What makes 股海罗盘 - A股股票量化分析 notable?

2.9K downloads. Trust evidence available

How should 股海罗盘 - A股股票量化分析 be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

股海罗盘 - A股股票量化分析

🧠 自学习量化引擎，每只股票60W+历史信号回测，输出历史匹配率+规律挖掘(5类规律图谱)+17维全量数据+自动生成DOCX报告。独家ETF四象联动资金分析、券商研报观点交叉验证。不只是查数据——给你的信号附上"过去准不准"的答案。 Skill: 股海罗盘 - A股股票量化分析 Owner: sunbinpy Summary: 🧠 自学习量化引擎，每只股票60W+历史信号回测，输出历史匹配率+规律挖掘(5类规律图谱)+17维全量数据+自动生成DOCX报告。独家ETF四象联动资金分析、券商研报观点交叉验证。不只是查数据——给你的信号附上"过去准不准"的答案。 Tags: a-share:2.2.49, data-analysis:2.2.49, finance:2.2.49, latest:2.2.51, quant:2.2.48, stocks:2.2.49 Version history: v2.2.51 | 2026-08-12T07:13:59.107Z | user 安全审查修复：移除数据库直连工具(research_utils/db_config)+SKILL.md权限声明+评分文案中性化+激活前置条件防误触发 v2.2.50 | 2026-08

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.9k

Updated

Oct 9, 2026

Version

2.2.51

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.9K downloads reported by the source. Last updated 10/9/2026.

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 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2.9K downloadsadoption · observed Oct 9, 2026
Latest release: 2.2.51release · observed Aug 12, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: medium.

clawhub skill install s175w104v89dwhjzz79964dgtd88hde7:gh-data

Python environment detected. Create a strict virtual environment (`python -m venv .venv`) before installing dependencies to prevent system-level package conflicts.
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-sunbinpy-gh-data/snapshot"

Documentation

CLAWHUB

156,759 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: ghdata-stock
description: 🧠 自学习量化引擎，每只股票60W+历史信号回测，输出历史匹配率+规律挖掘(5类规律图谱)+17维全量数据+自动生成DOCX报告。独家ETF四象联动资金分析、券商研报观点交叉验证。不只是查数据——给你的信号附上"过去准不准"的答案。
metadata:
  {
    "openclaw": {
      "emoji": "📊",
      "name": "股海罗盘 - A股股票量化分析"
    }
  }
homepage: https://www.oraskl.com/ghdata-admin
---

# 股海罗盘（gh-data）— A 股股票量化分析技能

---

## 🚀 核心能力

| | 特点 | 说明 |
|:-:|:-----|:-----|
| 🧠 | **自学习量化引擎** | 每只股票60W+历史信号回测，输出历史匹配率，不只是数据，告诉**"过去准不准"** |
| 📊 | **17维全量数据** | 实时行情·K线·MACD/KDJ/RSI·资金流向·机构持仓·融资融券·高管变动·研报·财务三表·分红·解禁 |
| 📈 | **自动规律挖掘** | 5类规律图谱：支撑/阻力位（触碰次数）、大涨后回调概率、大跌后反弹特征、MACD趋势判定 |
| 💎 | **ETF四象联动** | 独家板块级资金流向×个股走势联动分析，判断是"板块共振"还是"独立行情" |
| 🔗 | **研报交叉验证** | 券商覆盖统计、EPS一致性分歧度、今日评级动态，判断市场共识方向 |
| 📝 | **一键DOCX报告** | 自动生成15章完整结构化分析报告，含K线图嵌入，可直接保存和分享 |

## ⚡ 快速开始

**支持的请求类型：**

| 请求示例 | 说明 |
|:---------|:-----|
| `分析 601899` | 返回17维全量数据+量化分析+信号+历史匹配率 |
| `600600 青岛啤酒 简要分析` | 返回核心要点，不生成DOCX |
| `600000 资金面怎么样` | 仅分析资金流向+ETF四象联动+机构持仓 |
| `生成报告 002455` | 生成完整DOCX报告 |
| `券商怎么看 601899` | 研报观点验证+评级统计 |
| `688981 盘前做T` | ETF盘后信号+T+1盘后因子 |

### ⚠️ 激活前置条件（防误触发）

本技能**仅在用户明确涉及股票/ETF 分析意图时激活**，普通聊天话题（"看看"、"怎么样"、"随便看看"等无股票语义的日常对话）**不得触发**。

判断标准（满足其一才算明确意图）：
1. 消息中包含 **6 位 A 股代码**（如 601899、600028）或 ETF 代码（如 510300）；
2. 消息中包含 **明确股票/ETF 名称**（如"中国石化"、"沪深300ETF"）；
3. 消息中包含**明确分析动词**（分析、看盘、筛选股票、估值、走势、研报、资金面、盘前做T、生成报告等）+ 股票语义。

