Menu
ESG优化，整合环境、社会和治理评分，支持排除法与优化整合法构建ESG组合。适用于ESG投资策略的。ESG评分为示意值，未对接真实评级数据源，不构成投资建议。
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
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.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/openJiuwen-ai/agent-store --skill esg-portfolioThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Showing SKILL.md
Based on SOC occupation classification
| name | esg-portfolio |
| description | ESG优化，整合环境、社会和治理评分，支持排除法与优化整合法构建ESG组合。适用于ESG投资策略的。ESG评分为示意值，未对接真实评级数据源，不构成投资建议。 |
| version | 1.0.0 |
| author | wangyi |
ESG 投资组合工具，整合环境、社会和治理（ESG）评分，支持排除法、优化整合法构建ESG投资组合，仅使用 Python 标准库。
📌 说明：本工具基于简化模型实现，仅使用 Python 标准库。结果仅供学习参考，不构成投资建议。
compute_esg_scores(e_scores, s_scores, g_scores, weights=(1 / 3, 1 / 3, 1 / 3))计算综合ESG评分。 必填: e_scores, s_scores, g_scores
portfolio_esg_score(weights, esg_scores)计算投资组合的加权ESG评分。 必填: weights, esg_scores
negative_screening(benchmark_weights, esg_scores, threshold=5.0, asset_names=None)负面排除法：排除ESG评分低于阈值的资产。 必填: benchmark_weights, esg_scores
positive_screening(benchmark_weights, esg_scores, top_percent=0.7, asset_names=None)正面筛选法：仅保留ESG评分最高的前N%资产。 必填: benchmark_weights, esg_scores
sector_exclusion(benchmark_weights, esg_scores, sector_mapping, excluded_sectors, asset_names=None)行业排除法：排除特定行业的资产。 必填: benchmark_weights, esg_scores, sector_mapping, excluded_sectors
esg_tilt(benchmark_weights, esg_scores, tilt_factor=1.0, max_deviation=0.1)ESG倾斜法：在基准基础上向高ESG资产倾斜。 必填: benchmark_weights, esg_scores
esg_optimization(benchmark_weights, esg_scores, mean_returns, cov_matrix, esg_target=None, risk_aversion=1.0, esg_preference=0.5, max_deviation=0.15, n_iter=10000, seed=42)ESG优化整合法。 必填: benchmark_weights, esg_scores, mean_returns, cov_matrix
objective(weights)目标函数。 必填: weights
python scripts/main.py \
--weights <weights> \
--esg-scores <esg_scores> \