trading-strategist▌
kukapay/crypto-skills · updated Apr 8, 2026
Data-driven cryptocurrency trading strategies combining Binance market data, technical indicators, and sentiment analysis.
- ›Integrates real-time and historical price/volume data from Binance with calculated TA indicators (SMA, RSI, MACD, Bollinger Bands, Stochastic)
- ›Aggregates market sentiment from crypto RSS feeds to inform buy/sell/hold signals and entry/exit recommendations
- ›Generates risk management guidance including stop-loss levels, position sizing (1-5% of capital), and volatil
Trading Strategies Skill
This skill generates data-driven trading strategies for cryptocurrencies by integrating multiple data sources and analytical tools.
Core Components
- Binance Market Data: Real-time price, volume, and historical klines from Binance API
- Technical Analysis (TA): Calculated indicators including SMA, RSI, MACD, Bollinger Bands, Stochastic, and more
- Market Sentiment: Aggregated sentiment scores from popular crypto RSS feeds
Workflow
Step 1: Data Collection
- Fetch current ticker data from Binance API (
/api/v3/ticker/priceand/api/v3/ticker/24hr) - Retrieve historical klines (
/api/v3/klineswith 30-100 days of data) - Aggregate sentiment using the market-sentiment skill
Step 2: TA Calculation
Use the scripts/calculate_ta.py script to compute indicators from historical data.
Step 3: Strategy Generation
Combine TA signals, price action, and sentiment score to recommend:
- Buy/Sell/Hold signals
- Entry/exit points
- Risk management (stop-loss, position sizing)
- Timeframes (swing, day trading)
Usage Examples
Basic Strategy Request
For ETH, generate a trading strategy based on current market data.
→ Fetch ETH data, calculate TA, get sentiment, output strategy.
Advanced Analysis
Analyze BTC with 50-day history, include sentiment, recommend swing trade.
→ Use longer history, focus on swing signals.
Risk Management
- Always include stop-loss recommendations
- Suggest position sizes (1-5% of capital)
- Warn about volatility and leverage risks
- Note: Not financial advice
References
- TA formulas: See references/ta_formulas.md
- Sentiment interpretation: See references/sentiment_guide.md
Scripts
scripts/calculate_ta.py: Python script for TA indicator calculationsscripts/fetch_binance.py: Helper for Binance API calls ./skills/trading-strategies/SKILL.md
Discussion
Product Hunt–style comments (not star reviews)- No comments yet — start the thread.
Ratings
4.7★★★★★32 reviews- ★★★★★Shikha Mishra· Dec 24, 2024
We added trading-strategist from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
- ★★★★★Ganesh Mohane· Dec 20, 2024
trading-strategist is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
- ★★★★★Kabir Gill· Dec 4, 2024
trading-strategist reduced setup friction for our internal harness; good balance of opinion and flexibility.
- ★★★★★Evelyn Patel· Nov 23, 2024
Registry listing for trading-strategist matched our evaluation — installs cleanly and behaves as described in the markdown.
- ★★★★★Aanya Okafor· Nov 15, 2024
Solid pick for teams standardizing on skills: trading-strategist is focused, and the summary matches what you get after install.
- ★★★★★Sakshi Patil· Nov 11, 2024
Keeps context tight: trading-strategist is the kind of skill you can hand to a new teammate without a long onboarding doc.
- ★★★★★Kaira Iyer· Oct 14, 2024
trading-strategist fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
- ★★★★★Aditi Shah· Oct 6, 2024
We added trading-strategist from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
- ★★★★★Chaitanya Patil· Oct 2, 2024
trading-strategist has been reliable in day-to-day use. Documentation quality is above average for community skills.
- ★★★★★Ira Bansal· Sep 21, 2024
trading-strategist has been reliable in day-to-day use. Documentation quality is above average for community skills.
showing 1-10 of 32