Learn
Verified@ivangdavila
npx machina-cli add skill @ivangdavila/learn --openclawData Storage
~/learn/
├── topics/ # One folder per topic
│ └── {topic}/
│ ├── concepts.json # Concepts with SR schedule
│ ├── notes.md # Study notes
│ └── progress.md # Mastery tracking
├── reviews/ # Due review queue
│ └── due.json
└── config.json # Preferences
Create on first use: mkdir -p ~/learn/{topics,reviews}
Scope
This skill:
- ✅ Creates learning plans in ~/learn/
- ✅ Tracks concepts with spaced repetition
- ✅ Generates quizzes for active recall
- ✅ Reminds user when reviews are due (stores schedule in ~/learn/reviews/)
- ❌ NEVER accesses external learning platforms without permission
- ❌ NEVER stores data outside ~/learn/
Quick Reference
| Topic | File |
|---|---|
| Cognitive principles | cognition.md |
| Spaced repetition math | retention.md |
| Verification methods | verification.md |
Core Rules
1. Workflow
Goal → Plan → Study → Practice → Verify → Review
2. Active Recall Only
NEVER passive review. Always:
- Ask question first, user answers
- Then show correct answer
- User rates: easy / good / hard / wrong
3. Starting a Topic
- User states what they want to learn
- Create ~/learn/topics/{topic}/
- Break down into concepts
- Add to spaced repetition queue
4. Spaced Repetition
In concepts.json:
{
"concept_name": {
"added": "2024-03-15",
"interval_days": 1,
"next_review": "2024-03-16",
"ease_factor": 2.5,
"reviews": 0
}
}
After each review:
- Correct → increase interval (×ease_factor)
- Incorrect → reset to 1 day
5. Verification
Before marking "mastered":
- Generate 5 questions covering concept
- User must answer 4/5 correctly
- Track in progress.md (topic folder)
6. Configuration
In ~/learn/config.json:
{
"depth": "standard",
"learner_type": "practical",
"daily_review_limit": 20
}
Overview
Learn creates organized learning plans in ~/learn, tracks concepts with spaced repetition, and generates active recall quizzes. It stores all data locally with a clear folder structure for topics, reviews, and config, ensuring privacy and control over your learning data.
How This Skill Works
On first use, Learn creates ~/learn/topics/{topic}/ with concepts.json, notes.md, and progress.md to manage SR schedules. It queues due reviews in ~/learn/reviews/due.json and follows the workflow: Goal → Plan → Study → Practice → Verify → Review, using interval adjustments via an ease_factor. Mastery verification requires generating 5 questions and answering 4 correctly before marking a concept mastered.
When to Use It
- Starting a new topic or domain and want a local, structured plan
- Building long-term memory for exams or certifications
- Creating a personal, offline knowledge base with clear tracking
- Learning across multiple domains using a consistent SR and recall approach
- Need a privacy-first system that stores all data in ~/learn without external platforms
Quick Start
- Step 1: mkdir -p ~/learn/{topics,reviews}
- Step 2: mkdir -p ~/learn/topics/{topic}/; create concepts.json, notes.md, progress.md inside
- Step 3: Edit ~/learn/config.json for depth, learner_type, and daily_review_limit; begin first review cycle
Best Practices
- Follow the Active Recall workflow: ask first, then reveal, and rate difficulty
- Break topics into concepts and track each in concepts.json with SR data
- Update intervals and ease_factor after each review to optimize spacing
- Use the 5-question verification (4/5 correct) before marking mastered
- Keep notes.md and progress.md up to date; rely on ~/learn/reviews/due.json for reminders
Example Use Cases
- A student creates a calculus topic with concepts like limits and derivatives, studying via SR and quizzes
- A software engineer learns a new language by adding concepts (syntax, patterns) and scheduling reviews
- A language learner builds vocabulary lists as topics and practices active recall before exams
- A project manager masters a framework by breaking it into concepts and tracking mastery
- A hobbyist learns photography techniques, stores notes, and reviews key concepts on a set schedule
