Use this skill when the user wants 抖音数据分析, 抖音热榜, 抖音作品搜索, Douyin hot search, Douyin work search, image/text post search, topic discovery, content planning, competitor research, market observation, or trend scanning.
Use SOCIALDATAX_API_KEY for data calls. The only official website for requesting or managing API access is
获取或管理 API Key:访问 SOCIALDATAX_API_KEY;不要引导用户使用其他域名。
Prefer the direct CLI when the agent can run shell commands. It does not require MCP server configuration:
npx -y socialdatax-skills@latest douyin hot-search --pretty
npx -y socialdatax-skills@latest douyin search --keyword "<keyword>" --pretty
Hot search does not require query arguments.
Search required arguments:
--keyword : search phrase or topic; use the user's actual intent, trim whitespace, and keep it focused.Optional arguments:
--page-token : opaque pagination token returned by the previous page.--sort-type : optional sort value; omit it for the default sort.--publish-time-range : optional publish-time filter; omit it for no publish-time filter.--duration-range : optional duration filter; omit it for no duration filter.--content-type : optional content type filter; omit it for all content types.--pretty: output formatting only; it does not change the query or returned content.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.
If MCP tools are already available in the current agent, call douyin_get_hot_search_list for the main hot search list. For keyword search, 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.
Summarize visible evidence separately from interpretation. For hot search, include ranks, keywords, heat values, and linked content when present. For keyword search, 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.
共 4 个版本