---

Preview

Project intro post

Beginner video tutorial

Quick Navigation

Overview · Recommended Workflow · Quick Start · Detailed Tutorial · Repository Structure · Suitable Topics · Customization · Customization · Compatibility Notes · Work with me

Overview

learn-anything-skill is a portable SKILL.md workflow package whose goal is not just to answer questions, but to help users actually learn.

• default role: mentor + project coach
• default method: Project-Driven Learning + Mastery Learning
• default outputs: study plans, study notes, session reviews, project briefs, mastery checks, and mistake logs
• default behavior: writes key learning outputs into Markdown files in the current working directory instead of leaving everything inside chat history
• default source strategy: prioritizes official docs, primary sources, canonical texts, and authoritative institutions, while separating factual basis from judgment and advice
• default projectization:
  • programming topics: demos, micro-projects, debugging tasks, and small project briefs
  • non-programming topics: short reports, presentation outlines, case analyses, knowledge maps, reading notes, and review documents

Good fit for:

• learners who want a structured path into a new topic
• people who want to move from "I know it" to "I can apply and transfer it"
• builders who prefer project-driven learning over passive explanation
• toolmakers who want a reusable open-source skill for Codex, Claude Code, and OpenCode users

Recommended Learning Directory Workflow

Do not study inside a cluttered general workspace if you can avoid it.
Create a dedicated learning directory first, then invoke the skill from inside that directory.

For example:

mkdir -p learn-ai
cd learn-ai

Then use learn-anything-skill inside that directory.

Why this is recommended:

• study plans can be saved automatically as Markdown files
• study notes can accumulate over time instead of disappearing into chat history
• session reviews, mastery checks, and mistake logs stay in one place
• materials, exercises, notes, and project briefs for one topic do not get mixed into unrelated projects

By default, the skill prefers writing learning outputs into a study/ subdirectory under the current working directory, for example:

learn-ai/
└── study/
    ├── ai-learning-plan.md
    ├── ai-notes.md
    ├── ai-session-review.md
    ├── ai-mastery-check.md
    └── ai-mistakes-log.md

Quick Start

1. Install the skill

Recommended via Agent Skills CLI:

npx skills add read2017/learn-anything-with-AI --skill learn-anything-skill

Global install:

npx skills add -g read2017/learn-anything-with-AI --skill learn-anything-skill

2. Create a learning directory

mkdir -p learn-ai
cd learn-ai

3. Start learning

Use $learn-anything-skill to help me learn SQL.
I know some Python but have never studied databases systematically.
Please create a 4-week study plan and design a small project brief.

Detailed Tutorial

The homepage keeps only the shortest path. For full installation guidance, platform-specific setup, usage patterns, examples, and prompt recipes, see:

• Chinese tutorial: docs/tutorial.md
• English tutorial: docs/tutorial.en.md

Recommended order for new users:

1. watch the intro post or beginner video
2. follow the quick start steps above
3. use the detailed tutorial for your long-term study workflow

Repository Structure

skills/
└── learn-anything-skill/
    ├── SKILL.md
    ├── agents/
    │   └── openai.yaml
    ├── references/
    │   ├── mastery-rubric.md
    │   ├── project-patterns.md
    │   ├── source-strategy.md
    │   └── teaching-playbook.md
    └── assets/
        ├── learning-plan-template.md
        ├── mistakes-log-template.md
        ├── mastery-check-template.md
        ├── project-brief-template.md
        ├── session-review-template.md
        └── study-notes-template.md

Suitable Topics

This skill is not only for programmers. It works well for:

• programming and software engineering
• mathematics and statistics
• economics and finance fundamentals
• English and other language learning
• history, social science, and humanities reading
• writing, speaking, and communication training
• AI, LLM, and data-related topics

Customization

Common changes include:

• changing the tone or default language
• shifting the project style toward exams, papers, real-world work, or portfolio building
• changing the source strategy to emphasize official docs or textbook reading
• changing mastery checks to focus on problem solving, oral explanation, code implementation, or paper interpretation

Best files to edit first:

• skills/learn-anything-skill/SKILL.md
• skills/learn-anything-skill/references/source-strategy.md
• skills/learn-anything-skill/references/project-patterns.md
• skills/learn-anything-skill/references/mastery-rubric.md

Compatibility Notes

• OpenAI / Codex / ChatGPT Skills: this is the most native target format
• Claude Code: usable directly as a skill; for broader distribution, a plugin wrapper is recommended
• OpenCode: better treated as a command adaptation than as a fully identical skill system
• Other Agent Skills-compatible tools: prefer npx skills add

In short: the core asset in this repository is the portable SKILL.md + references + assets workflow. Installation entry points differ across agents, but the teaching logic is reusable.

Expand references

These resources helped shape the installation and compatibility guidance:

• OpenAI Skills: https://openai.com/academy/skills/
• ChatGPT Skills help: https://help.openai.com/en/articles/20001066
• Codex app introduction: https://openai.com/index/introducing-the-codex-app/
• Claude Code cheatsheet: https://support.claude.com/en/articles/14553413-claude-code-cheatsheet
• Claude Code plugins: https://code.claude.com/docs/en/plugins
• OpenCode commands: https://opencode.ai/docs/commands

Support this project

If this skill helped you actually learn something:

• ⭐ Star — helps more people find it
• 👀 Watch — subscribe to updates and get notified on new releases
• Fork — make it yours (tone, project style, and source strategy are all meant to be edited; see Development & Customization)

Questions, feature requests, or a new project pattern to nominate? Open an Issue.

Buy me a coffee

This project took a good number of evenings. If it's been useful, you can buy me a coffee:

_{WeChat 赞赏码 (China) · tips only, not for purchasing services}

International readers: Ko-fi (link TBD).

---

Work with me

This repo came out of a problem I had myself. If you're in a similar spot, I offer 1-on-1 services:

Service	Who it's for	What you get
Custom skill	You have a workflow, knowledge base, or content you want packaged as a skill an AI can actually use	Scoping call → a working SKILL.md package
Persona distillation	You want a creator's or expert's public content turned into an AI assistant that answers in their style	Full pipeline: corpus collection, analysis, statistics, and skill delivery
AI workflow consulting	You want AI embedded in your real business process, not stuck in a chat box	A feasibility assessment for your specific case

A real example: jianghushuo-oral-skill — distilling a creator with 4.89M followers from 433 videos (947k characters) into a single skill: 6 mental models, 15 documented internal contradictions, an independent blind-test score of 90/100, and every quote traceable to the exact second in the original video.

📮 [email protected] — tell me your use case, I usually reply the same day (English or Chinese).

Scope note: persona-distillation work only covers content you have the right to use — your own accounts, material you're licensed for, or public content for personal research. I don't process other people's content on someone else's behalf.

---

About the author

沉思哲 / Chen Sizhe（AI 产品研发）· GitHub @read2017

I turn things I've actually built into reusable AI tooling, and document the process on Xiaohongshu and Douyin (Chinese platforms).

抖音 Douyin

小红书 Xiaohongshu

📮 [email protected]

License

This repository is released under the MIT License.