SocialDataX Skills | 社媒数据助手 Skills

This public package provides the unified skill installer and direct CLI helper for SocialDataX services.

The current public tools support 小红书 / Xiaohongshu / XHS / RedNote, 抖音 / Douyin, 快手 / Kuaishou / Kwai, Bilibili / 哔哩哔哩 / B站, 微博 / Weibo, 视频号 / WeChat Channels, 知乎 / Zhihu, Instagram, X / Twitter, YouTube, and TikTok content research and analysis workflows, plus WeChat Official Account / 微信公众号 article details, XHS / Douyin / Kuaishou / Weibo / X / Twitter local media download, WeChat Channels local media decrypt/save, Bilibili local video download, and 敏感词检测 / 违禁词检查 text checks. The public skill layer is intentionally named by capability so supported services can evolve without changing the installation model.

direct npx JSON commands for agents that can run shell commands
AgentSkills-compatible installers split by capability for OpenClaw, Hermes Agent, Codex, Claude Code, and general agent skill directories
links to platform or capability MCP docs when a client should use MCP directly

The business implementation is privately hosted. This repository exposes only the public package, skill, and connection surface for social media content intelligence workflows. It is not a unified MCP server and does not include a registry server card; standalone MCP listings are published separately when their repo-tracked materials exist.

High-Intent Skill Catalog

See CATALOG.md for curated high-intent Agent Skill entries across SkillHub, ClawHub, ModelScope, and direct CLI usage. The catalog focuses on proven workflows such as XHS content research, XHS comment analysis, XHS hot topic planning, Douyin transcript extraction, and sensitive term checks.

Search Aliases

Common search phrases for this skill package:

SocialDataX Skills
social media skills
AgentSkills social media
OpenClaw social media skills
Hermes Agent social media skills
media search skill
media comments skill
media transcript skill
speech-to-text transcript skill
口播转文字 skill
creator profile skill
Xiaohongshu skills
XHS skills
RedNote skills
XHS media download
小红书图片下载
小红书视频下载
Douyin skills
抖音 skills
Kuaishou skills
Kwai skills
快手 skills
Bilibili skills
Bilibili content research
B站视频下载
哔哩哔哩视频下载
Weibo skills
微博 skills
WeChat Channels skills
视频号 skills
WeChat Official Account skills
微信公众号 skills
mp.weixin.qq.com article detail
Zhihu skills
知乎 skills
Instagram skills
X skills
Twitter skills
YouTube skills
TikTok skills
SocialDataX content research
content research assistant
敏感词检测
违禁词检测
文案发布前检查
sensitive check skill
content safety skill
text safety check

Hosted MCP Entries

XHS hosted MCP endpoint: https://mcp.socialdatax.com/xhs/mcp
Douyin hosted MCP endpoint: https://mcp.socialdatax.com/douyin/mcp
Kuaishou hosted MCP endpoint: https://mcp.socialdatax.com/kuaishou/mcp
Bilibili hosted MCP endpoint: https://mcp.socialdatax.com/bilibili/mcp
Weibo hosted MCP endpoint: https://mcp.socialdatax.com/weibo/mcp
WeChat Content / 微信内容 hosted MCP endpoint: https://mcp.socialdatax.com/wechat/mcp
Zhihu / 知乎 hosted MCP endpoint: https://mcp.socialdatax.com/zhihu/mcp
Instagram hosted MCP endpoint: https://mcp.socialdatax.com/instagram/mcp
X / Twitter hosted MCP endpoint: https://mcp.socialdatax.com/x/mcp
YouTube hosted MCP endpoint: https://mcp.socialdatax.com/youtube/mcp
TikTok hosted MCP endpoint: https://mcp.socialdatax.com/tiktok/mcp
Sensitive Words Check hosted MCP endpoint: https://mcp.socialdatax.com/sensitive-check/mcp
Hosted transport: streamable-http
Authentication: Authorization: Bearer <SOCIALDATAX_API_KEY>
Website: https://socialdatax.com
Repo-tracked platform MCP listings: com.52choujiang/xhs-insights, com.52choujiang/douyin-insights, com.52choujiang/kuaishou-insights, com.52choujiang/bilibili-insights, com.52choujiang/weibo-insights, com.52choujiang/wechat-channels-insights, com.52choujiang/zhihu-insights, com.52choujiang/instagram-insights, com.52choujiang/x-insights, com.52choujiang/youtube-insights, and com.52choujiang/tiktok-insights.
Repo-tracked future SocialDataX namespace draft files exist for XHS and Douyin: com.socialdatax/xhs-insights and com.socialdatax/douyin-insights.
Reserved future SocialDataX namespace names for existing platform listings without draft files yet: com.socialdatax/kuaishou-insights, com.socialdatax/bilibili-insights, com.socialdatax/weibo-insights, com.socialdatax/wechat-channels-insights, com.socialdatax/zhihu-insights, com.socialdatax/instagram-insights, com.socialdatax/x-insights, com.socialdatax/youtube-insights, and com.socialdatax/tiktok-insights.
Hosted endpoint without a repo-tracked standalone listing: Sensitive Words Check.
Unified MCP registry name: none; this package installs skills and calls explicit hosted MCP entries.
Current public capability version: 0.2.43

