Agent skill · Data & Analytics

douyin-video-search

Searches Douyin (douyin.com) for videos by keyword and returns structured video data including author info, stats, cover, description, hashtags, and download URL. Supports date range filtering and sorting by relevance, likes, or recency. Use when user mentions Douyin search, scrape Douyin videos, collect TikTok China videos, extract douyin video data, grab douyin results, fetch douyin keyword videos, douyin video list, douyin content mining, search douyin by keyword, douyin likes filter, douyin date filter, douyin video download links, douyin creator info, douyin hashtag extraction, douyin vid

browser-actgithub.com/browser-actGitHub ↗
claude-codecodexcursorships scriptsMIT
Install
npx skills add browser-act/skills --skill douyin-video-search --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 7 KB
Bundled scripts: yes
Path: solutions/video-platforms/douyin-video-search/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 5,160
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Douyin — Video Search > Keyword → paginated list of videos with author, stats, cover, description, hashtags, download URL ## Language All process output to user (progress updates, process notifications) follows the user's language. ## Objective Fetch Douyin video search results for a given keyword, with optional sort order and date filters, returning complete structured data for each video. ## Prerequisites - Browser is open and navigated to any Douyin page (douyin.com) with an active logged-in session - User is logged in to Douyin (avatar visible in top-right corner) ## Pre-execution Checks ### 1. Tool Readiness If browser-act has been confirmed available in the current session → skip this step. Invoke `browser-act` via Skill tool to load usage. If installation or configuration issues arise, follow its guidance to resolve then retry. ### 2. Login Verification If login status for Douyin has been confirmed in the current session → skip this step. Otherwise: navigate to `https://www.douyin.com` and check the top-right corner: - User avatar or account name visible → logged in, continue - "登录" button visible → not logged in; inform the user and assist them in completing login via `re

What's inside
Steps it walks through
  1. Language
  2. Objective
  3. Prerequisites
  4. Pre-execution Checks
  5. 1. Tool Readiness
  6. 2. Login Verification
  7. Capability Components
  8. API: Search videos by keyword
  9. Enum Parameters
  10. Pagination
  11. Success Criteria
  12. Known Limitations
  13. Execution Efficiency
  14. Experience Notes
Ships with 1 file
  • scripts/search-videos.py
More from skills
All skills →
About this skill
What does the douyin-video-search skill do?

Searches Douyin (douyin.com) for videos by keyword and returns structured video data including author info, stats, cover, description, hashtags, and download URL. Supports date range filtering and sorting by relevance, likes, or recency. Use when user mentions Douyin search, scrape Douyin videos, collect TikTok China videos, extract douyin video data, grab douyin results, fetch douyin keyword videos, douyin video list, douyin content mining, search douyin by keyword, douyin likes filter, douyin date filter, douyin video download links, douyin creator info, douyin hashtag extraction, douyin vid

How do I install it?

Run `npx skills add browser-act/skills --skill douyin-video-search --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From browser-act/skills, a repository with 5,160 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going