socialdatax-skills 0.2.29 → 0.2.30

package/README.md

@@ -2,7 +2,7 @@
 
 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, 微博 / Weibo, 视频号 / WeChat Channels, and 微信公众号 / WeChat Official Account article content research and analysis workflows, plus XHS local media download, Bilibili / 哔哩哔哩 / B站 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.
+The current public tools support 小红书 / Xiaohongshu / XHS / RedNote, 抖音 / Douyin, 快手 / Kuaishou / Kwai, 微博 / Weibo, 视频号 / WeChat Channels, and 微信公众号 / WeChat Official Account article content research and analysis workflows, plus XHS / Douyin / Kuaishou / Weibo local media download, Bilibili / 哔哩哔哩 / B站 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
@@ -10,6 +10,10 @@ The current public tools support 小红书 / Xiaohongshu / XHS / RedNote, 抖音
 
 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; platform MCPs are published separately.
 
+## High-Intent Skill Catalog
+
+See [CATALOG.md](./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, comment analysis, hot topic planning, viral note research, Douyin transcript extraction, and sensitive term checks.
+
 ## Search Aliases
 
 Common search phrases for this skill package:
@@ -82,7 +86,7 @@ Common search phrases for this skill package:
 - Sensitive Words Check MCP server name: `sensitive-check`
 - Sensitive Words Check future MCP registry name: `com.socialdatax/sensitive-check`
 - Unified MCP registry name: none; this package installs skills and calls explicit platform services.
-- Current public capability version: `0.2.29`
+- Current public capability version: `0.2.30`
 
 ## Direct CLI
 
@@ -121,6 +125,7 @@ npx -y socialdatax-skills@latest douyin user-series --profile-url "<profile_url_
 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
@@ -137,6 +142,7 @@ npx -y socialdatax-skills@latest kuaishou user-posts --profile-url "<profile_url
 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 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
@@ -155,6 +161,7 @@ npx -y socialdatax-skills@latest weibo user-posts --profile-url "<profile_url_or
 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
@@ -174,7 +181,7 @@ npx -y socialdatax-skills@latest wechat transcript --job-id "<job_id>" --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 download-media` is also local: pass one image or video media URL returned by XHS detail and either `--output <file>` or `--output-dir <directory>`. It writes through a `.part` file, resumes partial downloads when the server supports range requests, skips an already existing output file, and infers common image/video extensions in `--output-dir` mode.
+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>`. It writes through a `.part` file, resumes partial downloads when the server supports range requests, skips an already existing output file, and infers common image/video/audio extensions in `--output-dir` mode.
 
 For transcript commands, the direct CLI tries to deliver the final result in one run: submit may wait up to 210 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.
 
@@ -306,13 +313,16 @@ 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 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
@@ -360,6 +370,7 @@ Current XHS workflows include:
 - 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 style and account research.
 - Submit and check video note 口播转文字 / speech-to-text transcript jobs; submit tools 提交后最多等待 210 秒，未完成时继续查询同一个 job_id 直到终态.
+- Save returned `image_items[].image_url`, `image_items[].live_photo.video_url`, or `video.video_url` media links locally with `xhs download-media`.
 
 Current Kuaishou workflows include:
 
@@ -373,6 +384,7 @@ Current Kuaishou workflows include:
 - Read creator profile data from a non-empty user_id, profile link, short link, or share text. Live/fw-user profile shares are supported for profile data; successful results return a reusable non-empty user_id.
 - Fetch paginated creator work lists from a non-empty user_id, or from a profile link, short link, or share text that resolves directly to a non-empty user_id. For live/fw-user profile shares, call creator profile first and use the returned non-empty user_id.
 - Submit and check video work 口播转文字 / speech-to-text transcript jobs; submit tools 提交后最多等待 210 秒，未完成时继续查询同一个 job_id 直到终态.
+- Save returned `images[].url`, `video.play_url`, or `cover_image_url` media links locally with `kuaishou download-media`.
 
 Current Bilibili workflows include:
 
@@ -392,6 +404,7 @@ Current Douyin workflows include:
 - Fetch paginated creator work lists from a sec_user_id, profile link, short link, or share text.
 - Fetch paginated creator short-drama series lists from a sec_user_id, profile link, short link, or share text.
 - Submit and check video work 口播转文字 / speech-to-text transcript jobs; submit tools 提交后最多等待 210 秒，未完成时继续查询同一个 job_id 直到终态.
+- Save returned `images[].url`, `images[].live_photo.play_url`, `video.play_url`, `music.play_url`, or `cover_image_url` media links locally with `douyin download-media`.
 
 Current Weibo workflows include:
 
@@ -404,6 +417,7 @@ Current Weibo workflows include:
 - Read creator profile data from a profile link, short link, share text, or user_id.
 - Fetch paginated creator post lists from a user_id, profile link, short link, or share text.
 - Submit and check Weibo video 口播转文字 / speech-to-text transcript jobs; submit tools 提交后最多等待 210 秒，未完成时继续查询同一个 job_id 直到终态.
+- Save returned `image_urls[]` or `video.video_url` media links locally with `weibo download-media`.
 
