# Market Scanner

> 市场扫描仪，提供盘前/盘中/盘后三阶段市场扫描、异动识别与情绪状态判断。

- **Type:** Skill
- **Install:** `agentstack add skill-shaoxing-xie-openclaw-data-china-stock-market-scanner`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [shaoxing-xie](https://agentstack.voostack.com/s/shaoxing-xie)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [shaoxing-xie](https://github.com/shaoxing-xie)
- **Source:** https://github.com/shaoxing-xie/openclaw-data-china-stock/tree/main/skills/market-scanner

## Install

```sh
agentstack add skill-shaoxing-xie-openclaw-data-china-stock-market-scanner
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Market Scanner

**与 `market-sentinel`：本 Skill 主责时段化扫描、异动与市场快照；若要「涨停+资金+北向+板块」四源合成的整体情绪评分与阶段框架，请使用 `skills/market-sentinel/SKILL.md`，勿在本 Skill 中重复承担该聚合职责。**

## 目标

对 A 股市场进行时段化扫描，输出可执行前的结构化观察结论与风险提示。

## 输入

- 用户问题（盘前/盘中/盘后）
- 指数、板块、资金流、涨停池与交易时段工具数据

## 输出（固定结构）

1. 市场快照（指数、涨跌家数、成交环境）
2. 板块与资金强弱
3. 异动监控（放量突破/冲高回落/炸板）
4. 情绪状态与应对剧本

### 证据表（必选）

- 列出 `tool_check_trading_status`、`tool_fetch_market_data` 等调用与 `quality_status`；快照类结论须有工具字段对应。

### 反证与局限（必选）

- 时段边界、数据新鲜度 `data_freshness` 不足时对结论降置信。

## 强制规则

- 仅通过 **manifest / `tool_runner`** 调用依赖工具，禁止引导直连 `plugins.data_collection`。
- 盘中叙事前必须先调用 `tool_check_trading_status`。
- 输出必须带 `event_window` 与 `data_freshness`。
- 缺少核心行情或广度数据时输出 `insufficient_evidence`。
- 禁止输出买卖点、仓位比例、杠杆建议。
- 情绪阈值从 `config/market-scanner_config.yaml` 读取。

## 依赖工具

- `tool_resolve_symbol`（L2；标的代码归一，涉及个股/ETF/指数混输时优先）
- `tool_check_trading_status`
- `tool_fetch_market_data`
- `tool_fetch_sector_data`
- `tool_fetch_a_share_fund_flow`
- `tool_fetch_northbound_flow`
- `tool_fetch_limit_up_stocks`

## 通用输出字段

- `market_snapshot`
- `breadth`
- `sector_strength`
- `flow_snapshot`
- `anomaly_watchlist`
- `sentiment_state`
- `playbook`
- `risks`
- `event_window`
- `data_freshness`

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [shaoxing-xie](https://github.com/shaoxing-xie)
- **Source:** [shaoxing-xie/openclaw-data-china-stock](https://github.com/shaoxing-xie/openclaw-data-china-stock)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-shaoxing-xie-openclaw-data-china-stock-market-scanner
- Seller: https://agentstack.voostack.com/s/shaoxing-xie
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.
