Is the Smart Learn skill free?

Yes. The skill itself is free from HYH926/smart-learn. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Smart Learn SkillProof Score?

7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 2/5.

How do I install Smart Learn?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Smart Learn with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Smart Learn

Feynman-method study loop that writes notes into a Word doc and a mind map

by HYH926 · HYH926/smart-learn

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.6/10
Tested: Jul 30, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · 6534972

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 30, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

The Word half is real: docx_utils.py built a styled .docx that reopens cleanly with headings and per-step sections intact. The mind map half is not — the Mermaid file it emits puts every concept at the same indent level as the root, and Mermaid 11.16 rejects it with "There can be only one root", so the artifact the skill advertises as rendering natively in GitHub, VSCode, Notion and Obsidian renders nowhere (one extra level of indentation fixes it). The teaching structure genuinely changes the answer: explaining Kubernetes Services unaided opened with a definition and 10 pieces of jargon, while the skill's five-dimension template opened from motivation, used one jargon term, a non-technical analogy and a boundary-layer self-test question. Expect one manual fix: every bundled command is written as python .claude/skills/smart-learn/... so it fails from a project directory once the skill is installed globally.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 2/5

What Smart Learn does

Runs a five-step Feynman learning loop (concept map, explanation, self-test, association, summary) over any topic you want to master, and persists each step to a Markdown note, a Word document and a Mermaid mind map in knowledge_store/. Triggers on /smart-learn <topic> or phrasings like "teach me X" and "help me systematically learn X", and stays quiet for simple definition or summarisation requests. Interface and templates are in Chinese.

How to install Smart Learn

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Smart Learn

/smart-learn Feynman-method study loop that writes notes into a Word doc and a mind map

It also activates on plain-language prompts like these:

教我系统学习一下Kubernetes里Service网络模型，用费曼学习法讲一遍
帮我系统学习一下DDD领域驱动设计这个主题，生成完整学习笔记和一份思维导图存下来
/smart-learn 分布式事务这个主题，把整个学习过程存成一份Word文档给我

Frequently asked questions

Is the Smart Learn skill free?: Yes. The skill itself is free from HYH926/smart-learn. SkillProof publishes the install command and an independent test verdict at no cost.
Does Smart Learn work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 30, 2026. Verdict: Works with setup. The Word half is real: docx_utils.py built a styled .docx that reopens cleanly with headings and per-step sections intact. The mind map half is not — the Mermaid file it emits puts every concept at the same indent level as the root, and Mermaid 11.16 rejects it with "There can be only one root", so the artifact the skill advertises as rendering natively in GitHub, VSCode, Notion and Obsidian renders nowhere (one extra level of indentation fixes it). The teaching structure genuinely changes the answer: explaining Kubernetes Services unaided opened with a definition and 10 pieces of jargon, while the skill's five-dimension template opened from motivation, used one jargon term, a non-technical analogy and a boundary-layer self-test question. Expect one manual fix: every bundled command is written as python .claude/skills/smart-learn/... so it fails from a project directory once the skill is installed globally.
What is the Smart Learn SkillProof Score?: 7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 2/5.
How do I install Smart Learn?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Smart Learn with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.