 Current WeChat / 微信 workflows include:
 

package/cli.mjs

@@ -16,13 +16,13 @@ import {
   assertBilibiliFfmpegAvailable,
   downloadBilibiliVideoFromManifest,
 } from "./lib/media/bilibili-download.mjs";
+import { downloadPlatformMediaFromUrl } from "./lib/media/platform-download.mjs";
 import { decryptWechatMediaCommand } from "./lib/media/wechat-decrypt.mjs";
-import { downloadXhsMediaFromUrl } from "./lib/media/xhs-download.mjs";
 
 export { decryptWechatMediaCommand };
 
 const PACKAGE_NAME = "socialdatax-skills";
-const PACKAGE_VERSION = "0.2.29";
+const PACKAGE_VERSION = "0.2.30";
 const PACKAGE_SPEC = `${PACKAGE_NAME}@latest`;
 const LOG_PREFIX = `[${PACKAGE_NAME}]`;
 const MIN_NODE_VERSION = "20.18.1";
@@ -261,6 +261,7 @@ const DOUYIN_DIRECT_ACTION_OPTIONS = {
   ],
   "user-series": ["secUserId", "profileUrl", "pageToken", "pages", "all", "maxItems", "pretty"],
   transcript: ["url", "awemeId", "jobId", "maxWaitSeconds", "pretty"],
+  "download-media": ["url", "output", "outputDir", "pretty"],
 };
 const DOUYIN_DIRECT_ACTION_NAMES = Object.keys(DOUYIN_DIRECT_ACTION_OPTIONS).join(", ");
 const DOUYIN_SEARCH_SORT_TYPES = ["general", "time_descending", "like_count_descending"];
@@ -291,6 +292,8 @@ const DOUYIN_OPTION_DISPLAY_NAMES = {
   secUserId: "--sec-user-id",
   jobId: "--job-id",
   maxWaitSeconds: "--max-wait-seconds",
+  output: "--output",
+  outputDir: "--output-dir",
 };
 const KUAISHOU_DIRECT_ACTION_OPTIONS = {
   "hot-search": ["pretty"],
@@ -329,6 +332,7 @@ const KUAISHOU_DIRECT_ACTION_OPTIONS = {
     "pretty",
   ],
   transcript: ["url", "photoId", "jobId", "maxWaitSeconds", "pretty"],
+  "download-media": ["url", "output", "outputDir", "pretty"],
 };
 const KUAISHOU_DIRECT_ACTION_NAMES = Object.keys(KUAISHOU_DIRECT_ACTION_OPTIONS).join(", ");
 const KUAISHOU_OPTION_DISPLAY_NAMES = {
@@ -346,6 +350,8 @@ const KUAISHOU_OPTION_DISPLAY_NAMES = {
   userId: "--user-id",
   jobId: "--job-id",
   maxWaitSeconds: "--max-wait-seconds",
+  output: "--output",
+  outputDir: "--output-dir",
 };
 const BILIBILI_DIRECT_ACTION_OPTIONS = {
   download: ["url", "output", "outputDir", "ffmpegPath", "keepTracks", "pretty"],
@@ -395,6 +401,7 @@ const WEIBO_DIRECT_ACTION_OPTIONS = {
     "pretty",
   ],
   transcript: ["postUrl", "postId", "jobId", "maxWaitSeconds", "pretty"],
+  "download-media": ["url", "output", "outputDir", "pretty"],
 };
 const WEIBO_DIRECT_ACTION_NAMES = Object.keys(WEIBO_DIRECT_ACTION_OPTIONS).join(", ");
 const WEIBO_OPTION_DISPLAY_NAMES = {
@@ -412,6 +419,9 @@ const WEIBO_OPTION_DISPLAY_NAMES = {
   userId: "--user-id",
   jobId: "--job-id",
   maxWaitSeconds: "--max-wait-seconds",
+  url: "--url",
+  output: "--output",
+  outputDir: "--output-dir",
 };
 const WECHAT_DIRECT_ACTION_OPTIONS = {
   "hot-search": ["pretty"],
@@ -1107,6 +1117,32 @@ function validateFlagOption(options, key, displayName) {
   }
 }
 
+function validateDownloadMediaDirectActionOptions(
+  platform,
+  options,
+  allowedOptions,
+  displayNames
+) {
+  validateKnownOptions(options, allowedOptions);
+  validateFlagOption(options, "pretty", "--pretty");
+  for (const key of allowedOptions) {
+    if (!DIRECT_BOOLEAN_OPTIONS.has(key)) {
+      requireOptionValue(options, key, displayNames[key]);
+    }
+  }
+  if (!options.url) {
+    throw new Error(`Missing --url for ${platform} download-media.`);
+  }
+  if (!options.output && !options.outputDir) {
+    throw new Error(`Missing --output or --output-dir for ${platform} download-media.`);
+  }
+  if (options.output && options.outputDir) {
+    throw new Error(
+      `Use only one of --output or --output-dir for ${platform} download-media.`
+    );
+  }
+}
+
 function validateXhsDirectActionOptions(action, options) {
   const allowedOptions = XHS_DIRECT_ACTION_OPTIONS[action];
   if (!allowedOptions) {
@@ -1114,22 +1150,12 @@ function validateXhsDirectActionOptions(action, options) {
   }
 
   if (action === "download-media") {
-    validateKnownOptions(options, allowedOptions);
-    validateFlagOption(options, "pretty", "--pretty");
-    for (const key of allowedOptions) {
-      if (!DIRECT_BOOLEAN_OPTIONS.has(key)) {
-        requireOptionValue(options, key, XHS_OPTION_DISPLAY_NAMES[key]);
-      }
-    }
-    if (!options.url) {
-      throw new Error("Missing --url for xhs download-media.");
-    }
-    if (!options.output && !options.outputDir) {
-      throw new Error("Missing --output or --output-dir for xhs download-media.");
-    }
-    if (options.output && options.outputDir) {
-      throw new Error("Use only one of --output or --output-dir for xhs download-media.");
-    }
+    validateDownloadMediaDirectActionOptions(
+      "xhs",
+      options,
+      allowedOptions,
+      XHS_OPTION_DISPLAY_NAMES
+    );
     return;
   }
 
