← Back to Home
Case Study · Skill Cassette Build Template

Case Study:
Automated Crypto Trading.

A case study building a trading bot with BALIA OS that uses a crypto exchange API to detect price-action patterns and automatically enter and exit positions. It's built with the rigor required of any system that handles investment decisions — preventing data leakage, validating backtests in proper time-series order, and more.

Whether you're working with a widely known technical-analysis pattern like a head-and-shoulders or inverse head-and-shoulders, or a trading method you've developed yourself through experience, you can show the agent chart images and tell it "when the chart looks like this, judge it this way" — building a system that handles chart monitoring, entry decisions, and automatic order placement end to end.

Just Two Tools

ToolRoleThink of it as
Chat Claude (claude.ai)Decides "what to build" through conversation. Handles the design/spec sideA planning session with your architect
Claude Code in VS CodeTakes the finalized design and actually creates the files and writes the codeThe contractor on site

Basic Workflow

  1. Talk with Chat Claude → get a spec for "what to build"
  2. Chat Claude turns that spec into an instruction sheet (TASK.md)
  3. Hand the TASK.md to Claude Code in VS Code → it actually builds it
  4. Report the result back to Chat Claude → get the next instruction sheet
  5. Repeat steps 1–4 until it's complete

How This Differs From Typical Auto-Trading Software

Most off-the-shelf auto-trading software builds its logic once from historical data and then keeps using it unchanged forever. The build approach in this guide differs from that in two major ways.

Typical Auto-Trading SoftwareThis Guide's Build Approach
Symbol SelectionKeeps using the logic/symbols decided at the start, unchangedRe-runs a backtest on that day's market data every day and re-selects favorable symbols
Improving AccuracyJust keeps using the logic exactly as originally builtReviews daily trade results — especially trades that hit stop-loss — and keeps teaching the agent what it learns, continuously improving accuracy over time

Symbol selection is automatically re-tested every morning, and the watchlist keeps updating. The pre-order pattern check is also designed around a continuous improvement cycle — reviewing stop-loss trades and adding newly worded patterns one at a time. It's a system built to never just be "finished" with a fixed piece of logic.

Overall Schedule (Five Phases)

PhaseContentTool UsedDeliverable
Phase 0Environment setup and data foundation (choosing an exchange, obtaining API keys, collecting historical data, designing the data storage approach)BothRequirements sheet + full environment setup
Phase 1Signal and feature design (designing technical indicators and pattern detection, preventing data leakage)Chat ClaudeSignal design document
Phase 2Building the strategy backtest engine (time-series train/valid/test split, building the cassette)BothStrategy backtest engine + SKILL.md/WORKFLOW.md/SPEC & soul.md
Phase 3Parameter tuning (tune using only the valid period; the test period is for final confirmation only)BothTuned parameters + final evaluation results
Phase 4Rollout to live trading (demo/paper trading first → then a small live position, a design that can support multiple exchanges, ongoing monitoring)BothA running trading bot + monitoring setup

You build up validation on historical data step by step before ever going live — the kind of careful process any serious financial system requires. Since the assumptions vary a lot by target symbol and exchange, there's no ready-made TASK.md that skips the interview. Always start with the Phase 0 requirements interview.

Start Now: the Phase 0 Kickoff Prompt

Just paste this prompt as-is into a new conversation with "Chat Claude" (claude.ai) to kick off the Phase 0 requirements interview.

I want to build an automated trading bot (a skill cassette) that uses a crypto exchange API. I'm new to programming, so I'd like you (Chat Claude) to be my design/spec partner, with Claude Code in VS Code handling the implementation.
🔒

The rest is available in the full guide after purchasing T1.
(Full text including the default symbol-selection logic, entry/exit logic, details on preventing data leakage, and instruction-sheet templates for Phase 1 onward)

Buy T1 to See the Guide →

Disclaimer and Important Notes

⚠️ This guide and this cassette are not intended as investment advice or a solicitation to invest.

BALIA OS is a tool that helps you build automated systems, including trading bots. It does not guarantee any specific investment outcome. Backtest results based on historical data do not guarantee future market conditions or future trading performance.

Crypto trading involves large price swings, and losses can exceed your invested principal. Always trade based on your own judgment and at your own risk.

The design philosophy and methods introduced in this guide (pattern detection, risk management thinking, etc.) are provided for informational purposes only and do not guarantee any specific hit rate, win rate, or profit. Regulations and tax treatment for crypto trading vary by country and region. Follow the laws of your own jurisdiction regarding exchange availability and tax treatment, and consult a professional as needed.

Full Build Guide

The default symbol-selection logic, entry/exit logic, thinking behind preventing data leakage, instruction-sheet templates for Phase 1 onward, and more — the full write-up is all laid out on the BALIA OS guide site.

See the Full Build Guide →

See Other Case Studies

Other case studies built the same way — reservation management systems, community/fan site auto-updates, boat race prediction, and more — are live or in progress.

See All Case Studies →