What makes Initiation of Coverage Agent notable?

9.8K downloads. Trust evidence available

How should Initiation of Coverage Agent 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

Initiation of Coverage Agent

依托东方财富数据库，面向沪深京港美上市公司（A 股、港股、美股、北交所），生成首次覆盖报告或深度研究报告。当用户提及「首次覆盖」「首次覆盖报告」「初始覆盖」「深度研究」「深度报告」「个股深度」「公司深度」「标的深度分析」，或要求对某只股票/上市公司撰写全面、体系化的研究报告时，必须触发本 Skill。即使用户... Skill: Initiation of Coverage Agent Owner: financial-ai-analyst Summary: 依托东方财富数据库，面向沪深京港美上市公司（A 股、港股、美股、北交所），生成首次覆盖报告或深度研究报告。当用户提及「首次覆盖」「首次覆盖报告」「初始覆盖」「深度研究」「深度报告」「个股深度」「公司深度」「标的深度分析」，或要求对某只股票/上市公司撰写全面、体系化的研究报告时，必须触发本 Skill。即使用户... Tags: coverage:1.0.3, financial:1.0.3, latest:1.0.4, report:1.0.3, research:1.0.3, stock:1.0.3 Version history: v1.0.4 | 2026-04-17T11:18:37.457Z | user Publish 1.0.4 v1.0.3 | 2026-04-10

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

9.8k

Updated

Oct 9, 2026

Version

1.0.4

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 9.8K 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: 9.8K downloadsadoption · observed Oct 9, 2026
Latest release: 1.0.4release · observed Apr 17, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s172qfps754dhtdynwv0gwshes83mtd4:initiation-of-coverage-or-deep-dive

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
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-financial-ai-analyst-initiation-of-coverage-or-deep-div/snapshot"

Documentation

CLAWHUB

23,129 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: initiation-of-coverage-or-deep-dive
description: >
  依托东方财富数据库，面向沪深京港美上市公司（A 股、港股、美股、北交所），生成首次覆盖报告或深度研究报告。
  当用户提及「首次覆盖」「首次覆盖报告」「初始覆盖」「深度研究」「深度报告」「个股深度」「公司深度」「标的深度分析」，或要求对某只股票/上市公司撰写全面、体系化的研究报告时，必须触发本 Skill。
  即使用户仅表述为「帮我写一份 XX 公司的研究报告」而未出现「深度」「首次覆盖」等词，也应触发。
  不适用于业绩点评、财报点评、事件点评等场景。
metadata:
  {
    "openclaw": {
      "requires": {
        "env":["EM_API_KEY"]
      },
      "install": [
        {
          "id": "pip-deps",
          "kind": "python",
          "package": "httpx",
          "label": "Install Python dependencies"
        }
      ]
    }
  }
---

# 上市公司首次覆盖报告 / 深度研究报告生成

## 概述

本技能用于生成上市公司的**首次覆盖报告**或**深度研究报告**。通过调用统一脚本 `scripts/generate_deep_research_report.py`，
一次性完成实体识别、市场校验、报告生成及结果返回。

## 环境变量

| 变量名 | 说明 | 默认 |
|--------|------|------|
| `EM_API_KEY` | 接口鉴权密钥（必填） | 无 |
| `INITIATION_OF_COVERAGE_OR_DEEP_DIVE_OUTPUT_DIR` | 附件输出目录| `./miaoxiang/initiation_of_coverage_or_deep_dive`（相对当前工作目录） |


## 前提条件

### 1. 配置 `EM_API_KEY`

```bash
# macOS / Linux
export EM_API_KEY="your_api_key_here"
```

```powershell
# Windows PowerShell
$env:EM_API_KEY="your_api_key_here"
```

### 2. 安装依赖

```bash
pip3 install httpx --user
```


## 完整工作流程

### 第一步：调用报告生成脚本

调用 `scripts/generate_deep_research_report.py` 脚本，将用户的**原始问句**作为参数传入。该脚本内部自动完成以下全部流程：

1. **实体识别与市场校验**：调用实体识别接口，从用户问句中识别沪深京港美实体，返回标准化信息（`secuCode`、`marketChar`、`classCode`、`secuName`）；多个实体时优先取第一个；未识别到支持的实体则直接返回错误提示。
2. **报告生成**：将校验通过的实体信息作为参数，调用首次覆盖写作接口生成完整报告。

**调用方式**：

```bash
python3 {baseDir}/scripts/generate_deep_research_report.py --query "用户原始问句"
```

**脚本输出（JSON 格式）**：

- **成功时**：返回报告全文及附件地址等完整结果，包含报告标题、各章节内容、附件地址、分享链接等。
- **实体识别为空时**：返回错误信息 `"目前仅支持沪深京港美实体进行首次覆盖。您提供的实体不在支持范围内，请确认后重新输入。"`
- **入参不合法时**：返回 `"入参不支持，请重新检查实体类型和报告期。"`
- **接口调用失败/超时时**：返回 `"报告生成服务暂时不可用，请稍后重试。"`

**处理逻辑**：

- 脚本返回成功 → 进入第二步，进行结构化输出
- 脚本返回错误提示 → 将错误提示原样返回给用户，流程终止

注意：**禁止调用 任何「后台执行、稍后汇报」的方式跑本脚本**，只能在当前会话中同步等待到命令完成，拿到 stdout 的结果后再继续，否则会导致本 Skill 失败。

### 第二步：结构化输出

脚本返回报告全文后，按照以下固定结构进行响应输出。

---

## 输出格式规范

接口返回后，必须严格按以下模板输出，不得增删标题、不得改变顺序、不得添加额外章节：

### 标题
直接使用接口返回的 `title` 字段，单独成行，一般格式为"XXX公司首次覆盖报告：XXXXXX"。

### 正文
如果接口返回的 `content` 字段有相关行业报告信息，则原文透传；
否则读取接口返回的附件文件内容，总结相关报告信息返回，记住保证返回的正文内容非空。

### 附件
接口返回 pdf 以及 docx 格式文件的保存路径。

### 分享链接
直接使用接口返回的 `shareUrl` 字段，单独成行。

文案必须按以下固定格式输出：

```
{title}

{content}

---

**附件：**

- 📄 **PDF版完整报告地址**：{pdf_file_path}
- 📝 **Word版完整报告地址**：{word_file_path}

**分享链接：**
{shareUrl}
```

字段映射规则：
- `{title}` = 脚本返回的 `title`
- `{content}` = 脚本返回的 `content`
- `{pdf_file_path}` = 脚本返回的 `pdf_file_path`
- `{word_file_path}` = 脚本返回的 `word_file_path`
- `{shareUrl}` = 脚本返回的 `shareUrl`

当附件缺失时：
- 若仅有一种格式，仅输出存在的那一行（PDF 或 DOCX）。
- 若两种都不存在，输出：`完整报告：暂无可用附件`

## 格式要求

响应事件流中的数学公式格式规范：
- **行内公式**：使用 `\(...\)` 格式（不使用 `$...$`）
- **行间公式**：统一使用 `\[...\]` 格式
- 行间公式块内部内容保持不变

---

## 语言与标点规范

- 如果用户使用中文提问，全程使用中文回复，并使用规范中文标点（，。、；：""''！？）
- 如果用户使用英文或其他语言提问，使用对应语言回复
- 专有名词（如公司英文名、财务术语缩写）可保留原文

---

## 边界与异常处理

| 场景 | 处理方式 |
|------|---------|
| 用户未提供公司名/代码 | 礼貌询问："请提供您想覆盖的上市公司名称或股票代码

_meta.json

{
  "ownerId": "kn7b4ptpdag877t9kmq8axyja182taab",
  "slug": "initiation-of-coverage-or-deep-dive",
  "version": "1.0.4",
  "publishedAt": 1776424717457
}

skill-card.md

## Description:

Generates initiation-of-coverage or deep-dive equity research reports for supported A-share, Hong Kong, U.S., and Beijing Stock Exchange listed companies using Eastmoney data.

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

## Publisher:

[financial-ai-analyst](https://clawhub.ai/user/financial-ai-analyst)

### License/Terms of Use:

MIT-0

## Use Case:

External users and financial analysts use this skill to request comprehensive first-coverage or deep-dive research reports for supported listed companies. The skill returns a structured report response with generated content, attachment paths, and a share link when available.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill sends the user's original prompt to Eastmoney's report-generation API.

Mitigation: Avoid prompts that contain confidential, personal, or restricted information, and disclose the external data transfer to users before operation.

Risk: The skill depends on EM_API_KEY for external service access.

Mitigation: Provide the key only through a controlled environment variable, restrict access to trusted runtimes, and rotate the key if exposure is suspected.

Risk: The skill saves generated PDF and Word report files locally.

Mitigation: Use a scoped output directory, review generated files before sharing, and remove files when they are no longer needed.

Risk: The security guidance flags unsafe redirects, unpinned dependencies, and under-scoped permissions as review concerns.

Mitigation: Prefer a reviewed release that disables unnecessary redirects, pins dependencies, and explicitly scopes network, environment-variable, and file-write permissions.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/financial-ai-analyst/skills/initiation-of-coverage-or-deep-dive)
- [Eastmoney initial coverage API endpoint](https://ai-saas.eastmoney.com/proxy/app-robo-advisor-api/assistant/write/initial-coverage)

## Skill Output:

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

**Output Format:** [Markdown response with report text, local PDF/DOCX attachment paths, and a share URL; the helper script emits JSON.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Requires EM_API_KEY and may save generated report attachments under a local output directory.]

## Skill Version(s):

1.0.4 (source: server release evidence)

## 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.

Github ReposUpdated 6h 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.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular