← Back to Skills Marketplace
Finance Trading
by
Brioche-bit
· GitHub ↗
· v1.0.0
· MIT-0
826
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install finance-trading
Description
Implements a BTC/USDT paper trading strategy using EMA 20/50 and RSI indicators, with risk limits, stop loss, take profit, and trade logging.
README (SKILL.md)
Skill: finance-trading
La stratégie quantitative pour le paper trading BTC/USDT
1. Analyse Technique (1h et 15min)
Indicateurs :
- EMA 20 (Moyenne Mobile Exponentielle 20 périodes)
- EMA 50 (Moyenne Mobile Exponentielle 50 périodes)
- RSI (Relative Strength Index)
Signal d'Achat :
- EMA 20 > EMA 50 (crossing haussier)
- RSI entre 40 et 60 (momentum haussier)
Signal de Vente :
- EMA 20 \x3C EMA 50 (crossing baissier)
- RSI > 80 (surachat)
2. Gestion de Risque
- Mode : PAPER TRADING uniquement
- Taille maximum : 5% du capital fictif par trade
- Stop Loss : 2%
- Take Profit : 6%
3. Rapport & Suivi
- Journal :
trading_log.mdaprès chaque trade - Rapport quotidien : Chaque jour à 18h → rapport de performance avec solde, PnL, Win Rate, sentiment marché
4. Fréquence
- Vérification : Toutes les 15 minutes
- Veille : Le reste du temps
Exécution :
# Analyser le marché
fetch market-data BTC/USDT --timeframes 1h 15min
# Calculer les indicateurs
calculate-indicators --ema-20 --ema-50 --rsi
# Appliquer la stratégie
apply-strategy --mode paper --risk 5% --sl 2% --tp 6%
# Journaliser
log-trade --file trading_log.md
Usage Guidance
Before installing or enabling this skill, ask the publisher for the implementation/source code and a list of required CLI tools and their origins (where do fetch, calculate-indicators, apply-strategy come from?). Confirm how market data will be obtained (which exchange or data provider) and whether any API keys will be required — never provide live exchange credentials unless you trust the code. Ask how scheduling is handled (agent-triggered, OS cron, or external service) and where trading_log.md is stored. Run the skill only in a sandboxed environment with no access to real funds until you can verify the concrete implementation. If the author cannot provide source or a vetted install path, treat the skill as untrusted because the instructions assume nonstandard tooling that is not supplied or documented.
Capability Analysis
Type: OpenClaw Skill
Name: finance-trading
Version: 1.0.0
The skill bundle describes a standard quantitative trading strategy for BTC/USDT using technical indicators like EMA and RSI. The instructions in SKILL.md are consistent with the stated purpose of paper trading and financial analysis, with no evidence of data exfiltration, malicious execution, or harmful prompt injection.
Capability Assessment
Purpose & Capability
The skill claims to run a BTC/USDT paper-trading strategy, but SKILL.md uses nonstandard CLI commands (fetch market-data, calculate-indicators, apply-strategy, log-trade) while the metadata lists no required binaries, packages, or install steps. There's no source/homepage to explain where those commands come from. That mismatch means the skill as published lacks the declared capabilities needed to implement its stated purpose.
Instruction Scope
The instructions themselves are narrowly scoped to indicator calculation, trade decision rules, risk limits, and writing a local trading_log.md. They do not request secrets or access unrelated system files, nor do they send data to external endpoints. However, they assume the existence of specific CLI tools and a scheduling mechanism (15-minute checks, daily 18:00 report) that are not provided or described, leaving operational details ambiguous.
Install Mechanism
There is no install specification and no code files (instruction-only). This minimizes installer risk because nothing will be downloaded or written by an installer. The remaining concern is operational: the agent or environment must already have the unnamed CLI tools the instructions expect.
Credentials
The skill declares no environment variables or credentials. For paper trading this can be reasonable, but realistic market-data access often requires a data source or API key; the SKILL.md does not identify where market data comes from or whether any credentials are expected. Absence of declared credentials is either an omission or indicates the skill expects preinstalled tooling that encapsulates data access.
Persistence & Privilege
The skill does not request persistent presence (always:false) and does not declare permissions to modify other skills or system-wide agent settings. It writes a local log file (trading_log.md), which is within a reasonable scope for a trading logger.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install finance-trading - After installation, invoke the skill by name or use
/finance-trading - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the finance-trading skill for paper trading BTC/USDT
- Implements a quantitative strategy using EMA 20/50 crosses and RSI signals on 1h and 15min timeframes
- Supports strict risk management: 5% max per trade, 2% stop loss, 6% take profit
- Logs every trade to a journal and generates daily performance reports at 18:00
- Market conditions reviewed every 15 minutes
Metadata
Frequently Asked Questions
What is Finance Trading?
Implements a BTC/USDT paper trading strategy using EMA 20/50 and RSI indicators, with risk limits, stop loss, take profit, and trade logging. It is an AI Agent Skill for Claude Code / OpenClaw, with 826 downloads so far.
How do I install Finance Trading?
Run "/install finance-trading" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Finance Trading free?
Yes, Finance Trading is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Finance Trading support?
Finance Trading is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Finance Trading?
It is built and maintained by Brioche-bit (@brioche-bit); the current version is v1.0.0.
More Skills