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.

跳到安装

仓库: XinAloha/skills
最近来源活动: 2026年8月22日 14:54
检测到的 SKILL.md 语言: 中文
星标: 3
分支: 0

安装方式

默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。

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。

直接命令不会经过审查 Prompt；运行前请先检查来源。

npx skills add https://github.com/XinAloha/skills --skill skill-portfolio-optimize

命令会保持在同一行。复制前请横向滚动并检查完整内容。

想先保存到本地？可下载 SkillsMP 当前能够提供的文件。

检查来源文件

决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。

文件资源管理器

14 个文件

SKILL.md

来源说明 · 只读预览

返回搜索返回安装

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。"
}