How do I install the Media Crawler Weibo skill?

Run npx skillmds@latest add tsingyuai/media-crawler-weibo in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Media Crawler Weibo safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Media Crawler Weibo?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Media Crawler Weibo free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Media Crawler Weibo?

tsingyuai (@tsingyuai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Media Crawler Weibo by tsingyuai — Agent Skill

Name: Media Crawler Weibo
Author: tsingyuai

Media Crawler Weibo

Collect Weibo posts and creator evidence with MediaCrawler using search, exact post IDs, comments, optional media, and creator IDs. Use for discourse, trend, messaging, audience-language, or account research requiring preserved provenance and risk-aware detail enrichment.

tsingyuai Updated Sep 17, 2026

File contents

Weibo collection

Follow media-crawler. Define research purpose, keywords/post IDs/creator IDs, sample and time bounds, comments/media scope, and invoking Model Memory destination.

Search with --platform wb --type search; set WEIBO_SEARCH_TYPE deliberately. Use direct problem, category and audience/event query variants, then shortlist by relevance, time, source/account fit, content form and engagement. Configure exact post IDs in WEIBO_SPECIFIED_ID_LIST and user IDs in WEIBO_CREATOR_ID_LIST; run detail/creator mode.

ENABLE_WEIBO_FULL_TEXT makes extra detail requests and raises risk-control probability. Keep it off during broad discovery and enable it only for a small, explicit shortlist when full text is required. Treat repost text, original text and comments as different evidence. Deduplicate by post ID and preserve query provenance.

Return exact inputs, full-text/comment/media flags, raw/copied paths, coverage, time, commit, selection rationale and risk-control/partial failures.

Frequently asked questions