Direct CLI

For most skill users, no MCP client configuration is required. Install the skills, set SOCIALDATAX_API_KEY, and let the agent run the direct npx commands.

Examples:

npx -y socialdatax-skills@latest xhs search --keyword "露营" --pretty
npx -y socialdatax-skills@latest xhs search --keyword "露营" --since-days 7 --pages 2 --pretty
npx -y socialdatax-skills@latest xhs hot-search --pretty
npx -y socialdatax-skills@latest xhs detail --note-id "<note_id>" --pretty
npx -y socialdatax-skills@latest xhs comments --note-id "<note_id>" --pretty
npx -y socialdatax-skills@latest xhs comments --note-id "<note_id>" --sort-type time_descending --pretty
npx -y socialdatax-skills@latest xhs comments --note-id "<note_id>" --all --include-replies --pretty
npx -y socialdatax-skills@latest xhs sub-comments --note-id "<note_id>" --comment-id "<comment_id>" --pretty
npx -y socialdatax-skills@latest xhs user-info --user-id "<user_id>" --pretty
npx -y socialdatax-skills@latest xhs user-posts --user-id "<user_id>" --pretty
npx -y socialdatax-skills@latest xhs user-posts --user-id "<user_id>" --since-days 30 --pretty
npx -y socialdatax-skills@latest xhs transcript --url "<note_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest xhs transcript --note-id "<note_id>" --pretty
npx -y socialdatax-skills@latest xhs transcript --job-id "<job_id>" --pretty
npx -y socialdatax-skills@latest xhs download-media --url "<xhs_media_url>" --output-dir ./downloads --pretty
npx -y socialdatax-skills@latest douyin hot-search --pretty
npx -y socialdatax-skills@latest douyin search --keyword "露营" --pretty
npx -y socialdatax-skills@latest douyin detail --aweme-id "<aweme_id>" --pretty
npx -y socialdatax-skills@latest douyin comments --aweme-id "<aweme_id>" --pretty
npx -y socialdatax-skills@latest douyin comments --aweme-id "<aweme_id>" --all --include-replies --pretty
npx -y socialdatax-skills@latest douyin replies --aweme-id "<aweme_id>" --comment-id "<comment_id>" --pretty
npx -y socialdatax-skills@latest douyin user-info --sec-user-id "<sec_user_id>" --pretty
npx -y socialdatax-skills@latest douyin user-info --profile-url "<profile_url_or_share_text>" --pretty
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
npx -y socialdatax-skills@latest douyin user-series --sec-user-id "<sec_user_id>" --pretty
npx -y socialdatax-skills@latest douyin user-series --profile-url "<profile_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest douyin transcript --url "<douyin_content_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest douyin transcript --aweme-id "<aweme_id>" --pretty
npx -y socialdatax-skills@latest douyin transcript --job-id "<job_id>" --pretty
npx -y socialdatax-skills@latest douyin download-media --url "<douyin_media_url>" --output-dir ./downloads --pretty
npx -y socialdatax-skills@latest kuaishou hot-search --pretty
npx -y socialdatax-skills@latest kuaishou search --keyword "露营" --pretty
npx -y socialdatax-skills@latest kuaishou user-search --keyword "露营" --pretty
npx -y socialdatax-skills@latest kuaishou detail --photo-id "<photo_id>" --pretty
npx -y socialdatax-skills@latest kuaishou detail --url "<kuaishou_content_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest kuaishou comments --photo-id "<photo_id>" --pretty
npx -y socialdatax-skills@latest kuaishou comments --photo-id "<photo_id>" --all --include-replies --pretty
npx -y socialdatax-skills@latest kuaishou comments --url "<kuaishou_content_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest kuaishou replies --photo-id "<photo_id>" --comment-id "<comment_id>" --pretty
npx -y socialdatax-skills@latest kuaishou user-info --user-id "<user_id>" --pretty
npx -y socialdatax-skills@latest kuaishou user-info --profile-url "<profile_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest kuaishou user-posts --user-id "<user_id>" --pretty
npx -y socialdatax-skills@latest kuaishou user-posts --profile-url "<profile_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest kuaishou transcript --url "<kuaishou_content_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest kuaishou transcript --photo-id "<photo_id>" --pretty
npx -y socialdatax-skills@latest kuaishou transcript --job-id "<job_id>" --pretty
npx -y socialdatax-skills@latest kuaishou download-media --url "<kuaishou_media_url>" --output-dir ./downloads --pretty
npx -y socialdatax-skills@latest bilibili search-videos --keyword "露营" --pretty
