← Back to Skills Marketplace
178
Downloads
3
Stars
1
Active Installs
7
Versions
Install in OpenClaw
/install quick-learn
Description
A Feynman-based learning coach for systematic multi-day learning plans and quick article/book breakdowns. Supports EN and ZH.
Usage Guidance
This skill appears internally consistent with its stated purpose. Before installing, be aware that: (1) it will create and store plan/state files under learning-data/{slug} on the agent host; (2) it instructs the agent to perform web searches and fetch pages (network activity) to verify sources; (3) it will create scheduled cron-like jobs to push daily content — these recurring actions persist until disabled. The included script (scripts/learner.py) only generates path/quiz JSON and lists plans. If you accept scheduled pushes and local storage for plans, this skill is reasonable to use. If you are uncomfortable with autonomous scheduled pushes or persistent files, review/inspect the skill files and disable autonomous invocation or refuse cron creation before enabling the skill.
Capability Assessment
Purpose & Capability
Name/description (Feynman-based learning coach) match the behavior in SKILL.md and the included script: generating learning paths, quizzes, source-search guidance, saving plan files under learning-data/{slug}, and scheduling daily pushes. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
The runtime instructions direct the agent to perform web searches, fetch and inspect pages (headers, dates, GitHub commit times), write/read files under learning-data/{slug}, and create cron-style scheduled pushes. All of these actions are appropriate for a learning coach, but they do involve network fetches and persistent storage of plan/state data.
Install Mechanism
No install spec; this is instruction-only plus a small helper script (scripts/learner.py) included in the bundle. There are no downloads from external URLs or package installs, so nothing is written to disk beyond the skill's own files and any learning-data the agent creates during use.
Credentials
The skill requires no environment variables, no credentials, and no config paths. The actions described (web fetching and local plan files) do not require additional secrets; requested scope is proportionate to the described functionality.
Persistence & Privilege
The skill instructs creation of per-plan cron schedules and persistent files (learning-data/{slug}/path.json, review-state.json, etc.). always is false. Scheduling recurring pushes is consistent with a learning coach but is a persistence capability users should be aware of (it will schedule future agent actions and write plan state to disk).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install quick-learn - After installation, invoke the skill by name or use
/quick-learn - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.5.0
Language policy optimization: allow natural mixing of technical terms (State, Props, useEffect) in user's primary language, while forbidding gratuitous mixing. All reference files updated with consistent language notes.
v2.4.0
Compressed SKILL.md from 568 to 243 lines (-57%), merged 10 reference files to 5 (-52% total size), fixed 4 critical bugs (ZH template english word, input validation, error recovery, long-plan template cycling), security scanner optimized
v2.3.0
Reduce security scanner false positives: shortened description, removed embedded bash scripts, softened web_fetch/web_search language to natural descriptions, removed explicit tool name references where not needed
v2.2.0
Fix remaining gaps from 19-scenario analysis: (1) Add review card answer evaluation templates (correct/partially correct/wrong/don't know); (2) Add zero-data weekly report template; (3) Add Mermaid diagram ASCII fallback rules; (4) Fix mixed-language topic detection (ZH request + EN topic → ZH output with EN topic name preserved)
v2.1.0
Fix 5 critical issues: (1) Review cron architecture — isolated session only pushes card, chain scheduling handled by main session; (2) Add Mode B (Quick Learn) output templates with structured breakdown format; (3) Define clear day completion rules and Feynman 1-5 star scoring rubric; (4) Fix chain scheduling logic contradiction (1d→3d→7d nodes); (5) Add language detection rules, error handling, time ratio formula, knowledge map % formula, multi-plan progress format
v2.0.0
Add bilingual (EN/ZH) support: all documentation, prompts, templates, and scripts now support both English and Chinese with auto language detection
v1.0.0
Initial release: 快速学习教练，支持多日系统学习和快速单篇解读，费曼学习法驱动，遗忘曲线复习，知识图谱，学习周报，风格自适应
Metadata
Frequently Asked Questions
What is Quick Learn?
A Feynman-based learning coach for systematic multi-day learning plans and quick article/book breakdowns. Supports EN and ZH. It is an AI Agent Skill for Claude Code / OpenClaw, with 178 downloads so far.
How do I install Quick Learn?
Run "/install quick-learn" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Quick Learn free?
Yes, Quick Learn is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Quick Learn support?
Quick Learn is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Quick Learn?
It is built and maintained by wjy (@wjyhahaha); the current version is v2.5.0.
More Skills