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 Travisun/Opptrix --skill lean-ma-cross-trendgit clone --depth 1 https://github.com/Travisun/OpptrixWrote 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/travisun/opptrix/lean-ma-cross-trend)<a href="https://agentmods.dev/skills/travisun/opptrix/lean-ma-cross-trend"><img src="https://agentmods.dev/badge/skills/travisun/opptrix/lean-ma-cross-trend.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00097 | $0.01368 |
| Opus 5 | $0.00048 | $0.00684 |
| Sonnet 5 | $0.00019 | $0.00274 |
| Haiku 4.5 | $0.00010 | $0.00137 |
Grade A, and why
lean-ma-cross-trend 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 5d 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.
What it actually says
LEAN 均线交叉趋势
方法溯源 QuantConnect LEAN 中常见的双均线交叉 / 趋势跟踪算法思路；本技能用平台指标做规则状态解读，禁止假装跑完整 LEAN 引擎。
何时使用
用户要对 A股/场内 ETF 单标的或小集合做均线交叉（如快慢 MA/EMA）趋势规则诊断（LEAN 方法溯源，非美股原版照搬）。
边界：指标定义手册用 @skill:lean-indicator-playbook；平台综合策略信号用 @skill:instrument-signals；全宇宙批量均线筛选用 @skill:lean-ema-cross-universe。默认交付网页。
A股适配（默认）
- 默认市场 CN（A股 / 场内 ETF）。用户点名美股/港股再切换，并声明数据口径与微观结构差异。
- 默认 CN 标的；涨跌停会使均线交叉信号钝化或当日不可成交，须一句标注。
- T+1 影响「交叉当日交易」叙事；禁止做空金叉/死叉对称交易假设。
- 不可硬适配或数据缺口时：首页横幅写清完整度（partial 或更严）+ 必要时
ask_user。
分析架构（投研方法）
- 问题/假设：在约定快慢均线参数下，当前处于金叉/死叉/纠缠何种状态？趋势是否与价格结构一致？
- 证据清单：价格与均线序列（事实）、用户参数（假设）、延续/反转可能性（推断）
- 多维交叉验证：快慢线相对位置 vs 价格相对均线；短窗 vs 长窗冲突
- 结论与不确定：交叉信号滞后；震荡市假信号多
- 风险与缺口：样本过短、缺指标、参数未确认
- 微观/制度风险：涨跌停钝化、T+1、ST/停牌、融券受限（及相关会计口径差异）；不得按美股连续可成交或自由做空假设叙事
- 事实 | 假设 | 推断 分栏强制
数据维度
| 维度 | 取数方向 | 缺失时 |
|---|---|---|
| 标的 | search_instruments / ask_user |
先确认再分析 |
| 快照 | get_instrument_snapshot |
标明无现价 |
| 均线/指标 | get_instrument_indicators |
not-feasible 或仅文字规则 |
| 图表 | get_instrument_chart |
不画假图 |
| 参数 | ask_user（周期） |
用显式默认并标假设 |
| 计算 | opptrix_run |
可选 |
| 交付 | list_web_vendor → create_web |
可跳过口头要点 |
| 市场/微观结构 | CN 行情 + 均线 | 涨跌停日信号标失效风险 |
步骤
- 确认默认 CN：标的/宇宙为 A股或场内 ETF（用户点名其他市场再切换并声明差异）。应用涨跌停/T+1/融券受限等微观约束（见 A股适配）。
- 确认标的与均线参数（快/慢周期、MA 或 EMA）。
- 声明非 LEAN Runtime：仅方法溯源，不跑引擎。
- 拉取指标与图表，标注数据时效。
- 判定规则状态：金叉/死叉/纠缠；与价格位置交叉验证。
- 分栏结论后默认
create_web交付。
网页报告建议目录
- 范围：默认 A股/场内 ETF + LEAN 溯源
- 均线定义与交叉规则
- 当前状态（事实，带时效）
- 与价格结构的交叉验证
- 事实 / 假设 / 推断
- 局限、假信号与观察清单
- A股适配与限制（默认 CN；微观结构/代理/完整度）
- 免责声明（信号≠买卖建议）
禁止
- 荐股；把金叉写成「买入指令」
- 禁止假装跑完整 LEAN 引擎或伪造历史交叉胜率
- 禁止无交付就结束（默认 web）
- 编造未返回的均线数值
- 禁止把美股成分/ETF 清单不经映射直接当 A股结果
- 禁止假设可自由融券做空
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.
- 5d ago First seen · 86 lines · 97 tokens per session scan A 957b393e393c
lean-ma-cross-trend is a skill published in the GitHub repository Travisun/Opptrix (231 stars, last pushed yesterday), licensed Apache-2.0. It adds 97 tokens to every session and 1,368 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
national-team-position
A Chinese-language analysis tool that estimates changes in China’s government-backed ETF holdings by tracking ETF share counts and related index prices. ETFs are funds traded on stock exchanges, and the “national team” refers here to Central Huijin, a state investment company.
caijing-ipo-hk
A Chinese-language adviser for Hong Kong stock initial public offerings, or IPOs—the first sale of a company's shares to the public. It covers how to apply, how much to apply for, and risks such as the share price falling below the offering price.
caijing-fundamental
A finance research skill for writing a detailed, forward-looking analysis of a listed company’s business, financials, valuation, risks, and investment arguments. It covers companies listed in mainland China and Hong Kong.
rodya-caijing-studio
A toolkit for researching Chinese A-share and Hong Kong-listed companies and producing financial content. It includes separate workflows for company fundamentals, earnings, valuation, risks, industries, and IPO checks.
caijing-earnings
A finance research skill for reviewing listed companies’ earnings reports, or preparing for an upcoming report. It focuses on Chinese A- and Hong Kong-listed companies.
caijing-valuation
A Chinese-language adviser that assesses whether a stock's current valuation looks high or low. It adapts the comparison to the industry and examines historical and peer-company valuation ranges.