メニュー
Code patterns for classifying the current volatility regime and detecting anomalous recent moves. Always load alongside fetch-yfinance — the examples require a yfinance data fetch at the top of the same script. Load references/examples.md for working code.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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 | vol-regime |
| description | Code patterns for classifying the current volatility regime and detecting anomalous recent moves. Always load alongside fetch-yfinance — the examples require a yfinance data fetch at the top of the same script. Load references/examples.md for working code. |
references/examples.md — Working code patterns for:
These patterns are designed to be combined with a data-fetch block in a single
code execution. Do not call run_code separately for data fetching and regime
classification — combine them.
Load fetch-yfinance and vol-regime, read both references/examples.md files, then write
one complete block that fetches the data and computes the regime.
| Regime | Annualised vol (%) |
|---|---|
| low | < 20 |
| normal | 20 – 35 |
| elevated | 35 – 55 |
| extreme | > 55 |
Adjust thresholds for other assets. These are calibrated to WTI's historical vol distribution (2020–2025 median ≈ 31%).
Pattern 3 returns a trend_window integer (15 or 30 days) that you should
pass directly to the trend-projection skill's fitting step.
