Stock Realtime Brief
A股投研体系 v5.0 - 散户级 Bloomberg. 七大新工具:(1) DCF 内在价值 - 巴菲特/段永平/林奇思想 (2) 板块轮动识别 (3) 卖出信号体系 - 5维 (4) 北极星监控 - 公告自动 (5) 实时盘中警报 (6) 财报自动解析 (7) 历史回测引擎. 含 v2.1 选股模型(5维10... Skill: Stock Realtime Brief Owner: michaelliugh Summary: A股投研体系 v5.0 - 散户级 Bloomberg. 七大新工具:(1) DCF 内在价值 - 巴菲特/段永平/林奇思想 (2) 板块轮动识别 (3) 卖出信号体系 - 5维 (4) 北极星监控 - 公告自动 (5) 实时盘中警报 (6) 财报自动解析 (7) 历史回测引擎. 含 v2.1 选股模型(5维10... Tags: 4.0:4.0.0, 4.1:4.1.0, 4.2:4.2.0, a-share:5.5.0, ai-berkshire:5.5.0, alerts:5.0.0, all-in-one:4.0.0, analysis:4.2.0, anthropic:5.5.0, backtest:5.0.0, bull-market:4.2.0, business-transformation:5.5.
Rank
62
Safety
84
Downloads
1.7k
Updated
Oct 10, 2026
Version
5.5.0
Source
CLAWHUB
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. 1.7K downloads reported by the source. Last updated 10/10/2026.
Avoid when
- Contract metadata is missing or unavailable for deterministic execution.
Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing
Public facts
Every fact links back to the source it came from.
- Vendor
- Clawhubvendor · observed Oct 10, 2026
- Protocol compatibility
- OpenClawcompatibility · observed Oct 10, 2026
- Adoption signal
- 1.7K downloadsadoption · observed Oct 10, 2026
- Latest release
- 5.5.0release · observed Jul 6, 2026
- Handshake status
- UNKNOWNsecurity
Install and run
Setup complexity: low.
clawhub skill install s17a3nrwsry4bm9jeg7vk5714h8691ef:stock-realtime-brief- Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
- Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.
Contract: missing
curl -s "https://www.xpersona.co/api/v1/agents/clawhub-michaelliugh-stock-realtime-brief/snapshot"
Documentation
CLAWHUB
160,000 characters of source documentation, loaded on request.
Extracted files
5 files captured from the source.
SKILL.md
---
name: stock-realtime-brief
version: 5.5.0
description: "A股投研体系 v5.0 - 散户级 Bloomberg. 七大新工具:(1) DCF 内在价值 - 巴菲特/段永平/林奇思想 (2) 板块轮动识别 (3) 卖出信号体系 - 5维 (4) 北极星监控 - 公告自动 (5) 实时盘中警报 (6) 财报自动解析 (7) 历史回测引擎. 含 v2.1 选股模型(5维100分) + v5.0 蓝军对垒 + 7 铁律。触发: 盘前简报 / 智能选股 / 板块排名 / DCF估值 / 北极星 / 实时警报 / 财报解析 / 历史回测 / 纪律检查。仅适用 A股。"
metadata:
category: investment
market: A-share
version: 5.5.0
upgrade_notes: "v5.5: ai-berkshire 精华融合 (4大师视角+Thesis Drift+Quality Screen) + 业务转型修正因子 / 完整 38 模块"
modes:
- portfolio # 持仓模式
- single # 单股深度
- multi # 多股对比
- pick # 智能选股 (v4.0 新增)
- watch # 盯盘 (v4.0 新增)
- rr # 风险收益比 (v4.0 新增)
- check # 纪律检查 (v4.0 新增)
requires:
bins:
- python3
python_packages:
- akshare
- pandas
---
# A 股实时分析与操作建议(Stock Realtime Brief v4.0)
> "**规则比感觉重要**——把可以提前算清楚的事,写在能照着执行的清单里。"
## 🚀 v4.0 All-in-One 命令快查
```bash
# 📊 分析类(原 v3.x 能力)
python3 scripts/run_brief.py portfolio
