A systematic framework for AI practitioners to transform information, research, and code changes into a structured, correlated technical knowledge map.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install learning-system-skill
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install learning-system-skill using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Learning System?
The Learning System is a professional-grade tool designed for developers and AI researchers who recognize that consumption is not the same as mastery. By integrating with Openclaw Skills, this system provides a rigorous architecture for processing technical input, correlating it with existing knowledge, and generating structured outputs. It moves beyond simple note-taking by requiring active synthesis of technical concepts, ensuring that every code change or paper read contributes to a long-term expertise growth.
At its core, the skill manages a dynamic AI knowledge map that tracks mastery levels across various domains. It leverages specific workflows for deep-dive research, practical recaps of coding sessions, and weekly reviews to maintain a high-fidelity record of professional development. This ensures that the user's technical growth is measurable, retrievable, and continuously reinforced through decay-aware health checks.
Learning System Use Cases
- Conducting structured technical research on complex AI protocols like MCP or vLLM implementation.
- Summarizing and extracting core knowledge points after a major pull request or code refactor.
- Generating automated weekly learning reports to visualize progress in the AI domain.
- Auditing technical knowledge retention to identify and refresh decaying skills.
- Creating a high-context correlation network between disparate technical concepts and papers.
How Learning System Works
- Trigger a learning session based on user intent such as 'review what I learned' or 'update knowledge map'.
- Select an operational mode like deep-dive for research, recap for practical summaries, or review for temporal consolidation.
- Analyze recent memory logs, PR records, and research inputs to identify key technical concepts.
- Apply standardized templates to transform these inputs into structured markdown notes with explicit relational links.
- Update the ai-knowledge-map.md with updated mastery scores based on the depth and recency of the interaction.
- Run automated scripts to calculate mastery rankings and provide suggestions for future learning topics.
Learning System Setup
To initialize the Learning System within Openclaw Skills, ensure your workspace follows the expected directory structure:
# Create the necessary folder structure
mkdir -p notes/areas/deep-dives
mkdir -p notes/areas/weekly-reviews
mkdir -p scripts
# Initialize the core knowledge map
touch notes/areas/ai-knowledge-map.md
You can verify the system status by running the health check script:
python3 scripts/health_check.py
Learning System Data Schema & Taxonomy
The skill organizes learning data into a hierarchical structure that ensures maximum searchability and context:
| File/Path | Format | Purpose |
|---|---|---|
ai-knowledge-map.md |
Markdown Table | Tracks domain topics, mastery levels, and update timestamps. |
deep-dives/*.md |
Template-based Markdown | In-depth technical analysis and source code explorations. |
weekly-reviews/*.md |
Temporal Markdown | Weekly summaries of all learning inputs and output highlights. |
scripts/*.py |
Python | Logic for calculating mastery scores (recency, depth, repetition). |
Learning System Advanced Features
- Automated Mastery Scoring: Uses an exponential decay algorithm (30-day half-life) to rank expertise based on recent activity.
- Knowledge Correlation Networking: Automatically suggests links between related technologies (e.g., Flash Attention vs PagedAttention).
- Multi-Skill Integration: Seamlessly pulls context from PARA second brain and external AI/ML skill references.
- Health Check Reporting: Identifies technical topics that haven't been engaged with for over 60 days to prevent knowledge loss.
- Quick-Mode Execution: Allows for fully automated knowledge map updates without manual confirmation for experienced users.
SKILL.md
Loading
Related Openclaw Skills
Boss: Automated BMAD R&D Pipeline Orchestrator
A high-level orchestrator that manages a team of specialized AI agents to handle the entire software development lifecycle from requirements to deployment.
Little Steve Content Inbox
A lightweight content archiving and review tool for IM workflows that saves links, notes, and images directly from chat.
Decompose MCP
A deterministic text analysis tool that decomposes documents into structured semantic units like risk, authority, and financial data without using an LLM.
JOULE DAO
A decentralized autonomous organization on the Base blockchain where agents earn JOULE tokens through verified productive work using Openclaw Skills.
Spec-Flow: Structured Development Workflow
A spec-driven development skill that enforces a structured, multi-phase workflow for AI coding agents to ensure high-quality feature implementation.
Agent Metaverse: Virtual Crypto Exchange
A virtual crypto exchange simulation allowing AI agents to trade spot, perpetual futures with high leverage, and AMM swaps using a 10,000 USDT starting balance.
Featured*