@@ -1150,6 +1176,16 @@ function validateDouyinDirectActionOptions(action, options) {
     return;
   }
 
+  if (action === "download-media") {
+    validateDownloadMediaDirectActionOptions(
+      "douyin",
+      options,
+      allowedOptions,
+      DOUYIN_OPTION_DISPLAY_NAMES
+    );
+    return;
+  }
+
   validateKnownOptions(options, allowedDirectOptions(allowedOptions));
   validateDirectMetaOptions(options);
   validateDirectPaginationOptions("douyin", action, options);
@@ -1167,6 +1203,16 @@ function validateKuaishouDirectActionOptions(action, options) {
     return;
   }
 
+  if (action === "download-media") {
+    validateDownloadMediaDirectActionOptions(
+      "kuaishou",
+      options,
+      allowedOptions,
+      KUAISHOU_OPTION_DISPLAY_NAMES
+    );
+    return;
+  }
+
   validateKnownOptions(options, allowedDirectOptions(allowedOptions));
   validateDirectMetaOptions(options);
   validateDirectPaginationOptions("kuaishou", action, options);
@@ -1212,6 +1258,16 @@ function validateWeiboDirectActionOptions(action, options) {
     return;
   }
 
+  if (action === "download-media") {
+    validateDownloadMediaDirectActionOptions(
+      "weibo",
+      options,
+      allowedOptions,
+      WEIBO_OPTION_DISPLAY_NAMES
+    );
+    return;
+  }
+
   validateKnownOptions(options, allowedDirectOptions(allowedOptions));
   validateDirectMetaOptions(options);
   validateDirectPaginationOptions("weibo", action, options);
@@ -1944,6 +2000,9 @@ function printHelp() {
   console.log(`  npx -y ${PACKAGE_SPEC} douyin transcript --aweme-id "<aweme_id>" --pretty`);
   console.log("      Submit or check a Douyin video speech-to-text transcript job.");
   console.log("");
+  console.log(`  npx -y ${PACKAGE_SPEC} douyin download-media --url "<douyin_media_url>" --output-dir ./downloads --pretty`);
+  console.log("      Save one Douyin media URL returned by detail to a local file.");
+  console.log("");
   console.log(`  npx -y ${PACKAGE_SPEC} kuaishou hot-search --pretty`);
   console.log("      Call the Kuaishou hot-search list tool directly and print JSON.");
   console.log("");
@@ -1990,6 +2049,9 @@ function printHelp() {
   console.log(`  npx -y ${PACKAGE_SPEC} kuaishou transcript --photo-id "<photo_id>" --pretty`);
   console.log("      Submit or check a Kuaishou video speech-to-text transcript job.");
   console.log("");
+  console.log(`  npx -y ${PACKAGE_SPEC} kuaishou download-media --url "<kuaishou_media_url>" --output-dir ./downloads --pretty`);
+  console.log("      Save one Kuaishou media URL returned by detail to a local file.");
+  console.log("");
   console.log(`  npx -y ${PACKAGE_SPEC} bilibili download --url "<bilibili_video_url_or_share_text>" --output-dir ./downloads --pretty`);
   console.log("      Fetch Bilibili download links, save DASH tracks locally, and merge them with ffmpeg.");
   console.log("");
@@ -2035,6 +2097,9 @@ function printHelp() {
   console.log(`  npx -y ${PACKAGE_SPEC} weibo transcript --post-url "<weibo_post_url_or_share_text>" --pretty`);
   console.log("      Submit or check a Weibo video speech-to-text transcript job.");
   console.log("");
+  console.log(`  npx -y ${PACKAGE_SPEC} weibo download-media --url "<weibo_media_url>" --output-dir ./downloads --pretty`);
+  console.log("      Save one Weibo image or video media URL returned by detail to a local file.");
+  console.log("");
   console.log(`  npx -y ${PACKAGE_SPEC} wechat hot-search --pretty`);
   console.log("      Call the WeChat Channels / 视频号 hot-search list tool directly and print JSON.");
   console.log("");
@@ -2146,14 +2211,14 @@ function printHelp() {
   console.log("  --keyword <text>");
   console.log("  --url <url-or-share-text>");
   console.log("      Content link, short link, or share text for URL-based detail/comment/article commands.");
-  console.log("      For xhs download-media, pass one image or video media URL returned by XHS detail.");
+  console.log("      For xhs/douyin/kuaishou/weibo download-media, pass one media URL returned by detail.");
   console.log("      For Douyin detail/comments, pass a content page link, not video.play_url.");
   console.log("  --media-url <video.video_url>");
   console.log("      WeChat detail result media URL for local decrypt-media download.");
   console.log("  --output <file>");
-  console.log("      Output file path for local decrypt-media, XHS download-media, or Bilibili download.");
+  console.log("      Output file path for local decrypt-media, download-media, or Bilibili download.");
   console.log("  --output-dir <directory>");
-  console.log("      Directory for XHS download-media or Bilibili download output when --output is omitted.");
+  console.log("      Directory for download-media or Bilibili download output when --output is omitted.");
   console.log("  --ffmpeg-path <path>");
   console.log("      ffmpeg executable path for Bilibili download; defaults to ffmpeg.");
   console.log("  --keep-tracks");
@@ -2276,7 +2341,7 @@ async function runXhsDirectCommand(args) {
   validateXhsDirectActionOptions(action, options);
 
   if (action === "download-media") {
-    const data = await downloadXhsMediaFromUrl(options.url, options);
+    const data = await downloadPlatformMediaFromUrl("xhs", options.url, options);
     process.stdout.write(JSON.stringify(data, null, options.pretty ? 2 : 0));
     process.stdout.write("\n");
     return;
@@ -2311,6 +2376,13 @@ async function runDouyinDirectCommand(args) {
   }
   validateDouyinDirectActionOptions(action, options);
 