python3 scripts/run_brief.py single 600519
python3 scripts/run_brief.py multi 600519 000858
# 🎯 智能选股(v4.0 新增)
python3 scripts/run_brief.py pick all # 综合 TOP
python3 scripts/run_brief.py pick business # 业绩驱动
python3 scripts/run_brief.py pick money # 资金驱动
python3 scripts/run_brief.py sectors # 板块强度
python3 scripts/run_brief.py push # QQ 推送简报
# 👁 盯盘 Agent(v4.0 新增)
python3 scripts/run_brief.py watch start # 启动盯盘(systemd 后台)
python3 scripts/run_brief.py watch check # 立刻检查一次
# 📋 纪律守护(v4.0 新增)
python3 scripts/run_brief.py rr 650 670 688 720 640 615 570
# 风险收益比 = 现价 保守 中性 乐观 技术止损 硬止损 极限止损
python3 scripts/run_brief.py check 600519 # 纪律综合检查
```
## v4.0 整合的能力
| 来源 | 整合后 | 状态 |
|---|---|:---:|
| stock-smart-picker | scripts/smart_picker.py | ✅ |
| price-watcher | scripts/price_watcher.py | ✅ |
| v3.2 决策模板 | scripts/disciplines.py | ✅ |
| universe_v2.json | configs/universe.json | ✅ |
| watchlist.json | configs/watchlist.json | ✅ |
## 1. 三种使用模式
### 1.1 模式选择决策树
```
用户输入 →
├─ 提到"持仓 / 我的票 / 盘前简报"
│ → 模式 P:持仓模式(读 portfolio + 7 步法)
│
├─ 只提到 1 只股票("看下 X / 分析 X")
│ → 模式 S:单股深度模式(技术面 + 操作位)
│
├─ 提到 2 只及以上("X 和 Y 谁好 / 这几只票")
│ → 模式 M:多股对比模式(横向对比 + 排序推荐)
│
└─ 不确定时 → 优先问一句确认,不要默认
```
### 1.2 三种模式的核心差异
| 维度 | 模式 P(持仓) | 模式 S(单股) | 模式 M(多股) |
|------|:---:|:---:|:---:|
| 数据源 | portfolio + 实时 + K线 | 实时 + K线 + 个股资金流 | 实时 + K线(精简) |
| 输出篇幅 | 长(含融资体检) | 中(含基本面+技术面) | 短(对比表为主) |
| 止损规则 | 完整三档(含重仓收紧) | 标准三档 | 不强制止损 |
| 融资体检 | ✅ 必做 | ❌ | ❌ |
| 特色 | 全面、防漏 | 深、详 | 横向、快 |
### 1.3 何时使用 / 何时不用
| 场景 | 触发 |
|------|:---:|
| 持仓盘前/盘中简报 | ✅ P |
| "看下 600519 / 帮我分析 X" | ✅ S |
| "X 和 Y 哪个好 / 这几只票排序" | ✅ M |
| "今天买什么 / 推荐股票" | ❌(这不是本 skill 职责,应转给"选股 skill") |
| "X 公司基本面怎么样" | ⚠️ 单股模式可附带基本面,但不是核心 |
| 港美股 / 期货 / ETF | ❌ |
---
## 2. 通用 7 步法(三种模式共用骨架)
```
Step 1 解析用户输入 → 识别模式 P/S/M + 提取股票代码
Step 2 拉实时行情 → 优先腾讯接口(最稳)
Step 3 拉历史 K 线 → AKShare stock_zh_a_hist (qfq, 近 60 日)
Step 4 计算关键位 → MA5/10/20/30 + 近 N 日高低 +README.md
# 📊 Stock Realtime Brief > **A股投研体系 v5.0** — 选股 + 估值 + 跟踪 + 警报 + 复盘 全面闭环 / 散户级 Bloomberg > 🎉 **v5.0 重磅升级 (2026-06-28)**: 新增 **7 大投研工具** — DCF 内在价值计算 / 板块轮动 / 卖出信号 / 北极星监控 / 实时警报 / 财报解析 / 历史回测 > 📊 v2.1 选股模型 (5 维 100 分) + v5.0 蓝军对垒 + 北极星跟踪 = 散户级 Bloomberg 完整体系 > 🏆 5 个月实战 +105% 收益率验证 [](https://opensource.org/licenses/MIT) [](https://www.python.org/downloads/) []() [](https://clawhub.ai) [](https://github.com/Michaelliugh/stock-realtime-brief/actions/workflows/test.yml) [](https://codecov.io/gh/Michaelliugh/stock-realtime-brief) 中文 | [English](./README_EN.md)  --- ## ✨ 它能做什么 针对 A 股市场,**根据用户输入的不同形态自动切换三种分析模式**: | 模式 | 触发场景 | 输出 | |:---:|---------|------| | 📦 **Portfolio** | 给定持仓文件 | 完整盘前简报:实时态势 + 关键均线 + 三档硬止损 + 融资风险体检 + 重要公告告警 + 优先级操作清单 | | 🔍 **Single** | 单只股票 | 单股深度分析:态势速判 + 技术面 + 5 档操作位(介入/加仓/止损/短线止盈/波段止盈) | | 📊 **Multi** | 多只股票 | 横向对比表:综合评分排序 + 关键差异点 + ⭐/🟡/⚠️ 标签 | **自动模式**:根据输入数量自动选择 — 1 只走 Single,多只走 Multi,有 portfolio 文件走 Portfolio。 ## 📸 输出示例 <table> <tr> <td width="33%"><b>🔍 单股深度分析</b><br><img src="./docs/images/sample_single.png" alt="Single mode sample"></td> <td width="33%"><b>📊 多股对比分析</b><br><img src="./docs/images/sample_multi.png" alt="Multi mode sample"></td> <td width="33%"><b>📦 持仓简报</b><br><img src="./docs/images/sample_portfolio.png" alt="Portfolio mode sample"></td> </tr> </table> --- ## 🚀 30 秒快速开始 ### 1. 安装 ```bash git clone https://github.com/<你的用户名>/stock-realtime-brief.git cd stock-realtime-brief pip install -r requirements.txt ``` ### 2. 单股分析(最简单) ```bash python -m stock_realtime_brief --code 300750 ``` 输出示例: ``` 🔍 宁德时代 300750 实时分析 — 2026-05-06 14:30 ## 一、态势速判 **📈 多头排列,趋势向上** ## 二、技术面 - 现价: **256.78** | 涨跌幅: **+2.31%** | 换手: 1.85% | 成交额: 8.93 亿 - 均线: MA5=251.20 MA10=247.45 MA20=240.12 MA30=235.67 - 近 N 日: 高 **268.50** / 低 **210.30** - 40 日涨幅: **+18.45%** ... ``` ### 3. 多股对比 ```bash python -m stock_realtime_brief --codes 600519,300750,600036 ``` ### 4. 持仓简报 ```bash # 复制示例配置 cp examples/portfolio_demo.json my_portfolio.json # 编辑成你自己的持仓 vim my_portfolio.json # 跑简报 python -m stock_realtime_brief --portfolio my_portfolio.json ``` --- ## 🎯 核心特性 ### ⭐ 三档硬止损纪律 不是"建议关注"那种空话,而是**写进券商条件单就能直接执行**的具体价位: | 档位 | 价位逻辑 | 动作 | |:---:|---------|------| | **预警线** | MA5(一般)/ MA10(重仓)+ 利润保护位 | 减 1/3 | | **风控线** | MA10(一般)/ MA20(重仓)/ max(MA20, 成本-15%) | 再减 1/3 | | **清仓线** | MA20 / 成本-25%(亏损) | 全清 | ### ⭐ 数据源容错策略 A 股数据源时不时抽风。本工具按**实战验证的可靠性顺序**降级: ``` 腾讯财经(最稳)→ 新浪财经批量 → AKShare(带 timeout) ``` > **踩过
_meta.json
{
"ownerId": "kn776jtv3xwpaavvks8986f55x81df2a",
"slug": "stock-realtime-brief",
"version": "5.5.0",
"publishedAt": 1783353114924
}CHANGELOG.md
# Changelog
All notable changes to this project will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [Unreleased]
## [5.5.0] - 2026-07-06 (ai-berkshire 精华融合)
### 🎭 重大升级 - 4 大师视角 + 业务转型修正因子
**触发**: 用户 7/6 深度研究 `xbtlin/ai-berkshire` 官方开源 + 3 次教诲罗博业务转型分业务视角
### Added - ai-berkshire 精华 3 大工具
- 🆕 **Four Masters Vote** (`four_masters_vote.py`)
- 段永平 + 巴菲特 + 芒格 + 李录 四大师独立打分
- 强制冲突 (不取平均) / 揭示真实矛盾
- **业务转型修正因子** (关键 - 分业务视角):
- 段永平: '新业务高毛利+高增' → +0.8
- 巴菲特: '新订单 ¥10亿+' → +1.5
- 芒格: '转型期有订单' → 减 30% 惩罚
- 李录: '卡脖子设备' → +1.0
- 应用示例: 罗博特科 从 2.0 → 4.3 (通过 可重仓)
- 🆕 **Thesis Drift Detector** (`thesis_drift.py`)
- 对比两个时间点论文
- 区分: 事实变化 / 估值变化 / 措辞变化 / 状态变化
- JSON 快照机制
- 论点漂移自动告警
- 🆕 **Quality Screen 8 条红线** (`quality_screen.py`)
- 巴菲特/段永平 8 条硬指标一票否决
- R1: 连续亏损 / R2: ROE / R3: 毛利率 / R4: 营收
- R5: PE / R6: PB / R7: 市值 / R8: 净利波动
