topic-research-report

v1.0.1

面向专题研究报告生成的能力。适用于用户提出“某主题/事件/政策的深度研究报告”类请求时,自动生成结构化研究内容。覆盖主题投资、政策影响、事件冲击、趋势判断等跨行业议题。触发核心条件:用户目标是“专题研究/深度解读/报告输出”,而非单行业常规研究或单标的诊断。

0· 337·2 current·2 all-time
byFinancial AI Analyst@financial-ai-analyst

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for financial-ai-analyst/topic-research-report.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "topic-research-report" (financial-ai-analyst/topic-research-report) from ClawHub.
Skill page: https://clawhub.ai/financial-ai-analyst/topic-research-report
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required env vars: EM_API_KEY
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install topic-research-report

ClawHub CLI

Package manager switcher

npx clawhub@latest install topic-research-report
Security Scan
Capability signals
Requires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The skill advertises generation of topical research reports and its code posts the user's query to an Eastmoney thematic research API (ai-saas.eastmoney.com). The only required credential (EM_API_KEY) matches the documented provider. No unrelated services, binaries, or credentials are requested.
Instruction Scope
SKILL.md instructs setting EM_API_KEY, running the provided script or calling the function, and writing/decoding returned base64 attachments to disk. The instructions do not ask the agent to read unrelated files or secrets, nor to transmit data to endpoints other than the documented Eastmoney API and the share URL returned by that API. Note: the skill will write attachment files under a local workspace directory.
Install Mechanism
No install spec is provided (instruction-only with an included Python script). The script uses only Python standard-library modules and does not download or execute external installers or archives.
Credentials
Only one environment variable is required: EM_API_KEY, which is appropriate and expected for authenticating to the Eastmoney API. This is sensitive information and the skill documentation correctly warns against exposing it in logs or code.
Persistence & Privilege
The skill is not marked 'always:true' and does not modify other skills or global configuration. It can be invoked autonomously by the agent (platform default) and will use the provided EM_API_KEY to make network calls to Eastmoney and write files locally; users should be aware that autonomous invocation plus a valid API key allows the skill to call the external API without further prompts.
Assessment
This skill appears to do what it says: it sends queries to Eastmoney's thematic research API and saves returned report text and base64 attachments to a local folder. Before installing or enabling it: (1) confirm the EM_API_KEY you supply is from the official Eastmoney service (https://ai.eastmoney.com/mxClaw) and understand its scope, expiry, and revocation options; (2) avoid pasting long-lived or high-privilege credentials—use a least-privilege key and rotate it if possible; (3) expect the skill to perform network calls to ai-saas.eastmoney.com and to write files under a workspace directory (miaoxiang/topic_research_report by default); (4) if you are concerned about autonomous invocation, restrict when the agent can call skills or only provide the API key in sessions where you trust the agent to run research tasks. If any of these behaviors are unacceptable, do not provide EM_API_KEY or run the script in a sandboxed environment.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

EnvEM_API_KEY
latestvk979tsahxz59pcp4m6yr4w14pd85emtp
337downloads
0stars
2versions
Updated 3d ago
v1.0.1
MIT-0

专题研究报告

通过自然语言 query生成专题研究报告,返回 Markdown 正文及分享信息,适用场景包括:

  • 事件驱动研究(政策、国际事件、宏观变化)
  • 主题投资研究(赛道、技术趋势、概念演化)
  • 跨行业影响分析(单一行业难覆盖的问题)
  • 快速输出可分享的专题深度内容

密钥来源与安全说明

  • 本技能仅使用一个环境变量:EM_API_KEY
  • EM_API_KEY 由东方财富妙想服务(https://ai.eastmoney.com/mxClaw)签发,用于接口鉴权。
  • 在提供密钥前,请先确认密钥来源、可用范围、有效期及是否支持重置/撤销。
  • 禁止在代码、提示词、日志或输出文件中硬编码/明文暴露密钥。

功能范围

基础生成能力

  • 输入专题 query,调用专题研究接口生成完整报告
  • 返回报告标题、正文、文章ID、分享链接及附件路径等结构化字段
  • 若返回 wordBase64/pdfBase64,自动解码保存为本地 .docx/.pdf 附件

触发规则(何时使用本技能)

  • 用户明确要求“专题研究/深度分析/研究报告”
  • 研究对象为主题、事件、政策、趋势、跨行业议题
  • 典型问法:东方财富专题研究美联储加息对A股影响AI Agent产业链专题

