内容科学|Content Science

Sun Yuchen's stock selection model

Professionalv1.0.0
By 内容科学|Content ScienceUpdated 2026-05-11stockselectionmodel@clawhub_harveyzzzz/stockselectionmodel
Finance#新闻#股票#飞书

According to AlphaMoat, as of 2026-09, Sun Yuchen's stock selection model has 2,050 downloads and 0 stars — ranked #4,393 of 5,078 AI skills overall, and #380 of 465 in Professional.

Installs
503
Downloads
2.0K
Stars
-
Overall Rank
#4,393
Top 87% overall · Top 82% in Professional
PlatformInstallsDownloadsStarsComments
ClawHub ↗22877--
SkillHub ↗5032.0K-—

Platforms count differently and update at different times.

What this skill does

The skill runs a three-step agent workflow. The first step executes node scripts/generate_brief.js to generate the report in real time, and the script does 5 things automatically: pull live sector quotes, fetch sector news, fetch U.S. correlated tickers and recent big events, extract the driving logic plus bullish and bearish factors, and produce a complete markdown report. The second step sends that markdown straight to the user, splitting it into two messages when it exceeds the single-message limit of a platform (for example about 4000 characters on Feishu), and asks that news summaries be condensed by hand into one sentence. The third step is optional extra analysis, combining references/sector_prompt.md for an LLM judgement that covers sector overview, leading stocks, catalysts, trend judgement, and action suggestions within 600 characters. The report layout is fixed: trend judgement, core metrics, sector moves, driving logic, up/down distribution, top gainers, top losers, view and forecast, U.S. correlations, bullish and bearish factors, recent big events, points to watch, and risk notice all appear every time. The supported new-energy and technology directions include new energy, photovoltaics, lithium batteries, energy storage, wind power, and charging piles, as well as AI, computing power, large models, semiconductors, optical modules, robotics, and autonomous driving; it also covers pharmaceuticals, innovative drugs, traditional Chinese medicine, medical aesthetics, weight-loss drugs, and vaccines, plus chemicals, chemical products, coal chemicals, phosphorus chemicals, and chemical fibre, as well as baijiu, consumer, brokerage, banking, insurance, defence, real estate, digital economy, and Huawei. The environment variable TAVILY_API_KEY is an optional Tavily search API key used only to enhance the news mode. The output format is compatible with Feishu, Coze, and other markdown platforms. The source states that the tool only provides information for reference and does not constitute investment advice; the stock market carries risk, so invest with caution. Market data, filters and generated analysis can be incomplete or delayed; treat outputs as research aids, not investment advice.

Profile published 2026-10-27

What you can do with it

  • Ask for the trend judgement, constituent stocks, and up/down distribution of an A-share sector.
  • Follow up on bullish and bearish factors, catalysts, and correlated U.S. leaders for a sector.
  • Check for unusual moves in AI-related stocks, or produce an AI morning brief and AI news digest.

When to use it

  • A user asks about quotes and news flow for sectors such as new energy, semiconductors, pharmaceuticals, chemicals, or brokerage.
  • You need a sector brief that includes driving logic, a risk notice, and U.S. correlations.
  • You need the report text in a format that renders on Feishu, Coze, or another markdown platform.

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

What is the outlook for the new-energy sector?
What bearish factors have affected pharmaceuticals recently?
Check whether AI-related stocks show unusual moves.

Monthly Trend

Downloads2.0K
7451.4K2.1K2026-03 · Downloads 8422026-05 · Downloads 1.1K2026-06 · Downloads 1.2K2026-07 · Downloads 1.4K2026-08 · Downloads 1.5K2026-09 · Downloads 2.0K26-0326-09
Stars-
0112026-03 · Stars -2026-05 · Stars -2026-06 · Stars -2026-07 · Stars -2026-08 · Stars -2026-09 · Stars -26-0326-09

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

MonthDownloadsMoMStars
2026-092.0K—-
2026-081.5K+8.6%-
2026-071.4K+15.0%-
2026-061.2K+9.9%-
2026-051.1K—-
2026-03842—-

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

4.5 KB · ClawHub v1.0.0
---
name: ai-stock-insider
version: 3.0.0
description: A股板块实时研报。全球新闻→A股映射、板块趋势研判、美股关联、利好利空、大事件提醒。零配置可用,输出兼容飞书/扣子/Markdown平台。
metadata:
  openclaw:
    optionalEnv: [TAVILY_API_KEY]
---