### Added - v5.5 铁律 (业务转型)
- **业务转型期公司必须分业务看** (罗博教训)
- **短期财报亏损 ≠ 长期价值差** (罗博: 光伏亏 / CPO 迅猛)
- **在手订单是硬印钞依据** (罗博: ¥11 亿在手)
- **用户反复教的必须沉淀到算法** (v5.5 学习 用户 3 次教诲)
- **LLM 不能死看财报数字 / 必须结合业务结构**
### Fixed - 罗博特科打分严重错误
- 修正 four_masters_vote 打分算法
- 加入业务转型修正因子
- 罗博 thesis 从 5 条 → 6 条 (加分业务事实)
- 罗博 净分 从 +80 → +105 (超满分)
### Real-World Validation
- 你 4 只持仓 4 大师综合:
- 药明 4.5 (真长线 winners)
- 罗博 4.3 (转型期 + 印钞订单)
- 中天 3.8 (业绩 winners)
- 华工 3.7 (业绩 winners)
- 全部 通过 / 可重仓
- 印证你 5 天教科书级 11 笔换股完全正确
---
## [5.4.0] - 2026-07-05 (Anthropic financial-services 精华融合)
### 🌟 重大升级 - 顶级 投行级 + 散户级 Bloomberg
**触发**: 用户 7/5 深度研究 Anthropic 官方开源 `anthropics/financial-services`,融合 3 大精华
### Added - Anthropic 精华 3 大工具
- 🆕 **Thesis Tracker** (`thesis_tracker.py`)
- 每只持仓 3-5 条 关键论点系统化追踪
- 4 只持仓 论点净分 全部 +80/85 极强持有
- Kill Switch 机制 (触发即全清)
- 基于 Anthropic equity-research/thesis-tracker
- 🆕 **Catalyst Calendar** (`catalyst_calendar.py`)
- 未来 60 天关键事件日历
- CRITICAL/HIGH/MEDIUM 三级分类
- T-7/T-3/T-1 提前提醒
- 涵盖: 财报/融资到期/政策/行业事件
- 基于 Anthropic equity-research/catalyst-calendar
- 🆕 **Daily Morning Note** (`daily_morning_note.py`)
- 每日 08:30 自动生成
- 6 大板块: 美股+期指+持仓+预判+挂单+事件+心法
- 完整盘前简报 一键生成
- 基于 Anthropic equity-research/morning-note
### Added - Anthropic 精华 沉淀
- 数据源优先级原则 (MCP > 机构源 > 严禁 web 传闻)
- Guardrails 护栏机制 ([UNSOURCED] 标记)
- 端到端工作流思想 (Scope → Overview → Compare → Ideas → Note)
- Thesis 定期复核制度
### Real-World Validation
- 5 周 sink 心法 + 战术:
- 5/29 v4.2 (7 铁律)
- 6/22 v5.0 (蓝军对垒)
- 6/28 13 大工具
- 7/1-7/2 教科书 11 笔 换股 (卖飞跌停 + 金字塔摊薄)
- 7/5 v5.4 Anthropic 融合
- 累计落袋: ¥264 万
- 当前浮盈: ¥70+ 万
- 全部 4 只持仓 thesis 极强
---
## [5.0.0] - 2026-06-28 (投研体系全面升级 / 7 大新工具上线)
### 🚀 重大升级 - 散户级 Bloomberg 完整体系
**触发**: 用户 6/22-6/28 系统性教 v1.0 → v2.1 选股模型 + 完整投研框架
### Added - 7 大新工具 (一周完成)
- 🆕 **DCF 内在价值计算器** (`dcf_calculator.py`)
- 三阶段 DCF 模型 (1-5/6-10/永续)
- 6 档评级 (极品 → 严重高估)
- 巴菲特 / 段永平 / 林奇 思想落地
- 区分 "好公司" ≠ "好股票"
- 🆕 **板块轮动识别** CONTRIBUTING.md
# Contributing
Thanks for your interest in contributing! 🎉
## How to contribute
### 🐛 Bug reports
Before opening an issue, please:
1. Search existing issues to avoid duplicates
2. Test on the latest version
3. Provide:
- Python version
- OS
- Exact command that triggered the bug
- Full error trace
- Expected vs actual behavior
### 💡 Feature requests
Open an issue with:
- Clear use case
- Proposed API / behavior
- Whether you can implement it yourself
### 🛠 Pull requests
1. **Fork** and create a branch from `main`
2. **Add tests** if you're changing logic
3. **Run tests**: `pytest tests/`
4. **Format**: `black src/ tests/`
5. **Lint**: `ruff check src/`
6. **Commit** with conventional format: `feat: add X`, `fix: handle Y`, etc.
