openclaw-skills/portfolio-risk-manager/SKILL.md
Use when reviewing portfolio exposures, checking concentration and beta risk, summarizing sector or region tilts, or preparing a risk note before reallocating capital.
npx skillsauth add seaworld008/commonly-used-high-value-skills portfolio-risk-managerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
像专业的风险会议(Risk Meeting)一样汇总投资组合:分析集中度(Concentration)、敞口(Exposure)、贝塔(Beta)、波动率(Volatility),识别组合在哪些领域过度倾斜。本技能旨在将杂乱的持仓清单转化为具有前瞻性的风险视图,辅助投资经理在调仓前进行全方位的“健康体检”。
# 确保已安装投资组合分析与统计库
pip install pandas numpy pyportfolioopt scipy
# 准备持仓数据
npx clawhub install portfolio-risk-manager
scripts/portfolio_risk.py。{
"portfolio_name": "Growth_Strategy_2026",
"base_currency": "USD",
"holdings": [
{ "ticker": "NVDA", "weight": 0.12, "beta": 1.65, "sector": "Semiconductors" },
{ "ticker": "MSFT", "weight": 0.10, "beta": 1.15, "sector": "Software" },
{ "ticker": "JPM", "weight": 0.08, "beta": 0.95, "sector": "Finance" }
],
"benchmark": "S&P 500"
}
### 🛡️ 投资组合风险周报:[Growth_Strategy]
**1. 核心风险指标 (Core Metrics)**:
- **总贝塔 (Total Beta)**: 1.25 (中等激进,偏向进攻型)
- **集中度 (Concentration)**: 前 5 大持仓占比 45% (**偏高**)
- **波动率 (Volatility Proxy)**: 18.5% (高于基准的 14.2%)
**2. 敞口倾斜 (Sector Tilts)**:
- **超配 (Overweight)**: 科技 (+12%), 半导体 (+8%)
- **低配 (Underweight)**: 医疗 (-5%), 能源 (-10%)
**3. 关键预警 (Risk Alerts)**:
- [NVDA] 权重已达 12%,触发 10% 警戒线。建议减持至 8%。
- [MSFT] 与 [NVDA] 相关系数上升至 0.85,组合在 AI 硬件与软件上的风险高度耦合。
**4. 压力测试 (Scenario Results)**:
- **利率上升 50bp**: 组合预期净值下降 -4.2%。
- **科技股回调 10%**: 组合预期净值下降 -12.5%。
**5. 最终决策方案**:
> [Action] 卖出 4% NVDA,买入标普 500 低波动 ETF 以降低 Beta 到 1.1。
# 运行描述性风险分析
python scripts/portfolio_risk.py --input assets/my_holdings.json --benchmark spy
# 构建优化器输入数据(协方差矩阵等)
python scripts/build_optimizer_inputs.py --returns assets/historical_returns.json
portfolio-risk-manager 计算“最小换手”下的调仓方案。options-strategy-evaluator。MEMORY.md。development
Enumerating failure modes via pre-mortem analysis. Systematically identifies failure scenarios for plans, designs, and features, scoring them with RPN/AP. Does not write code.
testing
Orchestrating specialist AI agent teams as a meta-coordinator. Decomposes requests into minimum viable chains, spawns each as an independent session in AUTORUN modes, and drives to final output. Use when a task spans multiple specialist domains, requires parallel agent execution, or needs hub-and-spoke routing across the skill ecosystem.
development
Converting document formats (Markdown/Word/Excel/PDF/HTML). Converts specs from Scribe and reports from Harvest into distributable formats; generates reusable conversion scripts. Use when converting documents, building accessibility-compliant PDFs, or creating Pandoc/LibreOffice pipelines.
testing
Curating cross-agent knowledge and guarding institutional memory. Extracts patterns from agent journals into METAPATTERNS.md, detects knowledge decay, propagates best practices, prevents organizational forgetting. Use when consolidating cross-agent insights, curating memory, or auditing knowledge decay.