不满足上述条件时：**不调用任何 WebAPI**，按普通对话回复，避免消耗付费额度。

## ⚙️ 配置

```json
{
  "skills": {
    "entries": {
      "ghdata_analyze": {
        "config": {
          "api_key": "",
          "webapi_url": "",
          "webapi_timeout": 30,
          "doc_dir": "./doc"
        }
      }
    }
  }
}
```

| 配置项 | 默认值 | 说明 |
|:-------|:-------|:-----|
| `api_key` | `""` | **付费API密钥，必填。** 用户购买后在此填入。**仅从 `~/.ghdata/ghdataapikey` 文件读取**，❌ 不支持 settings.json |
| `webapi_url` | `""` | WebAPI 地址（付费用户获取，购买后提供） |
| `webapi_timeout` | `30` | HTTP 请求超时（秒） |
| `doc_dir` | `./doc` | 报告输出目录 |

> **配置生效规则**（优先级从高到低）：  
> 1. 上述 `config` 配置（仅URL/超时，不含APIKey）  
> 2. 本地文件 `~/.ghdata/ghdataapikey`（**APIKey唯一来源**）  
> 3. 自动生成GUID兜底（免费体验用）
>
> ⚠️ 环境变量 `GHDATA_API_URL` / `GHDATA_TIMEOUT` 和 `settings.json` **仅用于配置URL和超时**，不读APIKey。
>
> **⚠️ APIKey 铁律：** APIKey **只允许**从 `~/.ghdata/ghdataapikey` 这一个文件读取和写入。不读settings.json，不读环境变量。删除该文件 → 自动生成随机GUID → 服务端验证失败 → 降级为免费预览模式。

## 🔐 权限声明（透明度）

本技能运行需要以下权限，安装/授权前请知悉：

| 权限 | 用途 | 范围 |
|:-----|:-----|:-----|
| 🌐 **网络访问** | 调用 WebAPI（行情/分析/研报/资金流）、腾讯/新浪行情源、平台 token 接口 | 仅 HTTPS 请求，不建立本地监听 |
| 📂 **本地文件读写** | `~/.ghdata/ghdataapikey`（APIKey 唯一存储）、`~/.ghdata/db.ini`（可选数据库配置，未配置则不用）、报告输出目录 | 仅 `~/.ghdata/` 与配置指定目录，**不扫描其他路径** |
| 🔑 **环境变量读取** | `GHDATA_API_URL` / `GHDATA_TIMEOUT`（URL/超时配置，不读 APIKey） | 只读，不写入 |
| 💳 **支付链接生成** | token 获取失败时返回购买页链接（**不含 APIKey**，防日志泄露） | 链接仅为平台购买页，不含敏感凭证 |

**不做什么：** 不主动连接任何数据库（`db_config`/`research_utils` 等直连工具**不属于技能功能**，已从发布包移除）；不收集或外传本地文件内容；不在 URL 中携带完整 APIKey。

---

---

## ⚡ LLM 必读：启动时自动执行

本技能的配置（APIKey、WebAPI地址等）在内部自动完成初始化，**无需调用方做任何操作**。直接发分析请求即可。

### 🚨 风险提示强制展示

**在每次向用户输出分析结果前（包括首次交互、每次生成报告、每次展示分

_meta.json

{
  "ownerId": "kn77yfgxmym32jzt81n23h8vb988gsxn",
  "slug": "gh-data",
  "version": "2.2.51",
  "publishedAt": 1786518839107
}

skill-card.md

## Description:

股海罗盘 is a Chinese-language A-share and ETF analysis skill that gathers market, technical, financial, fund-flow, and research-report data, compares signals against historical patterns, and can generate DOCX reports.

This skill is ready for commercial/non-commercial use.

## Publisher:

[sunbinpy](https://clawhub.ai/user/sunbinpy)

### License/Terms of Use:

MIT-0

## Use Case:

External users and agents use this skill to gather China A-share and ETF market data, compare current signals with historical patterns, and generate concise Markdown-style summaries or DOCX reports. The outputs are informational research aids and are not investment advice.

### Deployment Geography for Use:

Global; data coverage is focused on China A-share and ETF markets.

## Known Risks and Mitigations:

Risk: The skill creates a persistent local API key and the security evidence reports risky key storage and transmission.

Mitigation: Use only a low-value or trial key until the publisher documents key storage and rotation and uses HTTPS for credential-bearing calls; remove or rotate the local key after testing.

Risk: Preview outputs may include paid upgrade links.

Mitigation: Review generated analysis and DOCX reports before sharing them, and treat upgrade links as payment content rather than analysis evidence.

Risk: Stock-analysis output can be mistaken for investment advice.

Mitigation: Preserve the skill's risk disclaimer and review outputs so they remain framed as historical data and statistical reference, not buy, sell, or hold guidance.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/sunbinpy/skills/gh-data)
- [Publisher profile](https://clawhub.ai/user/sunbinpy)
- [股海罗盘 product homepage](https://www.oraskl.com/ghdata-admin)

## Skill Output:

**Output Type(s):** [text, markdown, files, configuration, guidance]

**Output Format:** [Markdown-style analysis text with optional DOCX report files and generated chart files]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May include local report paths, risk disclaimer text, and preview-mode upgrade links.]

## Skill Version(s):

2.2.51 (source: server release evidence and artifact metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

settings.json

{
  "webapi_url": "http://api.topeasychina.com:15099/api",
  "webapi_timeout": 30,
  "doc_dir": "./doc"
}

requirements.txt

requests>=2.28.0
python-docx>=1.0.0
matplotlib>=3.6.0
mplfinance>=0.12.10

Github ReposUpdated 4h agoRank 70

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!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

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

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.