# AI 股票内参 / 板块实时研报
Show all (156 lines)

实时拉取板块行情 + 新闻 + 美股关联 + 大事件,生成专业板块研报。

## 你可以这样问

### 板块研报(核心功能)
- "新能源板块怎么看?"
- "化工今天有什么催化?"
- "医药最近有哪些利空?"
- "AI 方向对应哪些美股龙头?"
- "券商板块这周有没有大事件?"

### AI 内参
- "今天的 AI 新闻"
- "AI 晨报"

### 异动提醒
- "看一下 AI 概念股有没有异动"

## Agent 工作流

当用户问板块/个股问题时,按以下顺序执行:

### 第 1 步:实时生成研报
```bash
node scripts/generate_brief.js --mode sector --sector <板块名> --output pretty
```

脚本会自动:
1. 拉取板块实时行情(东方财富免费API)
2. 抓取板块相关新闻(东方财富搜索)
3. 抓取美股关联标的 + 近期大事件
4. 自动提取驱动逻辑、利好利空
5. 生成完整 markdown 研报

### 第 2 步:发送给用户
拿到 markdown 后直接发送。如果内容超过平台单条消息限制(如飞书约4000字符),拆成上下两条发送。

**注意:新闻摘要需要人工精炼为一句话概括,不要直接用脚本原始输出的长文本。**

### 第 3 步:补充分析(可选)
如果用户需要更深入的分析,再结合 `references/sector_prompt.md` 做 LLM 研判。

## 研报固定布局(每次输出必须包含以下全部元素)

```
📊 {板块名} · 板块研报
{时间}

▎趋势判断
{趋势图标} {趋势文字}  ·  成分股 X 只  ·  涨停 X  跌停 X
{趋势说明}

▎核心指标(表格)
趋势 / 成分股 / 涨停 / 跌停 / 涨跌比

▎板块动态(表格)
资讯摘要(一句话概括) | 时间 | 来源 | 链接

▎驱动逻辑
• 从新闻自动提取

▎涨跌分布
🟥🟩 可视化条 + 数字

▎领涨个股(表格)
股票 | 代码 | 涨跌幅 | 状态

▎领跌个股(表格)
股票 | 代码 | 涨跌幅 | 状态

▎观点与预测
🔮 一句话预测

▎美股关联(表格)
美股标的 | 代码 | 关联说明

▎利好 / 利空
📈 利好因素(✅ 列表)
📉 利空因素(❌ 列表)

▎近期大事件(表格)
事件概括 | 时间 | 来源 | 链接

▎关注要点
1. 2. 3. 编号列表

▎风险提示
⚠️ 列表

— 免责声明 —
```

**重要:每次输出必须包含以上全部板块,不可省略任何元素。**

## 支持的板块

新能源 / 光伏 / 锂电池 / 储能 / 风电 / 充电桩
AI / 算力 / 大模型 / 半导体 / 光模块 / 机器人 / 自动驾驶
医药 / 创新药 / 中药 / 医美 / 减肥药 / 生物疫苗
化工 / 化学制品 / 煤化工 / 磷化工 / 化纤
白酒 / 消费 / 券商 / 银行 / 保险 / 军工 / 房地产 / 数字经济 / 华为

## 文件结构

```text
ai-stock-insider/
├── SKILL.md
├── scripts/
│   ├── generate_brief.js      # 一键总控入口
│   ├── fetch_news.js          # 全球 AI 新闻抓取
│   ├── fetch_sector_news.js   # 板块新闻抓取(东方财富搜索)
│   ├── fetch_us_related.js    # 美股关联 + 大事件抓取
│   ├── map_stocks.js          # 全球新闻 → A 股映射
│   ├── market_monitor.js      # AI 概念股异动监控
│   └── sector_analyze.js      # A 股板块趋势分析
└── references/
    ├── analysis_prompt.md     # AI 内参 prompt
    ├── sector_prompt.md       # 板块研判 prompt
    ├── stock_mapping.md       # A 股概念映射表
    └── source_list.md         # 数据源说明
```

## 平台兼容

- 飞书:markdown 表格 + 链接均可渲染
- 扣子(Coze):标准 markdown 兼容
- 其他 markdown 平台:标准语法,无特殊依赖

## 环境变量(可选)

| 变量 | 说明 | 必需 |
|------|------|------|
| `TAVILY_API_KEY` | Tavily 搜索 API Key(增强新闻模式) | 否 |

## 省 token 设计

1. 行情数据、新闻、美股关联全部由脚本拉取,不消耗 LLM token
2. 驱动逻辑、利好利空由脚本正则提取
3. LLM 只在用户需要深度分析时介入
4. 异动提醒不走 LLM

## 免责声明

本工具仅提供信息参考,不构成投资建议。股市有风险,投资需谨慎。

Popular in Professional

Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.