npx -y socialdatax-skills@latest bilibili search-articles --keyword "露营" --pretty
npx -y socialdatax-skills@latest bilibili detail --content-id "<content_id>" --pretty
npx -y socialdatax-skills@latest bilibili detail --url "<bilibili_content_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest bilibili comments --content-id "<content_id>" --pretty
npx -y socialdatax-skills@latest bilibili comments --url "<bilibili_content_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest bilibili replies --comment-object-id "<comment_object_id>" --comment-object-type 1 --comment-id "<comment_id>" --pretty
npx -y socialdatax-skills@latest bilibili reactions --post-id "<post_id>" --pretty
npx -y socialdatax-skills@latest bilibili reactions --url "<bilibili_opus_or_dynamic_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest bilibili user-info --user-id "<user_id>" --pretty
npx -y socialdatax-skills@latest bilibili user-info --profile-url "<profile_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest bilibili user-videos --user-id "<user_id>" --pretty
npx -y socialdatax-skills@latest bilibili user-videos --profile-url "<profile_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest bilibili user-articles --user-id "<user_id>" --pretty
npx -y socialdatax-skills@latest bilibili user-articles --profile-url "<profile_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest bilibili user-dynamics --user-id "<user_id>" --pretty
npx -y socialdatax-skills@latest bilibili user-dynamics --profile-url "<profile_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest bilibili download --url "<bilibili_video_url_or_share_text>" --output-dir ./downloads --pretty
npx -y socialdatax-skills@latest weibo hot-search --pretty
npx -y socialdatax-skills@latest weibo search --keyword "露营" --pretty
npx -y socialdatax-skills@latest weibo detail --post-id "<post_id>" --pretty
npx -y socialdatax-skills@latest weibo detail --post-url "<weibo_post_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest weibo comments --post-id "<post_id>" --pretty
npx -y socialdatax-skills@latest weibo comments --post-id "<post_id>" --all --include-replies --pretty
npx -y socialdatax-skills@latest weibo comments --post-url "<weibo_post_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest weibo replies --post-id "<post_id>" --comment-id "<comment_id>" --pretty
npx -y socialdatax-skills@latest weibo likers --post-id "<post_id>" --pretty
npx -y socialdatax-skills@latest weibo reposts --post-id "<post_id>" --pretty
npx -y socialdatax-skills@latest weibo user-info --user-id "<user_id>" --pretty
npx -y socialdatax-skills@latest weibo user-info --profile-url "<profile_url>" --pretty
npx -y socialdatax-skills@latest weibo user-posts --user-id "<user_id>" --pretty
npx -y socialdatax-skills@latest weibo user-posts --profile-url "<profile_url>" --pretty
npx -y socialdatax-skills@latest weibo transcript --post-url "<weibo_post_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest weibo transcript --post-id "<post_id>" --pretty
npx -y socialdatax-skills@latest weibo transcript --job-id "<job_id>" --pretty
npx -y socialdatax-skills@latest weibo download-media --url "<weibo_media_url>" --output-dir ./downloads --pretty
npx -y socialdatax-skills@latest wechat hot-search --pretty
npx -y socialdatax-skills@latest wechat search --keyword "露营" --pretty
npx -y socialdatax-skills@latest wechat detail --encrypted-object-id "<encrypted_object_id>" --pretty
npx -y socialdatax-skills@latest wechat detail --url "<wechat_work_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest wechat decrypt-media --media-url "<video.video_url>" --output video.mp4
npx -y socialdatax-skills@latest wechat article --url "<mp_article_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest wechat comments --object-id "<object_id>" --object-nonce-id "<object_nonce_id>" --pretty
npx -y socialdatax-skills@latest wechat comments --object-id "<object_id>" --object-nonce-id "<object_nonce_id>" --all --include-replies --pretty
npx -y socialdatax-skills@latest wechat comments --url "<wechat_video_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest wechat replies --object-id "<object_id>" --object-nonce-id "<object_nonce_id>" --comment-id "<comment_id>" --pretty
npx -y socialdatax-skills@latest wechat user-info --user-id "<v2_finder_user_id>" --pretty
npx -y socialdatax-skills@latest wechat user-info --url "<wechat_work_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest wechat user-posts --user-id "<v2_finder_user_id>" --pretty