+  if (action === "download-media") {
+    const data = await downloadPlatformMediaFromUrl("douyin", options.url, options);
+    process.stdout.write(JSON.stringify(data, null, options.pretty ? 2 : 0));
+    process.stdout.write("\n");
+    return;
+  }
+
   const operation = attachDirectMetadata(buildDouyinOperation(action, options), options);
   const data = await callDirectOperationWithOptions(operation, options);
   const envelope = {
@@ -2340,6 +2412,13 @@ async function runKuaishouDirectCommand(args) {
   }
   validateKuaishouDirectActionOptions(action, options);
 
+  if (action === "download-media") {
+    const data = await downloadPlatformMediaFromUrl("kuaishou", options.url, options);
+    process.stdout.write(JSON.stringify(data, null, options.pretty ? 2 : 0));
+    process.stdout.write("\n");
+    return;
+  }
+
   const operation = attachDirectMetadata(buildKuaishouOperation(action, options), options);
   const data = await callDirectOperationWithOptions(operation, options);
   const envelope = {
@@ -2469,6 +2548,13 @@ async function runWeiboDirectCommand(args) {
   }
   validateWeiboDirectActionOptions(action, options);
 
+  if (action === "download-media") {
+    const data = await downloadPlatformMediaFromUrl("weibo", options.url, options);
+    process.stdout.write(JSON.stringify(data, null, options.pretty ? 2 : 0));
+    process.stdout.write("\n");
+    return;
+  }
+
   const operation = attachDirectMetadata(buildWeiboOperation(action, options), options);
   const data = await callDirectOperationWithOptions(operation, options);
   const envelope = {

package/lib/media/{xhs-download.mjs → platform-download.mjs}

@@ -20,12 +20,33 @@ import {
   writeAllToFile,
 } from "./common.mjs";
 
-const XHS_DOWNLOAD_USER_AGENT =
+const MEDIA_DOWNLOAD_USER_AGENT =
   "Mozilla/5.0 (compatible; SocialDataX/1.0; +https://socialdatax.com)";
-const XHS_DOWNLOAD_REFERER = "https://www.xiaohongshu.com/";
-const XHS_DOWNLOAD_MAX_ATTEMPTS = 10;
-const XHS_DOWNLOAD_RETRY_DELAY_MS = 250;
-const XHS_RETRYABLE_HTTP_STATUSES = new Set([
+const PLATFORM_MEDIA_DOWNLOAD_CONFIGS = {
+  xhs: {
+    platform: "xhs",
+    displayName: "XHS",
+    referer: "https://www.xiaohongshu.com/",
+  },
+  douyin: {
+    platform: "douyin",
+    displayName: "Douyin",
+    referer: "https://www.douyin.com/",
+  },
+  kuaishou: {
+    platform: "kuaishou",
+    displayName: "Kuaishou",
+    referer: "https://www.kuaishou.com/",
+  },
+  weibo: {
+    platform: "weibo",
+    displayName: "Weibo",
+    referer: "https://weibo.com/",
+  },
+};
+const MEDIA_DOWNLOAD_MAX_ATTEMPTS = 10;
+const MEDIA_DOWNLOAD_RETRY_DELAY_MS = 250;
+const MEDIA_RETRYABLE_HTTP_STATUSES = new Set([
   408,
   409,
   425,
@@ -35,8 +56,8 @@ const XHS_RETRYABLE_HTTP_STATUSES = new Set([
   503,
   504,
 ]);
-const XHS_EXPIRED_HTTP_STATUSES = new Set([403, 404, 410]);
-const XHS_CONTENT_TYPE_EXTENSIONS = new Map([
+const MEDIA_EXPIRED_HTTP_STATUSES = new Set([403, 404, 410]);
+const MEDIA_CONTENT_TYPE_EXTENSIONS = new Map([
   ["image/jpeg", "jpg"],
   ["image/jpg", "jpg"],
   ["image/png", "png"],
@@ -44,8 +65,9 @@ const XHS_CONTENT_TYPE_EXTENSIONS = new Map([
   ["image/heif", "heif"],
   ["image/heic", "heic"],
   ["video/mp4", "mp4"],
+  ["audio/mp4", "m4a"],
 ]);
-const XHS_URL_FORMAT_EXTENSIONS = new Map([
+const MEDIA_URL_FORMAT_EXTENSIONS = new Map([
   ["jpg", "jpg"],
   ["jpeg", "jpg"],
   ["png", "png"],
@@ -53,31 +75,40 @@ const XHS_URL_FORMAT_EXTENSIONS = new Map([
   ["heif", "heif"],
   ["heic", "heic"],
   ["mp4", "mp4"],
+  ["m4a", "m4a"],
 ]);
-export async function downloadXhsMediaFromUrl(
+export async function downloadPlatformMediaFromUrl(
+  platform,
   url,
   options,
   {
     fetchMedia = fetch,
     downloadTimeoutMs = MEDIA_DOWNLOAD_TIMEOUT_MS,
     maxDownloadBytes = MEDIA_DOWNLOAD_MAX_BYTES,
-    retryDelayMs = XHS_DOWNLOAD_RETRY_DELAY_MS,
+    retryDelayMs = MEDIA_DOWNLOAD_RETRY_DELAY_MS,
     now = () => new Date(),
     linkFile = linkPath,
     copyFile = copyFilePath,
   } = {}
 ) {
-  const parsedUrl = parseHttpUrl(url);
-  const target = await resolveXhsMediaTarget(parsedUrl, options, now);
+  const config = resolvePlatformMediaDownloadConfig(platform);
+  const parsedUrl = parseHttpUrl(url, config);
+  const target = await resolvePlatformMediaTarget(parsedUrl, options, now, config);
   const existingOutput = await stat(target.outputPath).catch(ignoreMissing);
   if (existingOutput?.isDirectory()) {
-    throw new Error("--output must be a file path for xhs download-media.");
+    throw new Error(`--output must be a file path for ${config.platform} download-media.`);
   }
   if (existingOutput) {
-    return buildSkippedExistingResult(parsedUrl.href, target.outputPath, existingOutput.size);
+    return buildSkippedExistingResult(
+      config.platform,
+      parsedUrl.href,
+      target.outputPath,
+      existingOutput.size
+    );
   }
 
   return downloadWithPartResume(parsedUrl, target, {
+    config,
     fetchMedia,
     downloadTimeoutMs,
     maxDownloadBytes,
@@ -87,13 +118,15 @@ export async function downloadXhsMediaFromUrl(
   });
 }
 
-async function resolveXhsMediaTarget(parsedUrl, options = {}, now) {
+async function resolvePlatformMediaTarget(parsedUrl, options = {}, now, config) {
   if (options.output && options.outputDir) {
-    throw new Error("Use only one of --output or --output-dir for xhs download-media.");
+    throw new Error(
+      `Use only one of --output or --output-dir for ${config.platform} download-media.`
+    );
   }
   if (options.output) {
     const outputPath = resolve(expandHome(options.output));
-    await ensureParentDirectory(outputPath, "--output parent path");
+    await ensureParentDirectory(outputPath, "--output parent path", config);
     return {
       outputPath,
       partPath: `${outputPath}.part`,
@@ -101,20 +134,20 @@ async function resolveXhsMediaTarget(parsedUrl, options = {}, now) {
     };
   }
   if (!options.outputDir) {
-    throw new Error("Missing --output or --output-dir for xhs download-media.");
+    throw new Error(`Missing --output or --output-dir for ${config.platform} download-media.`);
   }
 
   const outputDir = resolve(expandHome(options.outputDir));
   const existingOutputDir = await stat(outputDir).catch(ignoreMissing);
   if (existingOutputDir && !existingOutputDir.isDirectory()) {
-    throw new Error("--output-dir must be a directory for xhs download-media.");
+    throw new Error(`--output-dir must be a directory for ${config.platform} download-media.`);
   }
   if (!existingOutputDir) {
-    await ensureParentDirectory(outputDir, "--output-dir parent path");
+    await ensureParentDirectory(outputDir, "--output-dir parent path", config);
     await mkdir(outputDir, { recursive: true });
   }
 
-  const fileTarget = inferMediaFileTarget(parsedUrl, now);
+  const fileTarget = inferMediaFileTarget(parsedUrl, now, config);
   const initialExtension =
     fileTarget.extension || fileTarget.urlFormatExtension || "bin";
   const fileName = formatMediaFileName(fileTarget.stem, initialExtension);
@@ -134,6 +167,7 @@ async function downloadWithPartResume(
   parsedUrl,
   target,
   {
+    config,
     fetchMedia,
     downloadTimeoutMs,
     maxDownloadBytes,
@@ -143,9 +177,10 @@ async function downloadWithPartResume(
   }
 ) {
   let lastError;
-  for (let attempt = 1; attempt <= XHS_DOWNLOAD_MAX_ATTEMPTS; attempt += 1) {
+  for (let attempt = 1; attempt <= MEDIA_DOWNLOAD_MAX_ATTEMPTS; attempt += 1) {
     try {
       const result = await downloadOnce(parsedUrl, target, {
+        config,
         fetchMedia,
         downloadTimeoutMs,
         maxDownloadBytes,
@@ -154,13 +189,14 @@ async function downloadWithPartResume(
       });
       if (result.skippedExisting) {
         return buildSkippedExistingResult(
+          config.platform,
           parsedUrl.href,
           result.outputPath,
           result.outputBytes
         );
       }
       return {
-        platform: "xhs",
+        platform: config.platform,
         action: "download-media",
         status: "downloaded",
         url: parsedUrl.href,
@@ -170,14 +206,14 @@ async function downloadWithPartResume(
         content_type: result.contentType,
       };
     } catch (error) {
-      if (error instanceof XhsExpiredMediaLinkError) {
+      if (error instanceof PlatformExpiredMediaLinkError) {
         throw error;
       }
       lastError = error;
       if (!shouldRetryDownloadError(error)) {
         throw error;
       }
-      if (attempt === XHS_DOWNLOAD_MAX_ATTEMPTS) {
+      if (attempt === MEDIA_DOWNLOAD_MAX_ATTEMPTS) {
         break;
       }
       await sleep(retryDelayMs);
@@ -185,15 +221,16 @@ async function downloadWithPartResume(
   }
 
