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 Lzh-xbccz/hermes-finance --skill us-equity-market-analysisgit clone --depth 1 https://github.com/Lzh-xbccz/hermes-financeWrote 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/lzh-xbccz/hermes-finance/us-equity-market-analysis)<a href="https://agentmods.dev/skills/lzh-xbccz/hermes-finance/us-equity-market-analysis"><img src="https://agentmods.dev/badge/skills/lzh-xbccz/hermes-finance/us-equity-market-analysis/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/lzh-xbccz/hermes-finance/us-equity-market-analysis"><img src="https://agentmods.dev/badge/skills/lzh-xbccz/hermes-finance/us-equity-market-analysis.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 | $0.00056 | $0.02937 |
| Opus 5 | $0.00028 | $0.01469 |
| Sonnet 5 | $0.00011 | $0.00587 |
| Haiku 4.5 | $0.00006 | $0.00294 |
Grade A, and why
us-equity-market-analysis 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
美股八维分析全流程
⛔ 铁律：你不是在写行情播报，你是在做证据审计。每个方向判断必须回答"为什么"，并先做反向审计。允许使用"证据不足"、"方向未确认"、"观望"；禁止在证据冲突时硬给做多/做空。
核心理念：美股由机构主导，单一事件（财报/利率决议/宏观数据）可瞬间扭转方向。技术面只占30%权重；公司事件、行业轮动、利率环境、VIX才是主驱动。
⛔ 禁止调用 mcp_yfinance 系列工具：Yahoo Finance 频繁 429。所有数据通过
scripts/目录下的 fetch 脚本获取（内置延迟+重试）。模型不要额外调mcp_yfinance_get_historical_stock_prices等 MCP 工具。
一、铁律
- 先判断是否有方向优势：个股/ETF→🟢做多/🔴做空/⚪观望；现金指数→偏多/偏空/震荡。方向由你基于各维度证据的逻辑强度和可靠性综合判断得出，不要用投票计数或权重打分决定方向；证据不足或冲突时默认观望/震荡。
- 财报3日黑名单：个股3个交易日内有财报→默认⚪观望（除非用户明确接受风险）。
- 止盈止损锚定结构：前高/前低、颈线、趋势线、斐波那契、EMA、缺口。禁止固定百分比。SL缓冲0.3-0.5%。
- 必须带失效条件：至少2个客观可观察的手动平仓条件。
- 数据缺口降级：技术结构/行业ETF联动/公司事件三项缺1项→⚪观望。
- 先复盘再判断：必须先看30D日线轨迹，判断主导手法。
- 市场时段感知：盘前/盘后流动性薄，不得用极端价做SL锚点。周末宏观块仅作背景。
- 隔夜缺口风险：个股必须标注缺口风险（高/中/低）。
- 未收盘K线不算确认。
二、八维框架
| # | 维度 | 核心关注 |
|---|---|---|
| 1 | 📈 技术结构 | K线结构、支撑阻力、量价、缺口（日线→4H→1H） |
| 2 | 🏗️ 市场/行业结构 | 行业ETF资金流、SPY/QQQ/IWM广度、板块轮动 |
| 3 | 🐋 公司事件/主导力量 | 财报/指引/回购、机构配置、监管/业务事件 |
| 4 | 😱 情绪与期权代理 | VIX水平与趋势、Put/Call代理、涨跌比率 |
| 5 | 🌍 宏观利率 | Fed政策、^TNX/^FVX收益率、DXY、经济数据 |
| 6 | 🔍 同业/ETF交叉验证 | 同板块≥2只个股 + 行业ETF + 大盘ETF方向一致性 |
| 7 | 🧯 流动性与缺口风险 | 财报窗口、盘前盘后、隔夜缺口、成交质量 |
| 8 | 🧭 缠论结构 | CZSC 中枢、笔、背驰、买卖点候补；只做确认/冲突/不足 |
强制输出规则：
- 先给
各维度证据，只基于第 1-7 维逐项列出每个维度的偏多/偏空/中性/缺失状态及理由。不要用投票计数或权重打分决定方向。 - 必须做
反向审计：若公司事件、行业 ETF、大盘、VIX 或利率与技术方向冲突，最终方向降级为观望/震荡。 - 再给
缠论确认，说明 CZSC 是确认、冲突还是不足。 - 最终方向由你基于各维度证据的逻辑强度综合判断后决定；个股财报/监管事件优先级高于缠论；CZSC 不能覆盖事件风险。
- 使用
python3 -m hermes_finance analyze us-equity <TICKER>或 MCPanalyze_us_equity，默认会尽量用采集器 K 线跑 CZSC。
三、决策流程
第零步：确认市场状态
- 盘中/盘前/盘后/休市？个股是否在财报黑名单？
第一步：复盘主导手法
90D日线→大环境 | 30D日线/4H→主导手法 | 24H 1H→今天是延续/回踩/陷阱
第二步：趋势结构
- higher highs + higher lows → 只做多
- lower highs + lower lows → 只做空
- 模糊 → 观望
第三步：主导力量判断
权重优先级：
- 个股：财报>行业龙头联动>利率/大盘>技术
- ETF：上游资产>资金流>行业轮动>技术
- 指数：宏观利率>广度>主导板块>技术
| 场景 | 操作 |
|---|---|
| 财报超预期+指引上调+机构增持 | 回调做多 |
| 行业ETF放量突破+板块领涨 | 顺势做多 |
| 财报miss+指引下调 | 反弹做空 |
| 财报在即+期权OI极端 | ⚪观望 |
| FOMC 48h内 | ⚪观望或大幅降仓 |
What ships with it
4 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.
- 12d ago First seen · 219 lines · 56 tokens per session scan A f3872fb72673
us-equity-market-analysis is a skill published in the GitHub repository Lzh-xbccz/hermes-finance (24 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 2,937 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 2026-08-30.
Other skills, from other repositories
tickdb-market-data
A real-time market-data API for foreign exchange, metals, indexes, stocks, and cryptocurrencies. An API is a service that software can call to request data.
ask-a-legend
Get one legendary trader's read on a symbol — Wyckoff, Gann, Elliott Wave, Dow Theory, Livermore, DeMark, Wilder (RSI/ADX), Ichimoku (Hosoda), Weinstein stage analysis, or O'Neil CAN SLIM. Pass the legend and symbol, e.g. "gann on eurusd" or "what would Wyckoff say about AAPL?". Analysis and a second opinion, not a…
convene
Convene the Trading Legends Council — ten legendary traders (Dow, Wyckoff, Livermore, Elliott, Gann, DeMark, Wilder, Ichimoku, Weinstein, O'Neil) each vote blind on a symbol, then a deterministic Chairman aggregates their ballots into one verdict (LONG/SHORT/NOTRADE). Analysis and a second opinion, not signals.
forge-legend
Author a new trading legend/persona from a famous trader's name or a plain-English strategy description, then lint and live-audition it before it joins your roster. E.g. "make a trader who buys liquidity sweeps" or "add an ICT legend".
trade-memory
Compliance-grade decision audit trail for AI trading agents. Records every trading decision with full context (conditions, filters, indicators, risk state), SHA-256 tamper detection, and structured export for MiFID II / EU AI Act readiness. Works alongside Binance Spot, Futures, and Web3 skills — they execute trades…
risk-management
Risk management domain knowledge for trading agents — affective state monitoring, position sizing, drawdown management, tilt detection, and behavioral guardrails. Use when checking risk before trades, managing drawdowns, detecting behavioral drift, or enforcing discipline. Triggers on "risk", "drawdown", "tilt"…