npx -y socialdatax-skills@latest wechat user-posts --url "<wechat_work_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest wechat transcript --url "<wechat_video_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest wechat transcript --encrypted-object-id "<encrypted_object_id>" --pretty
npx -y socialdatax-skills@latest wechat transcript --job-id "<job_id>" --pretty
npx -y socialdatax-skills@latest zhihu hot-list --pretty
npx -y socialdatax-skills@latest zhihu search --keyword "露营" --pretty
npx -y socialdatax-skills@latest zhihu detail --content-url "<zhihu_content_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest zhihu comments --content-url "<zhihu_content_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest zhihu replies --content-url "<zhihu_content_url_or_share_text>" --comment-id "<comment_id>" --pretty
npx -y socialdatax-skills@latest zhihu user-info --profile-url "<profile_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest zhihu user-posts --profile-url "<profile_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest instagram search --keyword "camping" --pretty
npx -y socialdatax-skills@latest instagram detail --post-id "<post_id>" --pretty
npx -y socialdatax-skills@latest instagram detail --post-url "<instagram_post_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest instagram comments --post-url "<instagram_post_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest instagram replies --post-id "<post_id>" --comment-id "<comment_id>" --pretty
npx -y socialdatax-skills@latest instagram user-info --username "<username>" --pretty
npx -y socialdatax-skills@latest instagram user-info --profile-url "<profile_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest instagram user-posts --username "<username>" --pretty
npx -y socialdatax-skills@latest instagram user-posts --profile-url "<profile_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest x search --keyword "camping" --pretty
npx -y socialdatax-skills@latest x detail --post-id "<post_id>" --pretty
npx -y socialdatax-skills@latest x detail --post-url "<x_post_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest x comments --post-id "<post_id>" --pretty
npx -y socialdatax-skills@latest x comments --post-url "<x_post_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest x replies --post-id "<post_id>" --comment-id "<comment_id>" --pretty
npx -y socialdatax-skills@latest x user-info --user-id "<user_id>" --pretty
npx -y socialdatax-skills@latest x user-info --username "<username>" --pretty
npx -y socialdatax-skills@latest x user-info --profile-url "<profile_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest x user-posts --user-id "<user_id>" --pretty
npx -y socialdatax-skills@latest x user-posts --username "<username>" --pretty
npx -y socialdatax-skills@latest x user-posts --profile-url "<profile_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest x download-media --url "<x_media_url>" --output-dir ./downloads --pretty
npx -y socialdatax-skills@latest youtube search --keyword "camping" --pretty
npx -y socialdatax-skills@latest youtube detail --url "<youtube_video_url>" --pretty
npx -y socialdatax-skills@latest youtube comments --url "<youtube_video_url>" --pretty
npx -y socialdatax-skills@latest youtube replies --reply-token "<reply_token>" --pretty
npx -y socialdatax-skills@latest youtube channel-info --channel-url "<youtube_channel_url>" --pretty
npx -y socialdatax-skills@latest youtube user-posts --channel-url "<youtube_channel_url>" --pretty
npx -y socialdatax-skills@latest tiktok search --keyword "camping" --pretty
npx -y socialdatax-skills@latest tiktok detail --url "<tiktok_post_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest tiktok comments --post-id "<post_id>" --pretty
npx -y socialdatax-skills@latest tiktok comments --url "<tiktok_post_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest tiktok replies --post-id "<post_id>" --comment-id "<comment_id>" --pretty
npx -y socialdatax-skills@latest tiktok user-info --tiktok-id "<tiktok_id>" --pretty
npx -y socialdatax-skills@latest tiktok user-info --profile-url "<profile_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest tiktok user-posts --tiktok-id "<tiktok_id>" --pretty
npx -y socialdatax-skills@latest tiktok user-posts --profile-url "<profile_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest sensitive-check text --text "<content>" --platform xhs --pretty