不触发规则(何时不要使用本技能)

  • 用户只问单行业基础研究(应走行业研究技能)
  • 用户只问单只股票/基金买卖判断(应走诊断技能)
  • 用户要求指标级计算、回测、量化建模(应走量化类能力)

触发示例

触发(专题研究)不触发(其他能力)
东方财富专题研究半导体行业最新景气度(行业研究)
美联储加息对A股影响海康威视值得买吗(个股诊断)
一带一路主题投资机会永赢先锋半导体风险大吗(基金诊断)
ChatGPT对教育行业冲击丹化科技MACD是否金叉(指标计算)

前提条件

1. 注册东方财富妙想账号

访问 https://ai.eastmoney.com/mxClaw 注册账号并获取 API Key。

2. 配置 Token

# macOS 添加到 ~/.zshrc,Linux 添加到 ~/.bashrc
export EM_API_KEY="your_api_key_here"

然后根据系统执行对应的命令:

macOS:

source ~/.zshrc

Linux:

source ~/.bashrc

快速开始

1. 命令行调用

python3 {baseDir}/scripts/get_data.py --query "东方财富专题研究"

输出示例

Title: 东方财富日报专题研究报告
ShareUrl: http://aife-test.eastmoney.com:9001/researchShare?shareId=xxx&scene=research
DOCX: /path/to/workspace/topic_research_report/5f14e352-cd8e-4169-9d69-7399f1eb8328_docx.docx
PDF: /path/to/workspace/topic_research_report/5f14e352-cd8e-4169-9d69-7399f1eb8328_pdf.pdf
(随后输出 Markdown 正文内容)

参数说明:

参数说明必填
--query用户原始专题研究问句✅(--query 或 stdin 二选一)
--no-save保留参数(兼容旧调用,当前对本技能无影响)

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。

2. 代码调用

import asyncio
from pathlib import Path
from scripts.get_data import generate_topic_research_report

async def main():
    result = await generate_topic_research_report(
        query="东方财富专题研究",
        output_dir=Path("workspace/topic_research_report"),
        save_to_file=True,
    )
    if "error" in result:
        print(result["error"])
    else:
        print(result["title"])
        print(result["share_url"])
        print(result["content"])
        if result.get("output_path"):
            print("已保存至:", result["output_path"])

asyncio.run(main())

输出文件说明

文件说明
<articleId>_docx.docxwordBase64 解码得到的 Word 附件(若返回)
<articleId>_pdf.pdfpdfBase64 解码得到的 PDF 附件(若返回)

返回字段说明

  • title:报告标题(来源于 data.title)。
  • article_id:报告 ID(来源于 data.articleId)。
  • share_url:报告分享链接(来源于 data.shareUrl)。
  • content:报告正文(优先 data.content)。
  • attachments:附件列表(解析 wordBase64/pdfBase64 后的本地路径)。
  • raw:原始接口返回,便于调试或二次处理。
  • error:接口调用失败时返回错误信息。

输出格式规范

接口返回后,必须严格按以下模板输出:

输出格式

## {title}

**正文:**

已经生成专题研究报告。此处仅展示部分正文内容,请下载附件查看报告详情和参考信息。

{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:**
{share_url}

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 attachments中的pdf_file_path
  • {word_file_path} = 脚本返回的 attachments中的word_file_path
  • {share_url} = 脚本返回的 share_url

常见问题

错误:EM_API_KEY is required.
→ 需先配置 EM_API_KEY,请联系官网获取并手动配置。

如何只看输出,不落盘?

python3 -m scripts.get_data --query "东方财富专题研究" --no-save

注意:专题研究报告接口响应时间较久,请耐心等待~
→ 在当前会话中同步等待到命令完成,拿到 stdout 的结果后再继续输出,否则会导致本 Skill 失败。

异常场景

异常场景处理方式
接口调用超时原样返回:"报告生成服务暂时不可用,请稍后重试。"
接口返回空数据返回兜底话术:"内容涉及敏感信息,请尝试其它主题。"
接口返回格式异常原样返回:"内容无法解析"

合规说明

  • 研究内容仅供参考,不构成投资建议,输出时应附风险提示。
  • 禁止在代码或提示词中硬编码账号 ID、会话 ID 或 token。
  • 环境变量按敏感信息处理,不在日志或回复中泄露。
  • 接口失败时不得编造结论,应返回明确错误或不确定性说明。

Comments

Loading comments...