抖音达人数据 SocialDataX 达人作品

用于抖音达人数据、抖音达人作品、视频列表、图文列表、近期发布、内容调研和创作者内容分析。覆盖 Douyin creator videos，来自 SocialDataX 社媒数据助手。

Use this skill when the user wants 抖音达人数据, a Douyin / 抖音 creator's published works list, video list, image/text post list, content style analysis, recent-topic review, creator benchmarking, or account tracking.

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 user-posts --sec-user-id "<sec_user_id>" --pretty
npx -y socialdatax-skills@latest douyin user-posts --profile-url "<profile_url_or_share_text>" --pretty

• --sec-user-id <sec_user_id>: preferred when the creator sec_user_id is already known.
• --profile-url <profile_url_or_share_text>: use for a profile URL, short link, or profile share text.
• --page-token <next_page_token>: opaque pagination token; pass back exactly the token returned by the previous page and do not reuse it across users.
• --pretty: output formatting only.

Use either --sec-user-id or --profile-url for one command, not both.

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, use one of these tools:

• douyin_get_user_posted_videos_by_sec_user_id: preferred when sec_user_id is already known.
• douyin_get_user_posted_videos_by_profile_url: use for profile URLs, short links, or profile share text.

Creator work-list pagination uses page_token. Pass back exactly the returned next_page_token; tokens are bound to the current user and should not be reused across users.

Output Guidance

Summarize content-list evidence by title or description, summary, publish time, interaction counts, media links, and content type when present. For image/text posts, use image_urls rather than assuming a video playback URL exists. Use returned content IDs to chain into detail or comment analysis when needed.