← Back to Skills Marketplace
wacai-zhishudashi-baidu-ranking
by
shidengyun
· GitHub ↗
· v1.0.0
· MIT-0
329
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install wacai-zhishudashi-baidu-ranking
Description
抓取百度搜索关键词“指数大师”的搜索结果标题，并按从前到后的顺序整理成编号列表，再通过企业微信机器人 webhook 推送。用于日报、定时巡检、品牌词/关键词排名观察、搜索结果快照汇报，尤其适合需要“打开浏览器→搜索→提取标题→推送消息”这一固定流程时。
Usage Guidance
Before installing or running this skill: (1) Be aware the code includes a default/hard-coded WeCom webhook URL — replace it with your own webhook (set WECOM_WEBHOOK_URL or use --webhook-url) if you want messages delivered to a destination you control. (2) Avoid granting the skill access to your existing Chrome profile or Browser Relay unless you trust it, because that exposes browsing context and cookies. (3) Use --dry-run first to inspect the payload the script would send. (4) If you must use this skill for sensitive data, review who controls the embedded webhook key and consider removing it from the code. (5) If unsure, treat this as potentially exfiltrating scraped content and prefer to supply your own webhook endpoint or run the scraping locally with manual push.
Capability Analysis
Type: OpenClaw Skill
Name: wacai-zhishudashi-baidu-ranking
Version: 1.0.0
The skill bundle is a legitimate automation tool designed to scrape Baidu search results for the keyword '指数大师' and send the findings to a WeChat Work (WeCom) webhook. The Python script (scripts/push_wecom.py) and the agent instructions (SKILL.md) are strictly focused on this task, using standard libraries and clear logic. While a WeCom webhook key is hardcoded, it is presented as the default endpoint for the tool's specific reporting purpose and can be overridden via environment variables, posing no inherent risk to the user's system or sensitive data.
Capability Assessment
Purpose & Capability
The name/description (scrape Baidu for the keyword and push results to a WeCom webhook) matches the included instructions and the push_wecom.py script. Requiring a webhook is expected for pushing messages. However, the code and SKILL.md embed a specific public WeCom webhook URL as the default, which is unusual if the expectation is that the user provides their own webhook.
Instruction Scope
Runtime instructions tell the agent to open baidu.com, run searches, and extract page titles via browser.snapshot or evaluate — which is appropriate for scraping. Concerningly, the SKILL.md allows/encourages using an existing Chrome profile (profile: "chrome") or Browser Relay when the user requests it; using an existing profile can expose other browsing context, cookies, or data. The SKILL.md also includes an explicit curl example with the embedded webhook URL (same as the script default), meaning scraped data will be sent to that external endpoint unless the user overrides it.
Install Mechanism
Instruction-only skill with a small helper script included; there is no installation spec, no downloads, and no packages installed. The risk from installation artifacts is low.
Credentials
The skill declares no required env vars, and the script accepts an override via WECOM_WEBHOOK_URL, but it provides a DEFAULT_WEBHOOK_URL embedded in the code pointing to a specific WeCom webhook. Embedding a remote webhook in the skill means data collected by the skill could be forwarded to an endpoint controlled by the skill author or a third party, which is disproportionate unless the user expects that. No other credentials are requested.
Persistence & Privilege
The skill does not request always:true, does not modify other skills or system-wide configs, and does not store credentials. Autonomous invocation is allowed (platform default) but is not combined here with other high privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install wacai-zhishudashi-baidu-ranking - After installation, invoke the skill by name or use
/wacai-zhishudashi-baidu-ranking - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of zhishudashi-baidu-ranking.
- Automates daily workflow: searches Baidu for "指数大师," extracts main result titles in order, and pushes the list to WeCom via webhook.
- Supports reliable browser automation, main-title-only extraction, and error handling for incomplete or failed results.
- Includes push_wecom.py script for flexible WeCom message sending (multiple modes supported).
Metadata
Frequently Asked Questions
What is wacai-zhishudashi-baidu-ranking?
抓取百度搜索关键词“指数大师”的搜索结果标题，并按从前到后的顺序整理成编号列表，再通过企业微信机器人 webhook 推送。用于日报、定时巡检、品牌词/关键词排名观察、搜索结果快照汇报，尤其适合需要“打开浏览器→搜索→提取标题→推送消息”这一固定流程时。 It is an AI Agent Skill for Claude Code / OpenClaw, with 329 downloads so far.
How do I install wacai-zhishudashi-baidu-ranking?
Run "/install wacai-zhishudashi-baidu-ranking" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is wacai-zhishudashi-baidu-ranking free?
Yes, wacai-zhishudashi-baidu-ranking is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does wacai-zhishudashi-baidu-ranking support?
wacai-zhishudashi-baidu-ranking is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created wacai-zhishudashi-baidu-ranking?
It is built and maintained by shidengyun (@shidengyun); the current version is v1.0.0.
More Skills