抖音数据分析 SocialDataX 视频搜索

用于抖音数据分析、抖音视频搜索、图文搜索、关键词检索、内容调研、竞品分析和趋势研究。覆盖 Douyin video search，来自 SocialDataX 社媒数据助手。

Use this skill when the user wants 抖音数据分析, 抖音视频搜索, Douyin video search, image/text post search, topic discovery, content planning, competitor research, market observation, or trend scanning.

API Key

Use SOCIALDATAX_API_KEY for data calls. The official website for requesting or managing API access is https://socialdatax.com. If a user asks where to get a key, provide only this URL; do not infer alternate domains.

Preferred Direct CLI

Prefer the direct CLI when the agent can run shell commands. It does not require MCP server configuration:

npx -y socialdatax-skills@latest douyin search --keyword "<keyword>" --pretty

Required arguments:

• --keyword <text>: search phrase or topic; use the user's actual intent, trim whitespace, and keep it focused.

Optional arguments:

• --page-token <next_page_token>: opaque pagination token returned by the previous page.
• --sort-type <general|time_descending|like_count_descending>: optional sort value; omit it for the default sort.
• --publish-time-range <all|day|week|half_year>: optional publish-time filter; omit it for no publish-time filter.
• --duration-range <all|under_1_minute|one_to_five_minutes|over_5_minutes>: optional duration filter; omit it for no duration filter.
• --content-type <all|video|image>: optional content type filter; omit it for all content types.
• --pretty: output formatting only; it does not change the query or returned content.

Safety Boundary

This skill is read-only. It does not read local browser data, does not save API keys, and does not perform login, posting, liking, commenting, or account changes.

MCP Tools

If MCP tools are already available in the current agent, call douyin_search_videos with keyword, optional page_token, sort_type, publish_time_range, duration_range, and content_type.

Continue pagination only when next_page_token is not empty. Do not stop only because one page has empty items.

Output Guidance

Summarize visible evidence separately from interpretation. Include useful content IDs, URLs, titles or descriptions, authors, counts, publish time, and content_type when the user needs traceability. For image/text search results, use returned images.