a permanently free and open-source Chinese AI practical tutorial project created and maintained by developer Carl. It provides a systematic learning path covering topics such as Claude Code, Codex, OpenClaw, Hermes, prompt engineering, ChatGPT, RAG, Agents, AI programming, Agent Skills, Obsidian, Midjourney, Runway, Stable Diffusion, digital humans, AI voice & music, and LLM fine-tuning. The project also spawns a series of Skills named after Chinese craftsmen (e.g., Luban, Paoding, Cailun) to refine, reuse, and propagate AI workflows. The tutorial website is learnprompt.pro, and the project itself serves as a public repository aiming to upgrade into an AI-native tutorial suited for real-world tasks.
LearnPrompt delivers structured tutorial content that teaches users how to use various AI tools. It reads and consolidates the latest information about these tools to generate step-by-step guides and examples. The project also maintains sub-projects like AI News Radar for monitoring AI information sources, the Luban Skill for polishing other Skills, and Humanize PPT for generating more human-like presentations. The Carl Skills repository collects and reuses real AI workflows, with support for automation via GitHub Actions. Users can access tutorials and updates through the official website, WeChat public account, Bilibili, and other channels.
- AI beginners who want to learn prompt engineering, ChatGPT, Midjourney, etc., can start with LearnPrompt.
- Content creators need AI assistance for writing, creating PPTs, and organizing materials, and can refer to real-task examples.
- Developers who want to understand workflows in Claude Code, Codex, and other AI coding tools can study relevant chapters.
- Knowledge management enthusiasts who want to combine Obsidian and AI to build personal knowledge bases can follow the methods.
- Agent developers who need reusable AI workflows can obtain and adapt them from the Carl Skills repository.
How do you install or deploy this agent?
The tutorial requires no installation; you can directly visit the official website learnprompt.pro. To use related Skills or tools, follow the README guides of each sub-project. For example, installing the Luban Skill requires Claude Code or Codex, and you need to follow the repository instructions. Specific installation steps vary by project but typically involve cloning the repository with Git and configuring the AI tool environment.
How do you use this agent?
Visit the official website or GitHub repository to read tutorials and choose topics of interest. For Skills, install them into environments like Claude Code or Codex according to their README. For instance, AI News Radar can be configured to run automatically with GitHub Actions, and the Luban Skill can call APIs to polish other Skills. Community support is available via WeChat or GitHub Issues.
What are this agent's strengths and limitations?
- Permanently free and open-source, continuously updated, beginner-friendly.
- Covers a wide range from tool basics to real tasks with concrete examples.
- Provides multiple reusable Skills to help automate workflows.
- Active community and author maintenance allow for feedback.
- Tutorial content may become outdated as AI tools evolve, requiring updates.
- Some advanced features depend on specific tools like Claude Code, with a learning curve.
- Installing Skills requires technical background; not purely beginner-friendly.
- The project involves multiple sub-repositories, making navigation potentially complex.
How does this agent compare with similar options?
Compared to other courses like Andrew Ng's ChatGPT Prompt Engineering, this tutorial emphasizes practical application and Chinese context; compared to Learn Prompting, it focuses more on tool coverage and real tasks.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| LearnPrompt: Free & Open-Source AI Practical Tutorials This agent | 0 · Major gaps | Web appFree | ★ 2.7k | 6d ago | MDX | ChatGPT · Codex · Claude Code · OpenAI API · Claude API |
| SEO Skills for AI Agents | 27 · Major gaps | — | ★ 537 | 12d ago | — | Codex · Claude Code |
| Patina Multilingual Writing Editor | 83 · Good | Agent plugin / skillFree + model costs | ★ 375 | 19d ago | JavaScript | Codex · Claude Code |
| LinkedIn Skills for Claude Code and Codex | 61 · Some gaps | Agent plugin / skillFree + model costs | ★ 4.9k | 3d ago | Python | Codex · Claude Code · Claude.ai |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows this is a tutorial repository with no Agent product code or configuration. There is no implementation of least privilege, user confirmation, data flow transparency, sensitive data handling, dependency security, external effects, rollback, or source attribution. Hence all trust criteria score 0.
The repository is primarily documentation and examples, with no executable code or tests. There is no evidence of self-consistency, dependency availability, or failure messages. Hence all reliability criteria score 0.
The repository targets AI learners, but does not define Agent capability boundaries, trigger precision, or environment fit. There is no Agent product, so all adaptability criteria score 0.
The repository has a README and LICENSE, but lacks install notes, naming stability, examples/FAQ, known limitations, versioning/changelog, and maintenance responsibility. The license is CC BY-NC-SA 4.0, but metadata says NOASSERTION. Hence all convention criteria score 0.
There is no usable Agent output, no evidence of marginal value or cost-benefit. Hence all effectiveness criteria score 0.
There are no verifiable claims, no cross-source corroboration, and no separation of fact and inference. Hence all verifiability criteria score 0.
- Not found in source: least-privilege scopingGrant only what the task needs: a dedicated account or read-only token, scoped to specific directories and repos.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: data-flow disclosureWatch which external services it contacts (proxy or firewall logs) and keep sensitive data out until you know where it goes.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Not found in source: verifiable attributionInstall from the official repo or registry and check the publisher and URL to avoid look-alike packages.
- This repository is a tutorial and documentation, not an Agent product; do not treat it as a runnable Agent.
- License metadata is NOASSERTION, but the actual LICENSE file is CC BY-NC-SA 4.0, an inconsistency.
- Dependencies include unpinned versions from GitHub (e.g., remark-bibtex), posing supply chain risks.