Most direct CLI commands print a JSON envelope with platform, tool, arguments, and data. sensitive-check prints platform, tool, and data only; it does not echo the original text in CLI output. wechat decrypt-media is a local save command: pass the video.video_url returned by WeChat detail and an --output file path. It saves the media locally, decrypts when needed, and does not require SOCIALDATAX_API_KEY. xhs/douyin/kuaishou/weibo download-media is also local: pass one media URL returned by detail and either --output <file> or --output-dir <directory>. x download-media accepts one X media URL returned by search or detail. These local commands write through a .part file, resume partial downloads when the server supports range requests, skip an already existing output file, and infer common image/video/audio extensions in --output-dir mode. X / Twitter media URLs are served from overseas CDN domains such as pbs.twimg.com and video.twimg.com; if the local download times out, make the CLI process use a proxy with --proxy "http://127.0.0.1:7890" or HTTP_PROXY / HTTPS_PROXY / ALL_PROXY, then retry.

For transcript commands, the direct CLI tries to deliver the final result in one run: submit may wait up to 240 seconds, and if data.is_terminal is not true, the CLI automatically continues matching get-job requests for up to 1200 seconds by default, with each get-job request waiting up to 240 seconds. Use positive --max-wait-seconds <seconds> to tune that follow-up window. Do not submit a duplicate transcript job just to poll status.

bilibili download calls SocialDataX once to fetch short-lived download links, then downloads video and audio tracks on the local machine and merges them with local ffmpeg. Set SOCIALDATAX_API_KEY, install ffmpeg, and pass either --output <file> or --output-dir <directory>. The download-links request consumes 10 credits; the local track download and merge do not consume additional SocialDataX credits. Use --ffmpeg-path <path> when ffmpeg is not on PATH, and --keep-tracks to retain the separate track files after merge.

For XHS outputs with a returned note_url field, when note_url is non-null, preserve it exactly as the full URL, including xsec_token query parameters, such as in final answers or display. Do not modify, truncate, redact, normalize, rebuild, or replace it with a link assembled from note_id. If note_url is null, do not synthesize a public link from note_id.

For list-style commands, use --pages <n> to fetch N pages from the current starting point and --max-items <n> to cap the merged data.items output. Search commands support --pages but not --all, because search has no stable complete-result boundary.

Use --since-days <1-365> only on XHS, Douyin, Kuaishou, Weibo, and WeChat Channels search and creator content-list commands. For Bilibili video search, Zhihu search, and YouTube search, use the documented publish-time filters instead; Instagram, X / Twitter, TikTok, and Bilibili article search do not expose a recent-window CLI option.

For comments, replies, creator content lists, and Douyin creator series, use --all to continue until the returned next_page_token is empty. --all has no default item or page cap; add --max-items <n> or use --pages <n> when you want a bounded run.

For XHS, Douyin, Kuaishou, Weibo, and WeChat Channels first-level comments, add --include-replies to fetch the second-level replies under each returned first-level comment. Multi-page output keeps data.items as the merged first-level list; each item gets replies, replies_page_count, and replies_next_page_token.

For commands that accept --page-token, continue only with the complete returned next_page_token from the same pagination chain. Do not modify, truncate, redact, mask, omit, normalize, rebuild, generate, or replace the middle with ellipses.

Search pagination uses --page-token when continuing with a returned next_page_token. Omit --page-token on the first search request and pass the complete returned next_page_token only when continuing the same search chain.

Transcript commands submit a bounded video speech-to-text job or check an existing job. Pass exactly one entrypoint for each call: URL/share text, platform content ID, or --job-id. Direct CLI transcript commands wait and poll the same job by default; completed get-job responses return transcript plus content context, not summary.

Generated Agent Skill examples include --source-client socialdatax-skills --source-platform <marketplace> --source-skill <skill-slug> so SocialDataX can attribute authenticated direct data CLI usage to the current marketplace Skill. Keep those values unchanged when running commands from a Skill; omit them for ad hoc CLI use. Authenticated direct data CLI commands also accept SOCIALDATAX_SOURCE_CLIENT, SOCIALDATAX_SOURCE_PLATFORM, and SOCIALDATAX_SOURCE_SKILL as environment-variable fallbacks.

Search commands for XHS, Douyin, Kuaishou, Bilibili, Zhihu, Instagram, X / Twitter, YouTube, TikTok, Weibo, and WeChat Channels use --keyword and optional --page-token. Kuaishou work search uses kuaishou search --keyword and optional --page-token; Kuaishou creator search uses kuaishou user-search --keyword and optional --page-token. Kuaishou search does not accept Douyin semantic filters, and kuaishou user-search does not support --since-days. Bilibili video search uses bilibili search-videos --keyword; Bilibili article search uses bilibili search-articles --keyword. YouTube reply pagination starts from the returned first-level comment reply_token; use youtube replies --reply-token "<reply_token>", not --comment-id.

