← Back to Skills Marketplace
ivangdavila

Learning

by Iván · GitHub ↗ · v1.0.3 · MIT-0
cross-platform ✓ Security Clean
9001
Downloads
8
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install learning
Description
Teaches any topic in adaptive sessions: probes prior knowledge, calibrates depth and format, and checks retention before advancing. Use when the user says teach me, explain this, ELI5, break it down, or help me understand or study something, when an explanation is not landing (re-asks, blank answers, "makes sense" with no follow-through), when material learned earlier keeps getting forgotten, when practice answers are confidently wrong, or when pacing study before an exam or deadline. Not for building a multi-week study plan or curriculum tracker, and not for authoring flashcard decks.
Usage Guidance
Install this if you want a tutor that remembers learning preferences, past misses, and topic progress between sessions. Review or clear the local files under ~/Clawic/data/learning/ if you do not want that history retained, especially on shared machines.
Capability Assessment
Credentials
Local reads and writes are limited to the learning data directory, migration from older learning directories, and a shared profile fallback for language/locale; this is proportionate to cross-session tutoring but should be visible to users.
Install Mechanism
The inspected artifact is markdown/json skill content with no executable scripts; metadata declares the local config path used by the skill.
Instruction Scope
Instructions are mostly scoped to tutoring behavior, but they do direct the agent to keep local learner preferences, hypotheses, and topic logs across sessions.
Persistence & Privilege
The skill automatically records declared preferences, observed format signals, and session results in local files without per-write confirmation; this is purpose-aligned but privacy-relevant.
Purpose & Capability
The skill's capabilities are centered on teaching, diagnostic probes, retrieval checks, retention scheduling, and adapting format or pacing to learner evidence.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install learning
  3. After installation, invoke the skill by name or use /learning
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
Display name shown correctly
v1.0.2
Full coverage pass: deeper guides, situation-named files, and per-user configuration
v1.0.1
Complete rewrite with real, actionable learning techniques
v1.0.0
Initial release - Auto-adaptive learning preferences
Metadata
Slug learning
Version 1.0.3
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 4
Frequently Asked Questions

What is Learning?

Teaches any topic in adaptive sessions: probes prior knowledge, calibrates depth and format, and checks retention before advancing. Use when the user says teach me, explain this, ELI5, break it down, or help me understand or study something, when an explanation is not landing (re-asks, blank answers, "makes sense" with no follow-through), when material learned earlier keeps getting forgotten, when practice answers are confidently wrong, or when pacing study before an exam or deadline. Not for building a multi-week study plan or curriculum tracker, and not for authoring flashcard decks. It is an AI Agent Skill for Claude Code / OpenClaw, with 9001 downloads so far.

How do I install Learning?

Run "/install learning" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Learning free?

Yes, Learning is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Learning support?

Learning is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Learning?

It is built and maintained by Iván (@ivangdavila); the current version is v1.0.3.

💬 Comments