mx-search
datawhalechina/hello-agents · Agent Skill
Provides access to intelligent financial information search, filtering sources for up-to-date news, analytics, and specific data.
Jump to install ↓Overview
| Publisher |  datawhalechinaOrganization |
|---|---|
| Repository | datawhalechina/hello-agents ↗ |
| Skill folder | mx-search |
| Stars | 77,275 |
| Bundled files | 1 |
| License | not specified — check with the author |
| Last updated | May 16, 2026 |
| Links | Skill source ↗ · Repository ↗ |
Mozgi check
What we found in the skill files. Details come with a subscription.
Installation
A skill is a folder with a SKILL.md file. Pick your agent and run the commands in a terminal (macOS, Linux or Git Bash on Windows) from your project root.
Copy the prompt into Claude, Codex or another assistant: it will review the skill and install it for you.
Install the “mx-search” skill from mozgi.io (https://mozgi.io/skills/mx-search/) for me. 1. Download the archive: https://mozgi.io/skills/mx-search/download If it fails, take the skill folder from the source: https://github.com/datawhalechina/hello-agents/tree/main/Co-creation-projects/lcyting-StockSage-agent/skills/资讯搜索/mx-search 2. Read SKILL.md and the other files. Check the skill is safe: no hidden commands, no sending data elsewhere, no scripts doing something other than described. If anything looks suspicious, stop and tell me. 3. Put the “mx-search” folder into your agent's skills folder: .claude/skills/ for Claude Code, .agents/skills/ for Codex, .cursor/skills/ for Cursor, .gemini/skills/ for Gemini CLI. Inside the project if we are in one, otherwise in the home folder (~/.claude/skills/ etc.). 4. Make sure <skills folder>/mx-search/SKILL.md exists. 5. Briefly tell me what this skill does and offer to try it on my task. If you cannot do a step yourself, tell me what to click or type.
git clone --depth 1 --branch main https://github.com/datawhalechina/hello-agents.git /tmp/hello-agents mkdir -p .claude/skills cp -r /tmp/hello-agents/Co-creation-projects/lcyting-StockSage-agent/skills/资讯搜索/mx-search .claude/skills/mx-search
Restart Claude Code — the skill appears in the list; call it manually with /mx-search. For all projects use ~/.claude/skills.
git clone --depth 1 --branch main https://github.com/datawhalechina/hello-agents.git /tmp/hello-agents mkdir -p .agents/skills cp -r /tmp/hello-agents/Co-creation-projects/lcyting-StockSage-agent/skills/资讯搜索/mx-search .agents/skills/mx-search
Codex looks for skills in .agents/skills from the current folder up to the repo root; call one with /skills or $mx-search. For all projects use ~/.agents/skills.
git clone --depth 1 --branch main https://github.com/datawhalechina/hello-agents.git /tmp/hello-agents mkdir -p .cursor/skills cp -r /tmp/hello-agents/Co-creation-projects/lcyting-StockSage-agent/skills/资讯搜索/mx-search .cursor/skills/mx-search
Cursor picks the skill up on start; call it with “/” in Agent chat. Cursor also reads .claude/skills and .agents/skills. For all projects use ~/.cursor/skills.
git clone --depth 1 --branch main https://github.com/datawhalechina/hello-agents.git /tmp/hello-agents mkdir -p .gemini/skills cp -r /tmp/hello-agents/Co-creation-projects/lcyting-StockSage-agent/skills/资讯搜索/mx-search .gemini/skills/mx-search
Gemini CLI offers to activate the skill when a task matches — you approve it. For all projects use ~/.gemini/skills.
Read SKILL.md and any companion files before deciding whether to install. Click a file to preview it.
SKILL.md contents
Original author text · read-onlymx-search 妙想资讯搜索 skill
本 Skill 基于东方财富妙想搜索能力，基于金融场景进行信源智能筛选，用于获取涉及时效性信息或特定事件信息的任务，包括新闻、公告、研报、政策、交易规则、具体事件、各种影响分析、以及需要检索外部数据的非常识信息等。避免AI在搜索金融场景信息时，参考到非权威、及过时的信息。
功能说明
根据用户问句搜索相关金融资讯，获取与问句相关的资讯信息（如研报、新闻、解读等），并返回可读的文本内容。
配置
- API Key: 通过环境变量
MX_APIKEY设置 - 默认输出目录:
/root/.openclaw/workspace/mx_data/output/（自动创建） - 输出文件名前缀:
mx_search_ - 输出文件:
mx_search_{query}.txt- 提取后的纯文本结果mx_search_{query}.json- API 原始 JSON 数据
使用方式（直接 Python 脚本调用）
1. 需要用户在妙想Skills页面获取apikey。
2. 将apikey存到环境变量，命名为MX_APIKEY：
```bash
export MX_APIKEY=your_apikey_here
```
3. 直接运行 Python 脚本搜索，支持自然语言问句：
# ==================== 常用调用示例 ====================
# 1. 个股相关资讯
python ./mx_search.py "东方财富最新公告"
python ./mx_search.py "贵州茅台最新研报"
python ./mx_search.py "比亚迪机构观点汇总"
# 2. 行业/板块新闻
python ./mx_search.py "人工智能板块近期新闻"
python ./mx_search.py "新能源汽车产业政策最新解读"
# 3. 宏观经济与市场分析
python ./mx_search.py "美联储加息对A股影响分析"
python ./mx_search.py "今日大盘异动原因分析"
python ./mx_search.py "北向资金最新流向解读"
# 4. 个股事件
python ./mx_search.py "贵州茅台分红派息实施公告"
python ./mx_search.py "宁德时代定增预案解读"
# 5. 交易规则
python ./mx_search.py "科创板交易涨跌幅限制"
python ./mx_search.py "新股申购规则"
# 6. 指定输出目录（可选）
python ./mx_search.py "格力电器最新研报" /path/to/output> ⚠️ 安全注意事项
>
> - 外部请求: 本 Skill 会将您的查询文本发送至东方财富官方 API 域名 ( mkapi2.dfcfs.com ) 以获取金融数据。
> - 凭据保护: API Key 仅通过环境变量 MX_APIKEY 在服务端或受信任的运行环境中使用，不会在前端明文暴露。
输出说明
脚本执行后会：
1. 在终端格式化输出搜索结果，列出每条资讯的标题、来源、日期、内容
2. 自动创建输出目录 /root/.openclaw/workspace/mx_data/output/
3. 保存纯文本提取结果到 .txt 文件
4. 保存原始 JSON 响应供二次处理
异常情形与处理方式
| 异常情形 | 可能原因 | 处理方式 |
|----------|----------|----------|
| connect: Connection refused | 网络无法访问 mkapi2.dfcfs.com | 检查服务器网络配置，确保能访问公网 |
| 401 Unauthorized / API密钥不存在 | API Key 错误或已失效 | 前往妙想Skills页面重新获取 API Key 并更新环境变量 |
| code=113 / 今日调用次数已达上限 | 当日调用次数超限 | 前往妙想Skills页面获取更多调用次数 |
| 未找到相关资讯 | 关键词太偏门或没有最新相关信息 | 尝试更换关键词，或扩大搜索范围 |
| 返回内容为空 | 网络中断或请求超时 | 检查网络后重试 |
| JSON解析错误 | 网络不完整导致内容截断 | 检查网络后重试 |
问句示例
|类型|示例问句|
|----|----|
|个股资讯|格力电器最新研报、贵州茅台机构观点|
|板块/主题|商业航天板块近期新闻、新能源政策解读|
|宏观/风险|A股具备自然对冲优势的公司 汇率风险、美联储加息对A股影响|
|综合解读|今日大盘异动原因、北向资金流向解读|
返回说明
|字段路径|简短释义|
|----|----|
|title|信息标题，高度概括核心内容|
|secuList|关联证券列表，含代码、名称、类型等|
|secuList[].secuCode|证券代码（如 002475）|
|secuList[].secuName|证券名称（如立讯精密）|
|secuList[].secuType|证券类型（如股票 / 债券）|
|trunk|信息核心正文 / 结构化数据块，承载具体业务数据|
Frequently asked questions
What does the mx-search skill do?
Provides access to intelligent financial information search, filtering sources for up-to-date news, analytics, and specific data.
How do I install mx-search?
Open the “Installation” block on this page and pick your agent — Claude Code, Codex, Cursor or Gemini CLI — for ready-made commands that copy the skill folder to the right place. Or copy the prompt from the “Via assistant” tab and let the assistant review and install the skill.
Which AI models work with mx-search?
Skills are plain Markdown instructions (the Agent Skills format), so mx-search works with any agent that reads SKILL.md: Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and more. The model loads the instructions only when a task matches the skill's description.
Is mx-search free?
The skill is published openly by datawhalechina. The skill itself costs nothing — you only pay your AI provider for the tokens you use. No license is specified in the repository — check the terms with the author before commercial use.
Is it safe to install skills?
A skill is a set of instructions your agent will follow, so read SKILL.md and its companion files before installing. Scripts in the skill folder only run if your agent runs them — keep an eye on what it does and do not grant unnecessary permissions.
How is a skill different from an MCP server or a plugin?
An MCP server or plugin gives the model new tools — code that runs and returns a result. A skill gives it knowledge and process: how to approach a task, which steps to follow and what good output looks like. It needs no server or API key.
Related skills
All skills →mx-xuangu
Filters stocks by market and financial indicators, searches for stocks within industries/sectors, and recommends stocks and sectors using up-to-date data.
datawhalechina77.3k
xlsx
Excel Tables: formulas, pivot tables, formatting, reading and analyzing existing workbooks.
anthropics176k
data-analysis
Analyzes uploaded Excel/CSV files, executes SQL queries, generates statistics and pivot tables, exports results.
bytedance82.3k
data-scientist
Analyzes and processes data using resident engines (DuckDB, Polars) and one-shot tools. Suitable for CSV/parquet/JSON analysis, group-by, join, aggregation, time series, and plotting.
code-yeongyu68.8k
stock-analyzer
Analyzes stocks and markets, providing conclusions, technical data, insights, and trading plans for investment decisions.
ZhuLinsen64.8k
creating-financial-models
Creates advanced financial models, including DCF analysis, sensitivity testing, and Monte Carlo simulations for informed investment decisions.
anthropics52.5k