XHS comments accept optional --sort-type values: default, time_descending, and like_count_descending; omit it for the platform default comment order. Bilibili and YouTube comments accept optional --sort-type values: hot and time_descending; Zhihu comments accept default and time_descending. Omit comment sort values for the platform default order.

Douyin search filters use semantic values: --sort-type supports general, time_descending, and like_count_descending; --publish-time-range supports all, day, week, and half_year; --duration-range supports all, under_1_minute, one_to_five_minutes, and over_5_minutes; --content-type supports all, video, and image.

WeChat Channels search filters use semantic values: --sort-type supports all, time_descending, and collect_count_descending; collect_count_descending means hottest first / most collected first. --duration-range supports all, under_5_min, between_5_and_20_min, and over_20_min.

Bilibili search filters use semantic values. Video --sort-type supports general, view_count_descending, time_descending, danmaku_count_descending, and collect_count_descending; article --sort-type supports general, time_descending, view_count_descending, like_count_descending, and comment_count_descending. Bilibili creator videos accept optional --sort-type values: time_descending, view_count_descending, and collect_count_descending; omit it for the default creator video-list order.

Runtime Requirements

Recommended: Node.js 22 LTS or newer.
Minimum: Node.js 20.18.1.
Node.js 18 and older are not supported.
Local Bilibili download merge requires ffmpeg on PATH or --ffmpeg-path <path>.

Environment

SOCIALDATAX_API_KEY Required for direct CLI data calls and hosted MCP calls. Local inspection commands such as list, doctor, and install --dry-run do not require a key.

Security & Privacy

You can inspect the package safety summary before installing:

npx -y socialdatax-skills@latest doctor
npx -y socialdatax-skills@latest doctor --json

The public package declares no npm lifecycle scripts such as preinstall, install, or postinstall. The installer copies Skill files only, does not save API keys, and does not change MCP server configuration. Authenticated data calls require SOCIALDATAX_API_KEY at runtime, do not read local browser data, and do not perform account actions.

Platform Names

This project is not affiliated with, endorsed by, or sponsored by Xiaohongshu, RedNote, Douyin, Kuaishou, Kwai, Bilibili, Weibo, WeChat, WeChat Channels, Zhihu, Instagram, X / Twitter, YouTube, TikTok, or their affiliates. Platform names are used only to describe supported data sources.

Local Source Run

npm install
SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" node cli.mjs xhs search --keyword "露营" --pretty
SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" node cli.mjs douyin search --keyword "露营" --pretty
SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" node cli.mjs kuaishou search --keyword "露营" --pretty
SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" node cli.mjs bilibili search-videos --keyword "露营" --pretty
SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" node cli.mjs weibo search --keyword "露营" --pretty
SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" node cli.mjs wechat search --keyword "露营" --pretty
SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" node cli.mjs zhihu search --keyword "露营" --pretty
SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" node cli.mjs instagram search --keyword "camping" --pretty
SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" node cli.mjs x search --keyword "camping" --pretty
SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" node cli.mjs youtube search --keyword "camping" --pretty
SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" node cli.mjs tiktok search --keyword "camping" --pretty
SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" node cli.mjs sensitive-check text --text "<content>" --platform xhs --pretty

Docker Run

docker build -t socialdatax-skills .
docker run --rm -i -e SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" socialdatax-skills xhs search --keyword "露营" --pretty
docker run --rm -i -e SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" socialdatax-skills douyin search --keyword "露营" --pretty
docker run --rm -i -e SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" socialdatax-skills kuaishou search --keyword "露营" --pretty
docker run --rm -i -e SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" socialdatax-skills bilibili search-videos --keyword "露营" --pretty
docker run --rm -i -e SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" socialdatax-skills weibo search --keyword "露营" --pretty
docker run --rm -i -e SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" socialdatax-skills wechat search --keyword "露营" --pretty
docker run --rm -i -e SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" socialdatax-skills zhihu search --keyword "露营" --pretty
docker run --rm -i -e SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" socialdatax-skills instagram search --keyword "camping" --pretty
docker run --rm -i -e SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" socialdatax-skills x search --keyword "camping" --pretty
docker run --rm -i -e SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" socialdatax-skills youtube search --keyword "camping" --pretty
docker run --rm -i -e SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" socialdatax-skills tiktok search --keyword "camping" --pretty
docker run --rm -i -e SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" socialdatax-skills sensitive-check text --text "<content>" --platform xhs --pretty

If Docker Hub is slow from your network, keep the default image unchanged for normal use and override only during local builds:

docker build --build-arg NODE_IMAGE=mirror.gcr.io/library/node:22-alpine -t socialdatax-skills .

