菜单
Copy-pasteable scikit-learn and numpy code patterns for fitting a linear trend on recent WTI price history, projecting point forecasts to standard horizons, and calibrating 80% prediction interval widths from residual standard errors. Load references/projection-examples.md before writing any trend-projection code.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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 | trend-projection |
| description | Copy-pasteable scikit-learn and numpy code patterns for fitting a linear trend on recent WTI price history, projecting point forecasts to standard horizons, and calibrating 80% prediction interval widths from residual standard errors. Load references/projection-examples.md before writing any trend-projection code. |
Run the statistical-analysis skill first to determine the current vol
regime and appropriate trend window before applying these patterns.
Load references/projection-examples.md via
load_skill_resource("trend-projection", "references/projection-examples.md")
before writing any trend-projection code.
The reference file contains:
sklearn.linear_model.LinearRegression
to fit the most recent 30 trading days of WTI close prices.1.28 * residual_std * sqrt(h / 5),
which produces the 80% CI half-width at horizon h business days.LinearRegression on [0..29] (x) vs close price (y).30 + h - 1.residual_std = std of (y - y_hat) on the 30-day window.1.28 * residual_std * sqrt(h / 5).[0.5 * 52w_low, 1.5 * 52w_high] as a
plausibility guard — extreme trend extrapolation is usually wrong.No scripts in this skill. Do not call run_skill_script.