   if (isAbortLikeError(lastError)) {
-    throw new Error("XHS media download timed out.");
+    throw new Error(`${config.displayName} media download timed out.`);
   }
-  throw new Error("XHS media download failed before completion.");
+  throw new Error(`${config.displayName} media download failed before completion.`);
 }
 
 async function downloadOnce(
   parsedUrl,
   target,
   {
+    config,
     fetchMedia,
     downloadTimeoutMs,
     maxDownloadBytes,
@@ -205,7 +242,7 @@ async function downloadOnce(
   const partPath = target.partPath;
   const existingPart = await stat(partPath).catch(ignoreMissing);
   let existingPartBytes = existingPart?.isFile() ? existingPart.size : 0;
-  const headers = normalizeXhsDownloadHeaders();
+  const headers = normalizePlatformDownloadHeaders(config);
   if (existingPartBytes > 0) {
     headers.Range = `bytes=${existingPartBytes}-`;
     delete headers["accept-encoding"];
@@ -217,11 +254,13 @@ async function downloadOnce(
     ...(signal ? { signal } : {}),
   });
 
-  if (XHS_EXPIRED_HTTP_STATUSES.has(response.status)) {
-    throw new XhsExpiredMediaLinkError();
+  if (MEDIA_EXPIRED_HTTP_STATUSES.has(response.status)) {
+    await cancelResponseBody(response);
+    throw new PlatformExpiredMediaLinkError(config);
   }
   if (response.status === 416) {
     return handleRangeNotSatisfiable(response, {
+      config,
       target,
       partPath,
       existingPartBytes,
@@ -230,17 +269,21 @@ async function downloadOnce(
     });
   }
   if (!response.ok) {
-    if (XHS_RETRYABLE_HTTP_STATUSES.has(response.status)) {
-      throw new XhsRetryableDownloadError();
+    await cancelResponseBody(response);
+    if (MEDIA_RETRYABLE_HTTP_STATUSES.has(response.status)) {
+      throw new MediaRetryableDownloadError();
     }
-    throw new Error(`XHS media download failed with HTTP ${response.status}.`);
+    throw new Error(
+      `${config.displayName} media download failed with HTTP ${response.status}.`
+    );
   }
 
   const contentType = normalizedContentType(headerValue(response.headers, "content-type"));
   const outputPath = resolveFinalOutputPath(target, contentType);
   const existingOutput = await stat(outputPath).catch(ignoreMissing);
   if (existingOutput?.isDirectory()) {
-    throw new Error("--output must be a file path for xhs download-media.");
+    await cancelResponseBody(response);
+    throw new Error(`--output must be a file path for ${config.platform} download-media.`);
   }
   if (existingOutput) {
     await cancelResponseBody(response);
@@ -268,7 +311,7 @@ async function downloadOnce(
     ) {
       await cancelResponseBody(response);
       await unlink(partPath).catch(ignoreError);
-      throw new XhsRetryableDownloadError();
+      throw new MediaRetryableDownloadError();
     }
     append = true;
     expectedResponseBytes = contentRange.end - contentRange.start + 1;
@@ -285,13 +328,18 @@ async function downloadOnce(
       contentRange.start !== 0
     ) {
       await cancelResponseBody(response);
-      throw new XhsRetryableDownloadError();
+      throw new MediaRetryableDownloadError();
     }
     expectedResponseBytes = contentRange.end - contentRange.start + 1;
     expectedTotalBytes = contentRange.total;
   }
 
-  assertMediaDownloadWithinLimit(expectedTotalBytes, maxDownloadBytes);
+  try {
+    assertMediaDownloadWithinLimit(expectedTotalBytes, maxDownloadBytes);
+  } catch (error) {
+    await cancelResponseBody(response);
+    throw error;
+  }
   let outputBytes;
   let bytesWritten;
   try {
@@ -305,7 +353,7 @@ async function downloadOnce(
     if (isAbortLikeError(error) || isDownloadTooLargeError(error)) {
       throw error;
     }
-    throw new XhsRetryableDownloadError();
+    throw new MediaRetryableDownloadError();
   }
 
   if (
@@ -315,17 +363,17 @@ async function downloadOnce(
     if (bytesWritten > expectedResponseBytes) {
       await unlink(partPath).catch(ignoreError);
     }
-    throw new XhsRetryableDownloadError();
+    throw new MediaRetryableDownloadError();
   }
 
   if (expectedTotalBytes !== undefined && outputBytes !== expectedTotalBytes) {
     if (outputBytes > expectedTotalBytes) {
       await unlink(partPath).catch(ignoreError);
     }
-    throw new XhsRetryableDownloadError();
+    throw new MediaRetryableDownloadError();
   }
 
