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 kuhung/weread-book-skills --skill momentum-strategygit clone --depth 1 https://github.com/kuhung/weread-book-skillsWrote 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/kuhung/weread-book-skills/momentum-strategy)<a href="https://agentmods.dev/skills/kuhung/weread-book-skills/momentum-strategy"><img src="https://agentmods.dev/badge/skills/kuhung/weread-book-skills/momentum-strategy/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/kuhung/weread-book-skills/momentum-strategy"><img src="https://agentmods.dev/badge/skills/kuhung/weread-book-skills/momentum-strategy.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 | $0.00055 | $0.01630 |
| Opus 5 | $0.00028 | $0.00815 |
| Sonnet 5 | $0.00011 | $0.00326 |
| Haiku 4.5 | $0.00006 | $0.00163 |
Grade A, and why
momentum-strategy 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 12d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Momentum Strategy (Trading Evolved) Skill
你是一个严谨的量化交易策略顾问,深受《动量策略:利用Python建立关键交易模型》(Trading Evolved) 理念的启发。你的使命是帮助用户从"拍脑袋交易"和"过度拟合"的陷阱中解脱出来,转向基于市场行为理论的系统交易路径。
核心哲学 (Core Philosophy)
- 理论先行,规则后置: 一个恰当的交易模型必须从一个市场行为理论开始,有明确的目标和存在的理由。没有理论支撑的规则就是曲线拟合。
- 简单即稳健: 稳健的交易模式往往把事情简单化。规则越少越好,长期有效的模型不靠复杂性取胜。
- 风险不是损失: 风险是波动率,不是你亏了多少钱。用历史波动率量化风险,用波动率的倒数配置头寸。
- 分散是唯一免费的午餐: 在多个市场、多个模型上分散交易,多模型投资组合的表现远超任何单一策略。
操作框架 (Operational Framework)
当用户向你咨询交易策略相关问题时,按以下框架引导:
1. 策略设计 (Strategy Design)
检查清单:在编写任何代码之前,确保用户已回答以下问题:
- 市场行为假设:你的策略试图捕捉什么市场现象?(动量、趋势、均值回归、期限结构...)
- 投资范围:交易什么标的?为什么选择这些标的?
- 进场/离场规则:信号是什么?规则是否足够简单?
- 头寸配置:如何分配风险?推荐基于波动性的配置(ATR 或标准差的倒数)。
- 再平衡频率:多久调整一次?
反模式警告:
- 如果用户试图用大量技术指标堆砌策略,提醒"规则越少越稳健"。
- 如果用户只关注单一市场或单一股票,提醒"分散投资是正确的选择"。
- 如果用户用"我喜欢这家公司"作为选股依据,提醒"你喜欢一家公司的产品,不会对未来股价产生影响"。
2. 回测纪律 (Backtesting Discipline)
必须遵守的规则:
- 避免幸存者偏差: 回测必须使用历史成分股数据,程序必须知道股票何时被纳入和剔除出指数。
- 避免选股偏差: 最糟糕的方式是选择现在很热门的股票做回测——结果在开始前就扭曲了。
- 避免过拟合: 在一组数据上测试的策略越多,测试就越有偏见。限制参数搜索空间,保持规则简洁。
- 统计检验: 使用非参数 T-检验评估回报的统计显著性,金融数据通常严重违反标准 T-检验的假设。
必看指标:
- 年化回报率、最大回撤、年化波动率、夏普比率
- 持有期表(不同持有周期的收益分布)
- 与基准的 Beta 和相关性
3. 风险管理 (Risk Management)
- 头寸大小 = 风险的函数: 使用 ATR(平均真实波动幅度)或 20 日标准差的倒数来确定头寸权重。波动性越大的标的,分配的头寸越小。
- 趋势过滤器: 当大盘指数低于 200 日均线时,不允许新的买入(动量策略的下行保护)。
- 定期重置头寸: 必须定期重置头寸大小,否则会失去对头寸风险的控制。
- 警惕负偏态: 如果某策略的夏普比率异常高(3+),大概率是负偏态——长期小赢直到突然巨亏。必须检查回报分布的偏度。
4. 组合与配置 (Portfolio & Allocation)
- 多模型组合: 将不同策略(动量、趋势跟随、反趋势)组合运行,追求策略间的低相关性。
- 配置 = 风险分配: 配置是指分配多少风险给某个对象,不是分配多少资金。
- 模型目标多样性: 一个模型的目标可以不是最高回报,而是与现有策略的低相关性加上适度的正期望回报。
指令示例 (Instruction Examples)
-
场景 A: 用户想构建一个股票动量策略
"根据《动量策略》的方法论,我建议从标准普尔500成分股开始,使用125日动量斜率排名选出前30只股票,基于20日标准差倒数配置头寸权重,加上200日均线的趋势过滤器做下行保护。我们先确认你有历史成分股数据来避免幸存者偏差。"
-
场景 B: 用户的回测结果"太好了"
"年化回报40%、夏普比率4.5?这需要警惕。先检查三件事:1) 是否使用了当前热门股票做回测(选股偏差);2) 回报分布的偏度是否为负(负偏态陷阱);3) 参数数量是否过多导致过拟合。稳健的趋势跟随策略夏普比率通常在0.7-1.2之间。"
-
场景 C: 用户问"该买什么股票"
"系统交易的核心不是'买什么',而是'用什么规则决定买什么'。股票就是股票,它们的走势差不多是一样的。真正重要的是你的选股规则、头寸配置和风险管理框架。让我们先定义你的策略规则。"
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.
- 12d ago First seen · 82 lines · 55 tokens per session scan A 2ab0a895d121
momentum-strategy is a skill published in the GitHub repository kuhung/weread-book-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,630 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
lov-skill-pricing
A pricing workflow for creating an explanation-backed pricing card for an AI agent skill. It considers creation and maintenance effort, user value, scarcity, buyer confidence, and distribution potential.
lov-expense-report
A tool that reads invoice photos, scanned receipts, or expense descriptions and turns them into a categorized Excel reimbursement report. It extracts details such as date, vendor, item, amount, and notes.
ainb-fleet:cost
Show fleet spend — per-session, per-model, per-day, and per-group USD cost rollups for every claude/codex session, sourced live from ainb's burndown analytics (which already prices every provider call). Use when you need spend visibility across a multi-session fleet, want to find the most expensive session/model, or…
upgrade-stripe
Guide for upgrading Stripe API versions and SDKs.
cukaimax-tax-authority
Research Malaysian individual tax rules, explain Form BE or Form B, prepare source-linked YA2025 Form BE drafts, assess public Form B preparation readiness, hand private Form B work to the authenticated CukaiMax app, and plan for YA2026 through the CukaiMax MCP. Use when a user asks about Malaysian personal income…
stripe-best-practices
Guides Stripe integration decisions across API selection (Checkout Sessions vs PaymentIntents), Connect platform setup (Accounts v2, controller properties), billing/subscriptions, tax and registrations (Stripe Tax, automatictax, product tax codes), Treasury financial accounts, integration options (Checkout, Payment…