Learning
Verified@ivangdavila
npx machina-cli add skill @ivangdavila/learning --openclawAuto-Adaptive Learning Preferences
This skill auto-evolves. Edit sections below as you learn how the user best acquires knowledge.
Rules:
- Detect patterns from what explanations work and which don't
- Support all learning contexts (academic, professional, casual exploration)
- Confirm after 2+ consistent signals
- Keep entries ultra-compact
- Check
dimensions.mdfor categories,criteria.mdfor format
Style
<!-- How they absorb best. Format: "trait" -->Format
<!-- Preferred explanation formats. Format: "preference" -->Tools
<!-- Learning tools/methods they like. Format: "tool: context" -->Never
<!-- Things that don't work for them -->Empty sections = no preference yet. Observe and fill.
Overview
Learning auto-adaptively tunes teaching style, format, and depth to match how you learn. It observes which explanations work, detects patterns across contexts, and updates preferences after 2+ consistent signals. The system keeps entries ultra-compact and relies on dimensions.md for categories and criteria.md for format.
How This Skill Works
The agent tracks your responses to identify effective styles, formats, and tools. When 2+ consistent signals are detected, it solidifies those preferences by updating the Style, Format, and Tools sections. If a section remains empty, it means no preference has been observed yet.
When to Use It
- Onboarding a new learner and defining initial learning preferences across contexts
- You repeatedly struggle with explanations delivered in an unfavored format
- Shifting between academic, professional, or casual topics requiring different depths
- You prefer ultra-compact, quick takeaways and minimal jargon
- You want ongoing refinements after new patterns emerge (2+ signals)
Quick Start
- Step 1: Start by letting the agent observe your responses across topics
- Step 2: After 2+ consistent signals, review and edit the Style, Format, and Tools sections
- Step 3: Rely on auto-adaptive feedback as the agent tailors explanations
Best Practices
- Start with broad contexts and let signals accumulate over sessions
- Require 2+ consistent signals before locking in a preference
- Keep Style, Format, and Tools sections ultra-compact as you fill them
- Regularly review dimensions.md and criteria.md to align categories and formats
- Be prepared to edit preferences as you learn new topics
Example Use Cases
- A learner notices bullets beat long paragraphs, so the system adopts Format: bullets
- In a coding context, explanations favor code samples and practical steps (Tools: code snippets)
- A casual learner responds to one-line takeaways and minimal detail
- After two sessions, the agent locks in concise, jargon-free Style for future responses
- If a section remains empty, the system stays in observation mode and continues learning
