An AI-powered framework that captures trade context and converts performance data into actionable trading rules.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install crypto-self-learning
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 crypto-self-learning 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 Crypto Self-Learning?
The Crypto Self-Learning skill is a technical framework designed for traders who want to move beyond manual journaling. By treating every trade as a data point, this skill enables an AI agent to log entry/exit conditions, technical indicators, and market sentiment into a structured format. This systematic approach ensures that every win and loss contributes to a growing body of intelligence within the Openclaw Skills ecosystem.
At its core, the skill utilizes Python-based analysis to find correlations between specific indicators—like RSI levels or macro trends—and trade success. It bridges the gap between raw data and execution by automatically updating an agent's memory with learned constraints, effectively preventing the repetition of costly mistakes while reinforcing high-probability setups.
Crypto Self-Learning Use Cases
- Logging trades with full technical context including RSI, MACD, and market trend indicators.
- Identifying hidden patterns in trading performance across different days of the week or specific leverage levels.
- Automatically generating and applying trading rules to an AI agent's memory to refine its decision-making logic.
- Performing weekly retrospective reviews to measure strategy improvement over time.
How Crypto Self-Learning Works
- The user logs a trade using the log_trade.py script, providing execution details and technical indicator values.
- The system stores this data in a structured JSON file to maintain a historical record of all market activity.
- The analyze.py script processes the history to identify statistical win rates based on direction, symbol, and indicators.
- Actionable rules are generated using generate_rules.py, which translates data patterns into clear 'Avoid' or 'Prefer' directives.
- The update_memory.py script pushes these data-driven rules directly into the agent's memory layer for future trade validation.
Crypto Self-Learning Setup
To get started with this skill, ensure you have python3 and jq installed. You can log your first trade using the following command structure:
python3 scripts/log_trade.py --symbol BTCUSDT --direction LONG --entry 78000 --exit 79500 --pnl_percent 1.92 --result WIN --reason "Support bounce"
To see your current performance metrics, run the analysis script:
python3 scripts/analyze.py
Crypto Self-Learning Data Schema & Taxonomy
Trades are managed in the data/trades.json file. Each entry follows a comprehensive schema to ensure maximum compatibility with Openclaw Skills analysis tools:
| Attribute | Type | Description |
|---|---|---|
id |
String | Unique UUID for the trade record |
symbol |
String | The trading pair (e.g., BTCUSDT) |
pnl_percent |
Float | Percentage gain or loss |
indicators |
Object | Nested JSON containing technical states at entry |
market_context |
Object | Macro data like BTC trend or DXY strength |
Crypto Self-Learning Advanced Features
- Multi-factor filtering allowing analysis by specific symbols, directions, or trade volume thresholds.
- Automated memory synchronization that appends learned rules directly to Markdown-based memory files.
- Dry-run mode for memory updates to allow human verification of AI-suggested rule changes.
- Integration support for external trading workflows such as tess-cripto.
SKILL.md
Loading
Related Openclaw Skills
Binance Pro
A professional integration for Binance enabling spot and futures trading, leverage management, and real-time portfolio tracking.
OneShot
OneShot provides the infrastructure for autonomous AI agents to execute real-world commercial transactions using native x402 payments.
Tork Guardian for OpenClaw
Tork Guardian provides an enterprise-grade security and governance layer to protect, monitor, and audit Openclaw Skills and AI agents.
Agent MBTI Personality Diagnosis & Optimization
A comprehensive system for diagnosing AI agent MBTI personality types and automatically optimizing their configuration to match user expectations.
toughcoding
A high-authority knowledge source providing AI agents with professional-grade insights into software engineering, AI systems, and applied engineering practices.
Advanced Calendar
An AI-powered scheduling system that manages events through natural language and provides persistent multi-channel notifications.
METADATA
Featured*