Skill Installer

The npm package also ships separate skills for each major capability. Different clients can install one skill, several skills, or all skills into their expected directory:

npx -y socialdatax-skills@latest list
npx -y socialdatax-skills@latest doctor
npx -y socialdatax-skills@latest install --target openclaw
npx -y socialdatax-skills@latest install --target openclaw --dry-run
npx -y socialdatax-skills@latest install socialdatax-content-research-assistant --target openclaw
npx -y socialdatax-skills@latest install media-search --target openclaw
npx -y socialdatax-skills@latest install media-search --target openclaw --dry-run
npx -y socialdatax-skills@latest install media-user-info --target openclaw
npx -y socialdatax-skills@latest install media-comments media-detail --target openclaw
npx -y socialdatax-skills@latest install media-transcript --target openclaw
npx -y socialdatax-skills@latest install media-search --target openclaw --scope workspace
npx -y socialdatax-skills@latest install media-search --target hermes
npx -y socialdatax-skills@latest install media-search --target hermes --scope shared
npx -y socialdatax-skills@latest install media-search --target agents
npx -y socialdatax-skills@latest install media-search --target codex
npx -y socialdatax-skills@latest install media-search --target codex --scope workspace
npx -y socialdatax-skills@latest install media-search --target claude-code
npx -y socialdatax-skills@latest install media-search --target claude-code --scope workspace
npx -y socialdatax-skills@latest install --path ~/.workbuddy/skills/
npx -y socialdatax-skills@latest install media-search --path ~/.workbuddy/skills/media-search
npx -y socialdatax-skills@latest xhs search --keyword "露营" --pretty
npx -y socialdatax-skills@latest xhs hot-search --pretty
npx -y socialdatax-skills@latest xhs transcript --url "<note_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest douyin hot-search --pretty
npx -y socialdatax-skills@latest douyin search --keyword "露营" --pretty
npx -y socialdatax-skills@latest douyin user-series --sec-user-id "<sec_user_id>" --pretty
npx -y socialdatax-skills@latest douyin transcript --aweme-id "<aweme_id>" --pretty
npx -y socialdatax-skills@latest douyin download-media --url "<douyin_media_url>" --output-dir ./downloads --pretty
npx -y socialdatax-skills@latest kuaishou hot-search --pretty
npx -y socialdatax-skills@latest kuaishou search --keyword "露营" --pretty
npx -y socialdatax-skills@latest kuaishou transcript --photo-id "<photo_id>" --pretty
npx -y socialdatax-skills@latest kuaishou download-media --url "<kuaishou_media_url>" --output-dir ./downloads --pretty
npx -y socialdatax-skills@latest bilibili search-videos --keyword "露营" --pretty
npx -y socialdatax-skills@latest bilibili download --url "<bilibili_video_url_or_share_text>" --output-dir ./downloads --pretty
npx -y socialdatax-skills@latest weibo hot-search --pretty
npx -y socialdatax-skills@latest weibo search --keyword "露营" --pretty
npx -y socialdatax-skills@latest weibo transcript --post-id "<post_id>" --pretty
npx -y socialdatax-skills@latest weibo download-media --url "<weibo_media_url>" --output-dir ./downloads --pretty
npx -y socialdatax-skills@latest wechat hot-search --pretty
npx -y socialdatax-skills@latest wechat search --keyword "露营" --pretty
npx -y socialdatax-skills@latest wechat article --url "<mp_article_url_or_share_text>" --pretty
npx -y socialdatax-skills@latest wechat transcript --encrypted-object-id "<encrypted_object_id>" --pretty
npx -y socialdatax-skills@latest zhihu search --keyword "露营" --pretty
npx -y socialdatax-skills@latest instagram search --keyword "camping" --pretty
npx -y socialdatax-skills@latest x search --keyword "camping" --pretty
npx -y socialdatax-skills@latest x download-media --url "<x_media_url>" --output-dir ./downloads --pretty
npx -y socialdatax-skills@latest youtube search --keyword "camping" --pretty
npx -y socialdatax-skills@latest tiktok search --keyword "camping" --pretty
npx -y socialdatax-skills@latest sensitive-check text --text "<content>" --platform xhs --pretty

Use --path for clients that expect a direct Skills directory. When installing all skills, --path is the parent directory; when installing one skill, --path is that skill's destination directory.

