skill-portfolio-optimize

Turn an alpha signal into optimal portfolio weights under real constraints. Use when a user has factor scores / expected returns and wants portfolio weights, or asks about mean-variance / risk-parity / minimum-variance / maximum-diversification optimisation, sector-neutral or turnover-limited construction. Bridges factor signals and backtesting.

Jump to install

Repository: XinAloha/skills
Last source activity: August 22, 2026 at 14:54
Detected SKILL.md language: Chinese
Stars: 3
Forks: 0

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

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/XinAloha/skills --skill skill-portfolio-optimize

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

14 files

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

name	skill-portfolio-optimize
description	Turn an alpha signal into optimal portfolio weights under real constraints. Use when a user has factor scores / expected returns and wants portfolio weights, or asks about mean-variance / risk-parity / minimum-variance / maximum-diversification optimisation, sector-neutral or turnover-limited construction. Bridges factor signals and backtesting.
license	GPL-3.0
category	工具
metadata	{"organization":"QuantSkills","organization_url":"https://github.com/quantskills","repository":"skill-portfolio-optimize","repository_url":"https://github.com/quantskills/skill-portfolio-optimize","project_type":"skill","collection":"portfolio-risk-validation"}

{
  "version": 1,
  "task": {
    "placeholder": "说明或上传 alpha 信号、收益面板/协方差矩阵、现有权重、行业与暴露约束",
    "required": true
  },
  "fields": [
    {
      "key": "objective",
      "label": "优化目标",
      "type": "select",
      "default": "mean_variance",
      "options": [
        { "value": "mean_variance", "label": "均值-方差" },
        { "value": "min_variance", "label": "最小方差" },
        { "value": "max_sharpe", "label": "最大夏普" },
        { "value": "risk_parity", "label": "风险平价" },
        { "value": "max_diversification", "label": "最大分散化" }
      ]
    },
    {
      "key": "weight_cap",
      "label": "单资产权重上限",
      "type": "number",
      "placeholder": "例如 0.05",
      "help": "以小数表示，0.05 即 5%"
    },
    {
      "key": "turnover_limit",
      "label": "换手率上限",
      "type": "number",
      "placeholder": "例如 0.30",
      "help": "仅在提供上一期权重时生效"
    }
  ],
  "prompt_template": "{{#task}}任务与材料：\n{{task}}\n\n{{/task}}{{#attachments}}用户上传的材料（已放入工作区）：\n{{attachments}}\n\n{{/attachments}}把 alpha 信号转化为受约束的目标组合权重，优化目标采用 {{objective}}。{{#weight_cap}}单资产权重上限为 {{weight_cap}}。{{/weight_cap}}{{#turnover_limit}}换手率上限为 {{turnover_limit}}。{{/turnover_limit}}使用正定且稳健的协方差估计，检查行业/因子中性、暴露、换手等约束的可行性与绑定情况，输出权重、风险贡献和求解诊断，不将历史优化结果表述为投资建议，输出中文报告。"
}