← Back to Skills Marketplace
109
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install weibo-backup
Description
使用 Playwright 自动化下载微博(weibo)收藏内容，本人或其他博主发表微博内容所有历史记录，包括图片、视频和长文章。 当用户提到"微博收藏"、"下载微博"、"备份微博"、"weibo favorites"、 "抓取微博内容"、"保存微博图片"或任何与微博数据备份相关的需求时， 支持 headless...
Usage Guidance
This skill appears coherent for personal Weibo backup using Playwright. Before installing, consider: run it locally and inspect the included Python file yourself; understand that the tool saves cookies or browser profile data locally (cookies.json or browser_data) — those contain session credentials and should be kept private; avoid supplying cookies that belong to other users; respect Weibo's terms of service and rate limits (the tool can download many images/videos and consume a lot of disk space); do not use it for large-scale commercial scraping. If you plan to run this on a shared machine, run it in a restricted environment (container or VM) and ensure you have sufficient disk space and bandwidth.
Capability Analysis
Type: OpenClaw Skill
Name: weibo-backup
Version: 1.0.0
The skill bundle provides a Weibo scraping and backup tool using Playwright. While the code appears functional for its stated purpose, it possesses high-risk capabilities including session cookie persistence (cookies.json), automated browser control, and arbitrary file downloads. The script weibo_favorites_4skill.py can also connect to remote browsers via CDP (--cdp-endpoint), which is a significant security risk if misconfigured. No clear evidence of intentional malice or data exfiltration was found, but the broad permissions required for scraping and the handling of sensitive session data warrant a suspicious classification according to the provided criteria.
Capability Assessment
Purpose & Capability
The name/description (Weibo data backup) align with the included SKILL.md and the Python script: it uses Playwright to automate a browser, save cookies or use a user-data-dir, scroll pages, extract images/videos/articles, and write Markdown files. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
Runtime instructions are narrowly scoped to opening a browser, prompting the user to log in if necessary, reading/writing cookies.json or a browser user-data directory, crawling Weibo pages, downloading media, and writing files to an output directory. The SKILL.md explicitly instructs to ask the user to log in and not to run headless on first login. It does not instruct the agent to read arbitrary system files, environment secrets, or to transmit data to remote endpoints outside of fetching expected media resources.
Install Mechanism
There is no automated install spec; the README and SKILL.md recommend installing Playwright via pip and running 'playwright install chromium', which is appropriate for a Playwright script. The README mentions an external npx-based skill installer as an installation convenience but the skill bundle itself contains the script and docs.
Credentials
The skill declares no required environment variables or primary credentials. It uses local cookies.json or a browser user-data directory for authentication, which is appropriate for automating a logged-in browser session. There are no requests for unrelated secrets or system-level credentials.
Persistence & Privilege
The skill is not marked always:true and does not attempt to change other skills or global agent configuration. It writes output files (index.md, markdown for posts, media) to its own output directory and can update an index.md in the same directory, which is expected behaviour for this tool.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install weibo-backup - After installation, invoke the skill by name or use
/weibo-backup - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of weibo-downloader (weibo-backup) skill:
- Automates backup of Weibo favorites, personal posts, or other users' posts, including images, videos, and long articles.
- Supports Playwright-based headless operations; offers flexible download options (image size, video, article extraction).
- Saves content in Markdown with bidirectional navigation links for easy browsing.
- Includes detailed usage instructions, command examples, parameter explanations, and troubleshooting.
- Requires user login for first-time setup; guides user through safe login and data extraction steps.
Metadata
Frequently Asked Questions
What is Weibo 微博数据备份?
使用 Playwright 自动化下载微博(weibo)收藏内容，本人或其他博主发表微博内容所有历史记录，包括图片、视频和长文章。 当用户提到"微博收藏"、"下载微博"、"备份微博"、"weibo favorites"、 "抓取微博内容"、"保存微博图片"或任何与微博数据备份相关的需求时， 支持 headless... It is an AI Agent Skill for Claude Code / OpenClaw, with 109 downloads so far.
How do I install Weibo 微博数据备份?
Run "/install weibo-backup" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Weibo 微博数据备份 free?
Yes, Weibo 微博数据备份 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Weibo 微博数据备份 support?
Weibo 微博数据备份 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Weibo 微博数据备份?
It is built and maintained by hhjin (@hhjin); the current version is v1.0.0.
More Skills