>- 抓取 A 股消息面情报:从财联社、华尔街见闻、金十、新浪 7x24、东财快讯、 证监会/央行/上交所/财政部政策公告、东方财富股吧等公开来源抓取与股票相关的 新闻、政策、情绪,输出结构化 JSON 或 Markdown。 当用户提到“A 股消息面”、“抓新闻”、“个股消息”、“政策监管”、“股吧情绪”、 “财联社”、“东财快讯”、“市场情绪”或需要把某只股票相关的公开情报聚合出来时 触发。也适用于“帮我看看 000001 最近有什么消息”这类口语化请求。
npx skills add https://github.com/daymade/claude-code-skills --skill ashare-news-fetcher
从多个公开中文财经/政策/社交来源抓取 A 股相关情报,输出结构化条目。
能做的:
000001,600519)抓取该股股吧情绪不能做的:
requests(必须)beautifulsoup4(可选,只有抓取政策来源时才需要)akshare(可选,用于名称→代码匹配;没有时只用正则提取代码)jieba(可选,安装后名称匹配使用分词,降低误匹配)JIN10_APP_ID(金十数据接口需要;未设置时会跳过该来源,不影响其他 cn 来源)最简安装:
pip install requests
# 如需政策来源:
pip install beautifulsoup4
# 如需名称匹配:
pip install akshare
# 如需更精确的名称匹配:
pip install jieba
/ashare-news-fetcher 000001,600519 cn,guba
参数说明(都是可选的):
000001,600519cn(中文快讯)、policy(政策)、guba(股吧)--sources cn --limit 30python scripts/fetch_intel.py --sources cn,policy --limit 20
python scripts/fetch_intel.py --symbols 000001,600519 --sources guba
python scripts/fetch_intel.py --sources cn --keywords 降准,降息 --format markdown
常用选项:
--sources:来源组,默认 cn--symbols:股票代码,用于 guba--keywords:关键词过滤,逗号分隔--limit:每组最多返回条数,默认 30--format:json 或 markdown,默认 json--output:输出到文件;省略则打印到 stdout--verbose:打印调试日志| 来源组 | 来源 | 内容类型 | 是否需要 bs4 |
|---|---|---|---|
| cn | 财联社、华尔街见闻、金十、新浪 7x24、东财快讯 | 市场快讯 | 否 |
| policy | 证监会、央行、上交所、财政部 | 政策/监管公告 | 是(证监会除外) |
| guba | 东方财富股吧 | 个股散户情绪 | 否 |
详细 API 端点和解析方式见 references/source_apis.md。
测试说明与运行方式见 references/testing.md。
每个 item 的结构见 references/output_schema.md。示例:
{
"item_id": "4ffde7bc7b18b55e",
"source_id": "cn_sina",
"source_name": "sina",
"title": "...",
"summary": "...",
"url": "...",
"category": "market",
"priority": "normal",
"tags": ["公司", "市场"],
"related_symbols": ["000001"],
"published_at": "2026-06-25 17:50:41",
"fetched_at": "2026-06-25 09:50:52",
"extra": {}
}
按时间倒序排列,每条展示来源、时间、分类、相关代码、标签、链接和摘要。
guba 来源对反爬较敏感,建议单次不要请求过多股票,代码之间已有 0.5s 请求间隔。jin10)前,建议在环境变量中配置 JIN10_APP_ID;未配置时该来源会自动跳过,不影响财联社、华尔街见闻、新浪、东财等其他 cn 来源。 export JIN10_APP_ID="your-app-id"
拿到结构化情报后,常见的下一步是交给分析 skill 做总结或生成日报:
> 要不要把这些消息总结一下,生成一份 A 股消息日报?
Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to improve their communication and leadership skills.
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".
Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack.
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.
Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.
Interactive daily standup/meeting update generator. Use when user says 'daily', 'standup', 'scrum update', 'status update', 'what did I do yesterday', 'prepare for meeting', 'morning update', or 'team sync'. Pulls activity from GitHub, Jira, and Claude Code session history. Conducts 4-question interview (yesterday, today, blockers, discussion topics) and generates formatted Markdown update.
Take daymade/ashare-news-fetcher from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference pip.
Without those the skill loads but fails at the first command.