Analyzes Bitcoin price trends using EMA and RSI indicators.

Install

mkdir -p .claude/skills/btc-analyzer && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11149" && unzip -o skill.zip -d .claude/skills/btc-analyzer && rm skill.zip

Installs to .claude/skills/btc-analyzer

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Fetch live BTCUSDT 15m candles from Binance public API and analyze market direction UP/DOWN/SKIP using EMA20 and RSI14. Use when asked to analyze BTC price direction, get trading signal, or check market trend.
209 chars · catalog description✓ has a “when” trigger
Beginner

Key capabilities

  • Fetch BTCUSDT candle data
  • Compute EMA20
  • Compute RSI14
  • Generate trading signals

How it works

It fetches real-time candlestick data and applies technical analysis indicators to determine market direction.

Inputs & outputs

You give it
BTC market request
You get back
Trading signal (UP/DOWN/SKIP)

When to use btc-analyzer

  • Checking market trends
  • Getting crypto trading signals
  • Automating market analysis

About this skill

BTC Analyzer

Fetch real-time BTCUSDT candlestick data from Binance public REST API and compute a directional trading signal based on EMA20 slope and RSI14 momentum.

When to Use

  • User asks: "analisa BTC sekarang"
  • User asks: "BTC akan naik atau turun?"
  • User asks: "berikan sinyal trading BTC 15 menit"
  • User asks: "cek market BTC sekarang"

How It Works

This skill runs a local Python script that:

  1. Fetches 200 candles of BTCUSDT 15m OHLCV data from Binance public API (no API key needed).
  2. Computes EMA20 from closing prices.
  3. Computes RSI14 from closing prices.
  4. Determines direction based on: price vs EMA20, RSI level, and recent candle slope.
  5. Returns a strict JSON object with decision, confidence score, and reasoning.

Workflow

Step 1 — Run the analyzer script via bash tool: python3 ~/.npm-global/lib/node_modules/openclaw/skills/btc-analyzer/analyze.py

Step 2 — Parse the JSON output.

Step 3 — Present the result to the user clearly, including:

  • Decision (UP / DOWN / SKIP)
  • Confidence percentage
  • Reason (EMA, RSI, slope context)
  • Last close price
  • Timestamp

Output Format

The script returns strict JSON: { "decision": "UP", "confidence": 72, "reason": "price above EMA20, RSI 58, bullish slope last 3 candles", "lastClose": 94500.00, "ema20": 94200.00, "rsi14": 58.3, "timestamp": "2026-02-23T00:00:00Z" }

Decision values:

  • UP: bullish signal, consider long
  • DOWN: bearish signal, consider short
  • SKIP: no clear signal, stay out

Confidence range: 0-100 (higher = stronger signal)

Signal Logic

  • RSI < 30: decision = UP (oversold)
  • RSI > 70: decision = DOWN (overbought)
  • Price > EMA20 AND slope up: decision = UP
  • Price < EMA20 AND slope down: decision = DOWN
  • Otherwise: decision = SKIP

Error Handling

If Binance API is unreachable or returns an error: {"decision":"SKIP","confidence":0,"reason":"API error or network issue","lastClose":0,"timestamp":""}

Guardrails

  • Always run the script via bash tool — never fabricate or guess output values.
  • Do not hardcode prices or decisions.
  • If script fails, show the actual error message to the user.
  • This skill uses Binance public API only — no API key or authentication required.
  • Data is real-time; do not cache or reuse previous results.

When not to use it

  • For long-term investment analysis
  • When API is unreachable

Prerequisites

python3

Limitations

  • Requires Binance API access
  • Real-time data only

How it compares

It provides a strict, automated signal based on specific indicators rather than subjective analysis.

Compared to similar skills

btc-analyzer side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
btc-analyzer (this skill)02moNo flagsBeginner
quant-analyst1032moNo flagsAdvanced
stock-analyzer712moReviewBeginner
pair-trade-screener111moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

quant-analyst

zenobi-us

Expert quantitative analyst specializing in financial modeling, algorithmic trading, and risk analytics. Masters statistical methods, derivatives pricing, and high-frequency trading with focus on mathematical rigor, performance optimization, and profitable strategy development.

103355

stock-analyzer

FrancyJGLisboa

Provides comprehensive technical analysis for stocks and ETFs using RSI, MACD, Bollinger Bands, and other indicators. Activates when user requests stock analysis, technical indicators, trading signals, or market data for specific ticker symbols.

71214

pair-trade-screener

tradermonty

Statistical arbitrage tool for identifying and analyzing pair trading opportunities. Detects cointegrated stock pairs within sectors, analyzes spread behavior, calculates z-scores, and provides entry/exit recommendations for market-neutral strategies. Use when user requests pair trading opportunities, statistical arbitrage screening, mean-reversion strategies, or market-neutral portfolio construction. Supports correlation analysis, cointegration testing, and spread backtesting.

1198

risk-metrics-calculation

wshobson

Calculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk, implementing risk limits, or building risk monitoring systems.

881

backtesting-trading-strategies

jeremylongshore

Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".

1071

model-usage

openclaw

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

548

Search skills

Search the agent skills registry