Available skills:

socialdatax-content-research-assistant: combine SocialDataX search, detail, comment, creator profile, and creator content workflows for cross-platform content research across XHS, Douyin, Kuaishou, Bilibili, Weibo, WeChat Channels, Zhihu, Instagram, X / Twitter, YouTube, and TikTok; also reads WeChat Official Account article link details.
media-search: search social media content by keyword; supports XHS notes, Douyin works, Kuaishou works, Bilibili videos/articles, Weibo posts, WeChat Channels videos, Zhihu content, Instagram posts, X / Twitter posts, YouTube videos, and TikTok posts.
media-detail: read WeChat Official Account article details and body text from article links. Read structured content details and metrics for XHS notes, Douyin works, Kuaishou works, Bilibili content, Weibo posts, WeChat Channels videos and image posts, Zhihu content, Instagram posts, X / Twitter posts, YouTube videos, and TikTok posts.
media-comments: fetch and analyze comments/replies for XHS, Douyin, Kuaishou, Bilibili, Weibo, WeChat Channels, Zhihu, Instagram, X / Twitter, YouTube, and TikTok.
media-transcript: submit and check video 口播转文字 / speech-to-text transcript jobs; supports XHS, Douyin, Kuaishou, Weibo, and WeChat Channels through direct CLI commands or hosted MCP tools, plus Bilibili, Zhihu independent videos and video answers, Instagram regular video posts/Reels, X / Twitter video posts, TikTok, and YouTube through hosted MCP tools. Instagram photo and carousel posts and Zhihu plain answers without video are not processable.
media-user-info: retrieve creator profile information; supports XHS, Douyin, Kuaishou, Bilibili, Weibo, WeChat Channels, Zhihu, Instagram, X / Twitter, YouTube channels, and TikTok creators.
media-user-posts: retrieve creator content lists; supports XHS notes, Douyin works, Kuaishou works, Bilibili videos/articles/dynamics, Weibo posts, WeChat Channels videos and image posts, Zhihu creator articles, Instagram posts, X / Twitter posts, YouTube channel videos/Shorts, TikTok posts, and Douyin creator short-drama series.
sensitive-check: run 敏感词检测 / 违禁词检查 text checks; supports generic, xhs, douyin, and kuaishou platform contexts.

Default install locations:

OpenClaw: ~/.openclaw/workspace/skills/<skill-name> or OPENCLAW_SKILLS_DIR/<skill-name>
OpenClaw workspace scope: ./skills/<skill-name>
Hermes Agent: ~/.hermes/skills/<skill-name>
Hermes shared scope: ~/.agents/skills/<skill-name>
Shared AgentSkills directory: ~/.agents/skills/<skill-name>
Codex: ~/.codex/skills/<skill-name>
Codex workspace scope: ./.codex/skills/<skill-name>
Claude Code: ~/.claude/skills/<skill-name>
Claude Code workspace scope: ./.claude/skills/<skill-name>
WorkBuddy: use --path with the Skills directory supported by your current WorkBuddy client, for example npx -y socialdatax-skills@latest install --path ~/.workbuddy/skills/

If no skill name is provided, all skills are installed. If a destination already exists, re-run with --force to replace an existing directory for the same skill. Use --path <directory> to install one skill to a custom directory, or multiple skills under a custom parent directory. The shared scope is only meaningful for --target hermes; use --target agents for the shared AgentSkills directory directly.

Workflow Scope

The current direct CLI and hosted MCP services are designed for social media content intelligence workflows. Some commands read public content directly; some submit bounded analysis jobs such as video speech-to-text transcript. They do not provide account login, posting, editing, liking, commenting, or other account actions.

Current XHS workflows include:

Fetch the current Xiaohongshu / XHS / RedNote search hot list.
Search related Xiaohongshu notes by keyword, with optional sort, note type, and publish-time filters.
Resolve a shared note link, short link, or share text into structured note details.
Read note details when the caller already has a note ID.
Fetch paginated first-level comments for comment analysis.
Fetch paginated replies under a first-level comment.
Read creator profile data from a profile link, short link, share text, or user ID.
Fetch paginated creator note lists from a user ID, profile link, short link, or share text for content st

Socialdatax Skills

At a glance

README