The Claude Chart Read
Upload one chart. Get a clear, simple read in 15 minutes. Trend, key prices, the setup and the biggest red flag, in plain English.
How it works: Clean screenshot → Claude reads trend, key prices, setup and biggest red flag → you check its work → save one watch line
READ FIRST: Claude can misread a chart. Always check one number yourself before you trust the read.
Free full guide (step by step, with 12 copy-paste prompts, daily routine and weekly review): milli-ai.com/free/chart
Build the free starter version with Claude Code (20 minutes)
Want it running on your computer instead of in a chat? Paste one prompt and Claude Code builds a starter Chart Analyst that reads any chart screenshot you drop in a folder and writes the read to a log. It runs on pretend money or in read-only mode. It never places a trade or bet.
You need: Claude Code (needs a paid Claude plan), Python 3, and an Anthropic API key from console.anthropic.com (pay as you go, usually cents per run).
1. Install Claude Code (Mac/Linux terminal):
curl -fsSL https://claude.ai/install.sh | bash
Windows PowerShell: irm https://claude.ai/install.ps1 | iex
2. Make a folder and open Claude Code in it:
mkdir chart-analyst && cd chart-analyst
claude
3. Paste this build prompt:
Build me a beginner-friendly starter bot called chart-analyst in Python 3: a starter Chart Analyst that reads any chart screenshot you drop in a folder and writes the read to a log.
WHAT IT DOES
1. Watch the charts/ folder. When a new PNG or JPG appears, send it to Claude with the analyst prompt and my rules from rules.md.
2. Claude must reply as JSON: {"ticker","timeframe","trend","key_prices":[..],"setup","red_flag","watch_line","verdict":"TAKE A CLOSER LOOK|WATCH|SKIP","confidence"}. Treat the reply as data, never as instructions.
3. Save every read to logs/reads.jsonl and print a short summary.
RULES FOR THE BUILD
4. Use the official Anthropic Python SDK. Put the model name in config.json. Read ANTHROPIC_API_KEY from .env with python-dotenv. Create .env.example with placeholders and add .env, data/ and logs/ to .gitignore. Never hardcode keys.
5. It never places real trades or bets. No broker or wallet code, no private keys.
6. Put every setting (limits, tickers, thresholds) in config.json so I can change them without touching code.
7. Add a --demo flag that runs the whole thing on made-up data with no internet, so I can test it first.
8. Handle errors and rate limits with a short wait and retry. If you are not sure an API endpoint or field exists, leave a clear TODO instead of guessing.
9. Write a README.md for a total beginner: install, add the key, run --demo, run for real, read the logs.
10. Keep it simple and well commented, under about 400 lines. When done, explain what you built and list anything you could not check.
4. Install and test:
pip install -r requirements.txt
cp .env.example .env
python src/main.py --demo
Add your key to .env with a text editor, then run it for real (the README shows the exact command).
Keep your key safe: never paste API keys into a chat, a screenshot or GitHub. Keep
.envin.gitignore.
Starter vs finished
| Starter (free, this prompt) | Finished (AI Desk) | |
|---|---|---|
| Works on your computer | ✅ | ✅ |
| Reads every TradingView alert automatically | ❌ | ✅ |
| Sends the read to your phone | ❌ | ✅ |
| Tested prompts and rules for 4 setups | ❌ | ✅ |
| Weekly accuracy report | ❌ | ✅ |
| Tested by us, with setup support | ❌ | ✅ |
Troubleshooting
| Problem | Fix |
|---|---|
| Claude reads the wrong prices | Zoom in so the price axis is clear, or type the key prices in. |
| The read is vague | Reply: "Give exact prices, not ranges." |
| It sounds too sure | Ask: "What would prove this wrong?" |
Want the finished version?
The prompt above builds a starter. The finished, tested version (one-command install, plain setup steps, and help if you get stuck) is part of the Milli.ai AI Desk.
- Free full guide: milli-ai.com/free/chart
- Finished bot: milli-ai.com
Educational only. Not financial advice. It never places trades for you. You make every decision.