7. **Open PR** with clear description
### 📊 Adding a new data source
Data sources should follow this contract:
```python
def fetch_realtime(codes: list[str]) -> dict[str, dict]:
"""Returns: {code: {price, pct_change, open, high, low, prev_close, ...}}"""
def fetch_hist_kline(code: str, days: int = 90) -> pandas.DataFrame:
"""Returns: DataFrame with columns [日期, 开盘, 收盘, 最高, 最低, 成交量]"""
```
Add to `src/stock_realtime_brief/data_sources.py` and register in the priority chain.
### 📈 Adding a new indicator
Add a function to `src/stock_realtime_brief/indicators.py`:
```python
def my_indicator(closes: list[float], **params) -> float | None:
"""Description of what this indicator measures."""
if len(closes) < required_length:
return None
return computed_value
```
Then expose via the analyzer chain.
### 🌍 Translations
Especially welcome! Open a PR adding `README_<lang>.md` and translating key user-facing strings in source.
## Code style
- Python 3.10+
- Type hints required for public APIs
- Docstrings for public functions
- Keep functions under 80 lines
- No global state (pass dependencies explicitly)
## Development setup
```bash
git clone https://github.com/Michaelliugh/stock-realtime-brief.git
cd stock-realtime-brief
pip install -e ".[dev]"
pytest
```
## Code of Conduct
Be respectful, assume good intent, and focus on what's best for users. Personal attacks, harassment, or discriminatory remarks will not be tolerated.
## Questions?
Open a discussion on GitHub Discussions or contact via Issues.AionUi
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants.
CopilotKit
The Frontend for Agents & Generative UI. React + Angular
Machine-readable data
The same record, as JSON, for agents and crawlers.
{
"facts": [
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Clawhub",
"href": "https://clawhub.ai/michaelliugh/skills/stock-realtime-brief",
"sourceUrl": "https://clawhub.ai/michaelliugh/skills/stock-realtime-brief",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-10T04:48:07.466Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-michaelliugh-stock-realtime-brief/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-michaelliugh-stock-realtime-brief/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-10-10T04:48:07.466Z",
"isPublic": true
},
{
"factKey": "traction",
"category": "adoption",
"label": "Adoption signal",
"value": "1.7K downloads",
"href": "https://clawhub.ai/michaelliugh/stock-realtime-brief",
"sourceUrl": "https://clawhub.ai/michaelliugh/stock-realtime-brief",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-10T04:48:07.466Z",
"isPublic": true
},
{
"factKey": "latest_release",
"category": "release",
"label": "Latest release",
"value": "5.5.0",
"href": "https://clawhub.ai/michaelliugh/stock-realtime-brief",
"sourceUrl": "https://clawhub.ai/michaelliugh/stock-realtime-brief",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-07-06T15:51:54.924Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-michaelliugh-stock-realtime-brief/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-michaelliugh-stock-realtime-brief/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
],
"events": [
{
"eventType": "release",
"title": "Release 5.5.0",
"description": "v5.5 ai-berkshire 精华融合: 4 大师视角 + Thesis Drift + Quality Screen + 业务转型修正因子 (罗博 2.0→4.3)",
"href": "https://clawhub.ai/michaelliugh/stock-realtime-brief",
"sourceUrl": "https://clawhub.ai/michaelliugh/stock-realtime-brief",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-07-06T15:51:54.924Z",
"isPublic": true
}
]
}Record generated Oct 10, 2026.
