← Back to Skills Marketplace
6782
Downloads
12
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install crypto-self-learning
Description
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.
Usage Guidance
Install only if you are comfortable storing trade history locally in plaintext and letting generated trading rules be written into an agent memory file. Use the dry-run mode and review the target MEMORY.md changes before applying them, especially because those rules may influence future trading decisions.
Capability Analysis
Type: OpenClaw Skill
Name: crypto-self-learning
Version: 1.0.0
The OpenClaw skill 'crypto-self-learning' is designed for local crypto trade analysis and rule generation. All scripts (`analyze.py`, `generate_rules.py`, `log_trade.py`, `update_memory.py`) operate on local JSON files within the skill's `data` directory. The `SKILL.md` instructions and the `update_memory.py` script's modification of `MEMORY.md` are directly aligned with the stated purpose of updating the agent's learned rules, without any evidence of prompt injection, data exfiltration, remote execution, or other malicious behaviors. Required binaries (`jq`, `python3`) are standard and appropriate for the task.
Capability Assessment
Credentials
The skill reads and writes local trade data under its own data directory and may print financial trading summaries to stdout, which is proportionate but potentially sensitive.
Install Mechanism
Metadata only declares required local binaries jq and python3, with no package installation, remote retrieval, dependency changes, or executable installer behavior.
Instruction Scope
Instructions are user-directed CLI commands with explicit log, analyze, generate, and dry-run memory update flows; there are no prompt overrides, hidden role changes, or unrelated agent instructions.
Persistence & Privilege
Persistence is limited to local trades.json, learned_rules.json, and a user-supplied MEMORY.md path; the memory update is disclosed and has a dry-run option, but users should review it because it can affect future agent behavior.
Purpose & Capability
The scripts log trades, analyze win/loss patterns, generate heuristic learned rules, and optionally update a MEMORY.md file; this matches the stated purpose, though the missing weekly_review.py reference and AI/self-learning wording overstate the implementation.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install crypto-self-learning - After installation, invoke the skill by name or use
/crypto-self-learning - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Self-learning system for crypto trading. Logs trades, analyzes patterns, generates rules, and auto-updates agent memory for continuous improvement.
Metadata
Frequently Asked Questions
What is 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. It is an AI Agent Skill for Claude Code / OpenClaw, with 6782 downloads so far.
How do I install Crypto Self-Learning?
Run "/install crypto-self-learning" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Crypto Self-Learning free?
Yes, Crypto Self-Learning is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Crypto Self-Learning support?
Crypto Self-Learning is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Crypto Self-Learning?
It is built and maintained by totaleasy (@totaleasy); the current version is v1.0.0.
More Skills