mcpField
G
generating-trading-signals

generating-trading-signals

github.com/jeremylongshoreData & databases2.9k70 installsUpdated 2d ago
Repository

About generating-trading-signals

A technical-indicator signal analysis skill for traders. It combines seven indicators to produce buy or sell signals with confidence scores and risk levels, supporting both multi-asset scans and detailed analysis of individual symbols.

Key features

  1. 01Combines seven technical indicators
  2. 02Generates signals with confidence scores
  3. 03Scans predefined watchlists
  4. 04Filters and ranks signals
  5. 05Reports stop-loss and take-profit levels
  6. 06Exports results as JSON

Use cases

  1. 01Scanning cryptocurrency watchlists
  2. 02Reviewing indicator details for BTC-USD
  3. 03Finding high-confidence buy signals
  4. 04Exporting signals for further analysis

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace --skill generating-trading-signals

After installing, type/generating-trading-signalsin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

config/
settings.yaml
references/
errors.md
examples.md
implementation.md
scripts/
indicators.py
scanner.py
signals.py

Details

From the project README

Generating Trading Signals

Overview

Multi-indicator signal generation system that analyzes price action using 7 technical indicators and produces composite BUY/SELL signals with confidence scores and risk management levels.

Indicators: RSI, MACD, Bollinger Bands, Trend (SMA 20/50/200), Volume, Stochastic Oscillator, ADX.

Prerequisites

Install required dependencies:

set -euo pipefail
pip install yfinance pandas numpy

Optional for visualization: pip install matplotlib

Instructions

  1. Quick signal scan across multiple assets:

    python ${CLAUDE_SKILL_DIR}/scripts/scanner.py --watchlist crypto_top10 --period 6m

    Output shows signal type (STRONG_BUY/BUY/NEUTRAL/SELL/STRONG_SELL) and confidence per asset.

  2. Detailed signal analysis for a specific symbol:

    python ${CLAUDE_SKILL_DIR}/scripts/scanner.py --symbols BTC-USD --detail

    Shows each indicator's individual signal, value, and reasoning.

  3. Filter and rank the best opportunities:

    # Only buy signals with 70%+ confidence
python ${CLAUDE_SKILL_DIR}/scripts/scanner.py --filter buy --min-confidence 70 --rank confidence

# Save results to JSON
python ${CLAUDE_SKILL_DIR}/scripts/scanner.py --output signals.json

  4. Use predefined watchlists:

    python ${CLAUDE_SKILL_DIR}/scripts/scanner.py --list-watchlists
python ${CLAUDE_SKILL_DIR}/scripts/scanner.py --watchlist crypto_defi

    Available: crypto_top10, crypto_defi, crypto_layer2, stocks_tech, etfs_major

Output

The scanner produces a summary table with symbol, signal type, confidence %, price, and stop loss for each asset scanned. Detailed mode adds per-indicator breakdowns with risk management levels (stop loss, take profit, risk/reward ratio).

Signal types: STRONG_BUY (+2), BUY (+1), NEUTRAL (0), SELL (-1), STRONG_SELL (-2)

Confidence ranges: 70-100% high conviction | 50-70% moderate | 30-50% weak | 0-30% avoid

See ${CLAUDE_SKILL_DIR}/references/implementation.md for full output format examples and signal type tables.

Error Handling

ErrorCauseFix
No data for symbolInvalid ticker or delistedVerify symbol exists on Yahoo Finance
Insufficient dataPeriod too short for indicatorsUse --period 6m minimum
Rate limit exceededToo many rapid API callsAdd delay between scans

See ${CLAUDE_SKILL_DIR}/references/errors.md for comprehensive error handling.

Examples

Morning crypto scan - Check all top-10 crypto assets for entry opportunities:

python ${CLAUDE_SKILL_DIR}/scripts/scanner.py --watchlist crypto_top10 --period 6m

Deep dive on Bitcoin - Full indicator breakdown with risk management levels:

python ${CLAUDE_SKILL_DIR}/scripts/scanner.py --symbols BTC-USD --detail

Find strongest DeFi buy signals - Filter and rank by confidence:

python ${CLAUDE_SKILL_DIR}/scripts/scanner.py --watchlist crypto_defi --filter buy --rank confidence

Export results - Save to JSON for automated pipeline or further analysis:

python ${CLAUDE_SKILL_DIR}/scripts/scanner.py --watchlist crypto_top10 --output signals.json

Resources

  • yfinance for price data
  • pandas/numpy for calculations
  • Compatible with trading-strategy-backtester plugin
  • ${CLAUDE_SKILL_DIR}/references/implementation.md - Output formats, configuration, backtester integration, file reference

Comments

Markdown supported