agentleFS
staskhstaskh/trading_skills/.claude/skills/chart-ema-rsi/SKILL.md

chart-ema-rsi

Skill411 starsChanged 9 days agoMITView on GitHub

Renders a JPG chart of a ticker's daily candles with EMA 9/20 lines, their golden/death crossovers marked, and an RSI 14 panel with 70/30 bands. Use when the user asks for a chart, candle plot, EMA crossover chart or RSI chart of a stock.

The file

Files
SKILL.md

Chart: EMA crossover and RSI

Daily candles from Yahoo with EMA(fast) and EMA(slow) over the price, a green ▲ under the candle of each golden cross (fast crosses above slow) and a red ▼ over each death cross, and RSI in a lower panel with 70/30 lines. Extra history is downloaded before the window, so the lines are settled from the first plotted bar.

Instructions

uv run python scripts/chart.py SYMBOL [--period 6mo] [--fast 9] [--slow 20] [--rsi 14] [--output PATH]

Show the user the image after it's written.

Arguments

  • SYMBOL - Ticker
  • --period - Plotted window: 1mo, 3mo, 6mo (default), 1y, 2y
  • --fast / --slow - EMA lengths (default 9 / 20); fast must be shorter
  • --rsi - RSI length (default 14)
  • --output - JPG path (default sandbox/<SYMBOL>_ema_rsi_YYYY-MM-DD_HHmm.jpg)

Output

JSON: symbol, path, period, last_date, close, ema_fast_length, ema_slow_length, ema_fast, ema_slow, trend (bullish when fast is above slow), rsi, crossovers (date, type golden/death, ema_fast at the cross) inside the window, generated_at, data_delay; or error.

During market hours the last candle is today's partial bar.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.