crypto-self-learning
Self-learning system for crypto trading. Logs trades with full context (indicators, market conditions), analyzes patterns of wins/losses, and auto-updates trading rules. Use to log trades, analyze performance, identify what works/fails, and continuously improve trading accuracy.
Why use this skill?
Learn from every trade with the crypto-self-learning skill. Log, analyze, and generate data-driven trading rules to optimize your AI agent's accuracy.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/totaleasy/crypto-self-learningWhat This Skill Does
The crypto-self-learning skill is an advanced AI-driven feedback loop designed to transform raw trading data into actionable intelligence. By treating every trade as an experimental data point, this skill systematically logs trade performance, context, and technical indicators. It provides a structured mechanism to move beyond intuitive guessing by calculating win rates across various market conditions, technical setups, and leverage levels. Through its integrated analysis and rule-generation scripts, it synthesizes historical performance into concrete, data-backed heuristics, ensuring your OpenClaw agent evolves its decision-making process based on actual historical outcomes.
Installation
To integrate this skill into your environment, use the OpenClaw repository manager. Execute the following command in your terminal:
clawhub install openclaw/skills/skills/totaleasy/crypto-self-learning
Once installed, ensure your environment has the necessary write permissions to the directory where you store your trading logs and memory files, as the skill needs to write and update markdown-based memory files to persist learned rules.
Use Cases
This skill is perfect for systematic traders and developers building autonomous bots. It excels in:
- Performance Auditing: Identifying specific times of day or market conditions where a strategy underperforms.
- Pattern Recognition: Automatically highlighting that certain indicators, like RSI levels, lead to higher probabilities of success when combined with macro context.
- Strategy Optimization: Converting raw CSV data into a clean 'Learned Rules' list that can be directly referenced by the agent during future trading sessions.
Example Prompts
- "OpenClaw, log my recent BTCUSDT long position: entry 78000, exit 79500, with an RSI of 28 and leverage of 5x."
- "Analyze my trading performance for the last 10 trades and show me which indicators contribute most to my wins."
- "Generate new trading rules based on my history and apply them to my agent memory file so I can trade more effectively tomorrow."
Tips & Limitations
The quality of the insights generated is strictly proportional to the quality of data provided. Always include the '--indicators' and '--market_context' flags; the more context you provide, the deeper the analytics. Note that the 'generate_rules' function is descriptive, not predictive—it summarizes past success but requires human oversight to ensure that historical market regimes remain relevant to current price action. Always use the '--dry-run' flag when updating memory to review changes before committing.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-totaleasy-crypto-self-learning": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution