Menu
One-shot code patterns for downloading price and market data from yfinance inside the E2B sandbox. Load this skill whenever a task requires market or futures data from Yahoo Finance. Load examples.md for working code.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
How to use the search_web tool well when grounding a forecast in recent news — phrase cutoff-aware queries, decide what is worth searching for, and weigh sources. Load this before your first search_web call. No scripts.
How to use the search_web tool well when grounding a forecast in recent news — phrase cutoff-aware queries, decide what is worth searching for, and weigh sources. Load this before your first search_web call. No scripts.
How to use the search_web tool well when grounding a forecast in recent news — phrase cutoff-aware queries, decide what is worth searching for, and weigh sources. Load this before your first search_web call. No scripts.
How to use the search_web tool well when grounding a forecast in recent news — phrase cutoff-aware queries, decide what is worth searching for, and weigh sources. Load this before your first search_web call. No scripts.
Reference guide for the repo concierge catalog — domain filters, the search-then-fetch workflow, and bootcamp routing. Load references/catalog-guide.md before your first answer. No scripts.
How to use the code execution sandbox well — parse the JSON payload (not disk files), compute a couple of useful diagnostics before forecasting, and keep the session stateful within a turn. Load this before writing code. No scripts.
| name | fetch-yfinance |
| description | One-shot code patterns for downloading price and market data from yfinance inside the E2B sandbox. Load this skill whenever a task requires market or futures data from Yahoo Finance. Load examples.md for working code. |
Each run_code call is a completely fresh Python process. There is no state,
no variables, and no files from any previous call. Every code block must be
fully self-contained: all imports, all data fetching, and all analysis in one
block.
yfinance is pre-installed in the sandbox. No pip install needed.
examples.md — Working code patterns for:
CL=F)as_of)load_skill_resource("fetch-yfinance", "references/examples.md") to load the patterns.| Series | Ticker |
|---|---|
| WTI crude oil | CL=F |
| Brent crude | BZ=F |
| S&P 500 | ^GSPC |
| Natural gas | NG=F |
| USD/CAD | CAD=X |
ticker.history() returns a timezone-aware DatetimeIndex on recent yfinance
versions. Strip the timezone with .dt.tz_localize(None) after reset_index.CL=F, NG=F), use auto_adjust=False and take the Close
column directly — adjusted close is not meaningful for rolled futures.