-  await finalizePartFile(partPath, outputPath, { linkFile, copyFile });
+  await finalizePartFile(partPath, outputPath, { config, linkFile, copyFile });
   return {
     outputPath,
     outputBytes,
@@ -337,6 +385,7 @@ async function downloadOnce(
 async function handleRangeNotSatisfiable(
   response,
   {
+    config,
     target,
     partPath,
     existingPartBytes,
@@ -354,7 +403,8 @@ async function handleRangeNotSatisfiable(
     const outputPath = resolveFinalOutputPath(target, contentType);
     const existingOutput = await stat(outputPath).catch(ignoreMissing);
     if (existingOutput?.isDirectory()) {
-      throw new Error("--output must be a file path for xhs download-media.");
+      await cancelResponseBody(response);
+      throw new Error(`--output must be a file path for ${config.platform} download-media.`);
     }
     if (existingOutput) {
       await cancelResponseBody(response);
@@ -365,7 +415,8 @@ async function handleRangeNotSatisfiable(
         contentType,
       };
     }
-    await finalizePartFile(partPath, outputPath, { linkFile, copyFile });
+    await cancelResponseBody(response);
+    await finalizePartFile(partPath, outputPath, { config, linkFile, copyFile });
     return {
       outputPath,
       outputBytes: existingPartBytes,
@@ -373,8 +424,9 @@ async function handleRangeNotSatisfiable(
       contentType,
     };
   }
+  await cancelResponseBody(response);
   await unlink(partPath).catch(ignoreError);
-  throw new XhsRetryableDownloadError();
+  throw new MediaRetryableDownloadError();
 }
 
 async function writeResponseBodyToPart(
@@ -387,7 +439,7 @@ async function writeResponseBodyToPart(
   }
 ) {
   if (!response.body) {
-    throw new XhsRetryableDownloadError();
+    throw new MediaRetryableDownloadError();
   }
 
   const file = await openFile(partPath, append ? "r+" : "w");
@@ -413,12 +465,17 @@ async function finalizePartFile(
   partPath,
   outputPath,
   {
+    config,
     linkFile = linkPath,
     copyFile = copyFilePath,
   } = {}
 ) {
   try {
-    await ensureParentDirectory(outputPath, "xhs download-media output parent path");
+    await ensureParentDirectory(
+      outputPath,
+      `${config.platform} download-media output parent path`,
+      config
+    );
     try {
       await linkFile(partPath, outputPath);
     } catch (error) {
@@ -432,7 +489,7 @@ async function finalizePartFile(
     }
   } catch (error) {
     if (isExistingOutputPathError(error)) {
-      throw await buildExistingOutputPathError(outputPath);
+      throw await buildExistingOutputPathError(outputPath, config);
     }
     throw error;
   }
@@ -458,23 +515,31 @@ async function cancelResponseBody(response) {
   }
 }
 
-function parseHttpUrl(value) {
+function resolvePlatformMediaDownloadConfig(platform) {
+  const config = PLATFORM_MEDIA_DOWNLOAD_CONFIGS[platform];
+  if (!config) {
+    throw new Error(`Unsupported media download platform: ${platform}`);
+  }
+  return config;
+}
+
+function parseHttpUrl(value, config) {
   let parsed;
   try {
     parsed = new URL(String(value || ""));
   } catch {
-    throw new Error("XHS media URL must be an HTTP URL.");
+    throw new Error(`${config.displayName} media URL must be an HTTP URL.`);
   }
   if (!["http:", "https:"].includes(parsed.protocol) || !parsed.hostname) {
-    throw new Error("XHS media URL must be an HTTP URL.");
+    throw new Error(`${config.displayName} media URL must be an HTTP URL.`);
   }
   return parsed;
 }
 
-function normalizeXhsDownloadHeaders() {
+function normalizePlatformDownloadHeaders(config) {
   return {
-    "User-Agent": XHS_DOWNLOAD_USER_AGENT,
-    Referer: XHS_DOWNLOAD_REFERER,
+    "User-Agent": MEDIA_DOWNLOAD_USER_AGENT,
+    Referer: config.referer,
     "accept-encoding": "identity",
   };
 }
@@ -491,8 +556,8 @@ function resolveFinalOutputPath(target, contentType) {
   return join(target.outputDir, formatMediaFileName(target.fileStem, extension));
 }
 
-function inferMediaFileTarget(parsedUrl, now) {
-  const fallbackStem = `xhs-media-${formatTimestamp(now())}`;
+function inferMediaFileTarget(parsedUrl, now, config) {
+  const fallbackStem = `${config.platform}-media-${formatTimestamp(now())}`;
   const urlFormatExtension = inferUrlFormatExtension(parsedUrl);
   const rawBasename = safeDecodeURIComponent(basename(parsedUrl.pathname || ""));
   const sanitized = sanitizeFileName(rawBasename);
@@ -515,20 +580,20 @@ function inferMediaFileTarget(parsedUrl, now) {
   };
 }
 
-async function ensureParentDirectory(outputPath, displayName) {
+async function ensureParentDirectory(outputPath, displayName, config) {
   const parent = dirname(outputPath);
   const existingParent = await stat(parent).catch(ignoreMissing);
   if (existingParent && !existingParent.isDirectory()) {
-    throw new Error(`${displayName} must be a directory for xhs download-media.`);
+    throw new Error(`${displayName} must be a directory for ${config.platform} download-media.`);
   }
   if (!existingParent) {
     await mkdir(parent, { recursive: true });
   }
 }
 
