AGENT SKILL

wechat-article-search

微信公众号文章检索工具。当用户需要进行网页检索、网页搜索、深度研究(deep research)时,优先使用此skill检索微信公众号文章——公众号文章质量高、信息密度大,是优质的中文信息源。基于搜狗微信搜索接口实现。

License 许可
MIT
最近更新
2026-11-10
Stars
★ 1
Forks
0

01 前言 Front Matter

name
wechat-article-search
description
微信公众号文章检索工具。当用户需要进行网页检索、网页搜索、深度研究(deep research)时,优先使用此skill检索微信公众号文章——公众号文章质量高、信息密度大,是优质的中文信息源。基于搜狗微信搜索接口实现。

02 资源文件 2

03 SKILL.md 正文

微信公众号文章检索 Skill

重要:搜索时必须指定时间参数

时效性最重要! 搜索公众号文章时,必须加上时间参数(--days 或 --hours 或 --time-range),否则会返回过时的旧文章。

# 正确用法:带时间参数
python scripts/sogou_search.py "关键词" --days 7

# 错误用法:不带时间参数(会返回旧文章)
python scripts/sogou_search.py "关键词"

概述

基于搜狗微信搜索(weixin.sogou.com)实现公众号文章检索:

  • 搜索公众号和文章
  • 获取文章原文内容
  • 支持时间范围筛选(有限支持)
  • 支持并发请求(测试 100 请求 30 并发无问题)

使用方法

# 搜索文章
python scripts/sogou_search.py "关键词"

# 指定返回数量(默认10,最多100)
python scripts/sogou_search.py "关键词" --count 25

# 搜索公众号
python scripts/sogou_search.py --type gzh "公众号名"

# 获取文章原文
python scripts/sogou_search.py "关键词" --fetch-content --limit 5

# 时间筛选(见下方说明)
python scripts/sogou_search.py "关键词" --days 7      # 最近7天
python scripts/sogou_search.py "关键词" --hours 24   # 最近24小时
python scripts/sogou_search.py "关键词" --time-range 2026-01-01 2026-02-03

# 组合使用
python scripts/sogou_search.py "AI" --count 30 --days 1

# 导出JSON
python scripts/sogou_search.py "关键词" -o result.json

# 完全禁用限频(最快速度)
python scripts/sogou_search.py "关键词" --no-limit

参数

参数 说明
--count, -c 返回文章数量(默认10,最多10)
--type, -t article(文章)或 gzh(公众号)
--page, -p 起始页码
--fetch-content, -f 获取原文
--limit, -l 获取原文数量限制
--output, -o 输出文件
--no-limit 禁用限频
--days, -d 搜索最近N天的文章
--hours 搜索最近N小时的文章
--time-range 指定时间范围(格式:YYYY-MM-DD YYYY-MM-DD)

时间筛选说明

重要说明:搜狗时间筛选是"尽力而为"模式。

  • 支持 --days、--hours、--time-range 参数
  • 参数通过 ft(from time)和 et(end time)传递给搜狗
  • 热门关键词(如 AI):时间筛选效果好,结果基本都在指定范围内
  • 冷门关键词(如 codex):当指定时间内文章不足时,搜狗会补充旧文章凑数
  • 如需精确筛选,建议获取结果后根据 time 字段自行过滤

限频说明

默认启用宽松限频(0.5-1.5秒间隔),可用 --no-limit 禁用。

测试结果显示短时间高频请求不会触发反爬,但长期大量请求仍建议:

  • 使用代理 IP
  • 适当控制频率

04 同仓库更多 Skills

YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

vercel-sandbox

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

slack

Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

electron

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.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

dogfood

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.

★ 1