Modular Market Brief

Data guidance

Prefer programmatic price tape when available:

• Use yfinance for tickers/ETFs/crypto/commodity futures (optional dependency).
• If a market needs a dedicated movers list, use a web source (exchange site / finance portal) and then enrich tickers via yfinance.

Installing yfinance (recommended, but not required)

If yfinance isn’t available, the skill can still produce a narrative brief from public sources.

For reliable installs on modern Linux distros (PEP 668), prefer a venv:

python3 -m venv ~/.venvs/market-brief
~/.venvs/market-brief/bin/pip install -U pip
~/.venvs/market-brief/bin/pip install yfinance pandas numpy

Then run scripts using ~/.venvs/market-brief/bin/python.

Trend labeling (simple + explainable)

Use MA/RSI-based state labels:

• BUY: close > MA20 > MA50 and RSI(14) >= 50
• SELL: close < MA20 < MA50 and RSI(14) <= 50
• WAIT: everything else

Always present it as a pattern (not a guarantee) and include a one-line rationale.

Bundled scripts (optional helpers)

• scripts/price_tape.py: pull prices + returns + MA/RSI for a ticker list (yfinance)
• scripts/movers_yahoo.py: free Yahoo Finance screeners for top gainers/losers/actives (best-effort)
• scripts/tmx_movers.py: example movers scraper (TMX Money) you can adapt or swap
• scripts/render_example.md: a template you can reuse

Only run scripts if you actually need structured output; otherwise write the report directly.

Safety / finance guardrails

• Don’t place trades.
• Avoid certainty language. Use “pattern / bias / invalidation.”
• If the user asks for explicit buy/sell instructions, provide a conceptual plan + risks.
• Remind about tax/fees only when relevant.