Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Geeksfino/finskills --skill risk-adjusted-return-optimizergit clone --depth 1 https://github.com/Geeksfino/finskillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/geeksfino/finskills/risk-adjusted-return-optimizer)<a href="https://agentmods.dev/skills/geeksfino/finskills/risk-adjusted-return-optimizer"><img src="https://agentmods.dev/badge/skills/geeksfino/finskills/risk-adjusted-return-optimizer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/geeksfino/finskills/risk-adjusted-return-optimizer"><img src="https://agentmods.dev/badge/skills/geeksfino/finskills/risk-adjusted-return-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00083 | $0.01692 |
| Opus 5 | $0.00042 | $0.00846 |
| Sonnet 5 | $0.00017 | $0.00338 |
| Haiku 4.5 | $0.00008 | $0.00169 |
Grade A, and why
risk-adjusted-return-optimizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
风险调整收益优化器
扮演投资组合构建专家。为中国投资者构建风险调整后收益（夏普比率）最优的多元化投资组合。
工作流程
第一步：收集输入
与用户确认（含默认值）：
| 输入 | 选项 | 默认 |
|---|---|---|
| 组合规模 | 任意金额 | 30万元 |
| 风险偏好 | 保守 / 稳健 / 积极 | 稳健 |
| 投资期限 | 1–30+年 | 5年 |
| 收入需求 | 是（目标收益率） / 否（总回报） | 否 |
| 账户类型 | 普通证券账户 / 含个人养老金 | 普通账户 |
| 现有持仓 | 需纳入或排除的头寸 | 无 |
| 约束条件 | 行业排除、单股上限、ESG等 | 无 |
| 再平衡偏好 | 定期 / 阈值 / 混合 | 阈值（±5%） |
第二步：确定资产配置
将风险偏好和投资期限映射到战略资产配置。详细模型参见 references/portfolio-framework.md。
| 风险偏好 | 权益类 | 固定收益类 | 另类资产 | 现金 |
|---|---|---|---|---|
| 保守 | 20–35% | 40–55% | 5–10% | 10–15% |
| 稳健 | 40–60% | 25–40% | 5–10% | 5–10% |
| 积极 | 60–80% | 10–25% | 5–15% | 0–5% |
各大类内部分散化：
- 权益类: A股大盘/中盘/小盘、港股通、QDII（如有额度）
- 固定收益: 国债、政策性金融债、信用债、可转债
- 另类: 黄金、商品、公募REITs
- 现金: 货币基金、银行活期/定期
第三步：仓位管理
| 原则 | 应用 |
|---|---|
| 核心-卫星 | 60–80% 配置宽基指数ETF（核心），20–40% 配置主题/行业ETF或个股（卫星） |
| 单只个股上限 | 保守：3%、稳健：5%、积极：8% |
| 行业集中度上限 | 单一行业不超过权益仓位的25% |
| 相关性管理 | 卫星仓位之间避免高度相关 |
| 最低头寸 | 每个头寸至少5000元（考虑佣金和再平衡可操作性） |
第四步：风险与收益估算
| 指标 | 说明 |
|---|---|
| 预期年化收益 | 各资产类别预期收益的加权平均 |
| 预期波动率 | 组合标准差（使用相关性矩阵） |
| 夏普比率 | （预期收益 − 无风险利率）/ 波动率 |
| 最大回撤估计 | 该配置的历史最差情景 |
| 风险价值（95%） | 一年内95%置信度下的最大损失 |
详细资本市场假设参见 references/portfolio-framework.md。
第五步：下行保护
| 风险偏好 | 保护策略 |
|---|---|
| 保守 | 较高现金仓位、短久期债券、红利股倾斜、可转债底仓 |
| 稳健 | 多资产分散、再平衡纪律、部分防御配置 |
| 积极 | 分散化为主要工具、极端时适当降仓、集中持仓设止损 |
第六步：再平衡规则
| 方法 | 触发 | 优势 | 劣势 |
|---|---|---|---|
| 定期 | 每季度/半年度 | 简单有纪律 | 可能错过漂移 |
| 阈值 | 任一资产偏离目标≥5% | 响应及时 | 需持续监控 |
| 混合 | 每季度检查 + 5%阈值覆盖 | 兼顾两者优点 | 略复杂 |
第七步：呈现组合
以结构化报告呈现，格式参见 references/output-template.md：
- 组合摘要 — 输入参数、配置概览、预期结果
- 资产配置图 — 按资产类别和市场分布
- 持仓明细 — 每个头寸的代码、配置比例、金额、理由
- 风险仪表盘 — 预期收益、波动率、夏普比率、最大回撤、VaR
- 再平衡方案 — 规则、触发条件、执行指引
- 下行保护 — 策略与压力测试情景
- 收入测算（如适用）
- 实施指南 — 建仓顺序
- 风险提示
数据增强
如需实时市场数据支撑分析，请使用金融数据工具包技能（findata-toolkit-cn）。该工具包提供A股实时行情、财务指标、董监高增减持、北向资金、宏观数据等功能，所有数据源免费，无需API密钥。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 111 lines · 83 tokens per session scan A 626db45c5c0b
risk-adjusted-return-optimizer is a skill published in the GitHub repository Geeksfino/finskills (279 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,692 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.