Skip to content

Minute-Level Market Analysis

Pulls intraday crypto/stock candles and computes VWAP, TWAP and volume profiles

Stars
37,433
Licence
MIT
Files
2 files

What it does

When this skill is installed, the agent can fetch minute-by-minute price candles (for example from the OKX crypto exchange, Tushare for China A-shares, or yfinance for US and Hong Kong stocks) and calculate intraday measures such as VWAP (volume-weighted average price), TWAP (time-weighted average price) and volume distribution. It also describes how to set up minute-interval backtests in the wider Vibe-Trading system, though the bundled script states it only supports analysis output and not the backtest engine, which only supports daily data.

Great for

  • Traders or analysts who want intraday VWAP/TWAP and volume breakdowns for crypto or stocks
  • Developers building minute-level strategy research who want ready-made data-fetching code
  • People comparing intraday liquidity or volume patterns across trading pairs

Skip it if

  • Live trading or order execution: the skill only retrieves and analyses historical data, and the backtest claim conflicts with the script's own note that the engine supports daily data only
  • Financial decisions based on unverified backtests: the SKILL.md and script disagree on backtest support and the code has not been validated
  • Users without a stable internet connection or API access, since data retrieval depends on external services with rate and row limits

Try asking

  • “Get the last 300 five-minute BTC-USDT candles from OKX and calculate VWAP and TWAP”
  • “Show the hourly volume distribution for ETH-USDT over the past week”
  • “Pull 1-minute yfinance data for a US stock and summarise its intraday volume pattern”
  • “Set up a 5-minute backtest config for OKX BTC-USDT over two weeks”
Step-by-step guide: how to use Minute-Level Market AnalysisInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    minute-analysis.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip minute-analysis.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip minute-analysis.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Keep minute-level date ranges short (about 7 days for 1m, 30 days for 5m) to avoid slow or timed-out requests
  • Check the script and SKILL.md for conflicting claims about backtest support before relying on results, and review the code before running it
  • Use a lower commission figure for minute strategies as the skill suggests, and treat any output as research rather than advice

What's inside

  • example_signal_engine.py
  • SKILL.md

Redistributed unmodified from HKUDS/Vibe-Trading under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.