-function buildSkippedExistingResult(url, outputPath, outputBytes) {
+function buildSkippedExistingResult(platform, url, outputPath, outputBytes) {
   return {
-    platform: "xhs",
+    platform,
     action: "download-media",
     status: "skipped_existing",
     url,
@@ -580,7 +645,7 @@ function isUsableContentRange(contentRange, contentLength) {
 
 function shouldRetryDownloadError(error) {
   return (
-    error instanceof XhsRetryableDownloadError ||
+    error instanceof MediaRetryableDownloadError ||
     isAbortLikeError(error) ||
     isNetworkLikeError(error)
   );
@@ -632,7 +697,7 @@ function formatMediaFileName(stem, extension) {
 }
 
 function mediaExtensionFromContentType(contentType) {
-  return XHS_CONTENT_TYPE_EXTENSIONS.get(contentType) || "";
+  return MEDIA_CONTENT_TYPE_EXTENSIONS.get(contentType) || "";
 }
 
 function inferUrlFormatExtension(parsedUrl) {
@@ -642,7 +707,7 @@ function inferUrlFormatExtension(parsedUrl) {
   if (!matched) {
     return "";
   }
-  return XHS_URL_FORMAT_EXTENSIONS.get(sanitizeFileExtension(matched[1])) || "";
+  return MEDIA_URL_FORMAT_EXTENSIONS.get(sanitizeFileExtension(matched[1])) || "";
 }
 
 function isExistingOutputPathError(error) {
@@ -655,12 +720,12 @@ function shouldFallbackToCopyAfterLinkError(error) {
   );
 }
 
-async function buildExistingOutputPathError(outputPath) {
+async function buildExistingOutputPathError(outputPath, config) {
   const existingOutput = await stat(outputPath).catch(ignoreMissing);
   if (existingOutput?.isDirectory()) {
-    return new Error("--output must be a file path for xhs download-media.");
+    return new Error(`--output must be a file path for ${config.platform} download-media.`);
   }
-  return new Error("XHS media download output file already exists.");
+  return new Error(`${config.displayName} media download output file already exists.`);
 }
 
 function formatTimestamp(value) {
@@ -712,12 +777,12 @@ function sleep(ms) {
   });
 }
 
-class XhsRetryableDownloadError extends Error {}
+class MediaRetryableDownloadError extends Error {}
 
-class XhsExpiredMediaLinkError extends Error {
-  constructor() {
+class PlatformExpiredMediaLinkError extends Error {
+  constructor(config) {
     super(
-      "XHS media link is unavailable or expired. Get a fresh media URL from the XHS detail result and retry."
+      `${config.displayName} media link is unavailable or expired. Get a fresh media URL from the ${config.displayName} detail result and retry.`
     );
   }
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "socialdatax-skills",
-  "version": "0.2.29",
+  "version": "0.2.30",
   "description": "SocialDataX / 社媒数据助手 skill installer and direct CLI helper for hosted platform social media MCP services.",
   "license": "MIT",
   "type": "module",

package/skills/media-comments/SKILL.md

@@ -37,7 +37,7 @@ Current platform support:
 ## API Key
 
 Use `SOCIALDATAX_API_KEY` for SocialDataX requests. The only official website for requesting or managing API access is <https://socialdatax.com/?from=npm>. If a user asks where to get a key, provide only this URL; do not infer alternate domains.
-获取或管理 API Key：访问 <https://socialdatax.com/?from=npm>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名。
+获取或管理 API Key：访问 <https://socialdatax.com/?from=npm>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名；do not infer alternate domains。
 
 ## Preferred Direct CLI
 

package/skills/media-detail/SKILL.md

@@ -38,7 +38,7 @@ Current platform support:
 ## API Key
 
 Use `SOCIALDATAX_API_KEY` for SocialDataX requests. The only official website for requesting or managing API access is <https://socialdatax.com/?from=npm>. If a user asks where to get a key, provide only this URL; do not infer alternate domains.
-获取或管理 API Key：访问 <https://socialdatax.com/?from=npm>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名。
+获取或管理 API Key：访问 <https://socialdatax.com/?from=npm>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名；do not infer alternate domains。
 
 ## Preferred Direct CLI
 
@@ -112,7 +112,7 @@ The command prints JSON with `platform`, `tool`, `arguments`, and `data`.
 
 ## Safety Boundary
 
-Platform detail access is read-only. It uses `SOCIALDATAX_API_KEY` from the user's environment at runtime for SocialDataX detail requests. Generated Skill files do not contain API keys. It does not read local browser data or perform login, posting, liking, commenting, or account changes. The optional XHS local save command writes only to the requested local `--output` path or `--output-dir` directory and does not require `SOCIALDATAX_API_KEY`. The optional WeChat Channels / 视频号 local save command writes only to the user-provided `--output` file, decrypts when needed, and does not require `SOCIALDATAX_API_KEY`. Prefer the direct CLI; hosted MCP tools are optional when the current agent already supports authenticated streamable HTTP MCP.
+Platform detail access is read-only. It uses `SOCIALDATAX_API_KEY` from the user's environment at runtime for SocialDataX detail requests. Generated Skill files do not contain API keys. It does not read local browser data or perform login, posting, liking, commenting, or account changes. The optional XHS, Douyin, Kuaishou, and Weibo local save commands write only to the requested local `--output` path or `--output-dir` directory and do not require `SOCIALDATAX_API_KEY`. The optional WeChat Channels / 视频号 local save command writes only to the user-provided `--output` file, decrypts when needed, and does not require `SOCIALDATAX_API_KEY`. Prefer the direct CLI; hosted MCP tools are optional when the current agent already supports authenticated streamable HTTP MCP.
 
 ## MCP Tools
 
@@ -148,11 +148,14 @@ If MCP tools are already available in the current agent, use one of these tools:
 Return factual fields such as title or description, content, author, publish time, interaction counts, images, and media summary when available.
 For XHS detail results, in every use of a returned `note_url`, such as final answers, display, references, storage, output, or forwarding, preserve it exactly as the full URL, including `xsec_token` query parameters. Do not modify, truncate, redact, mask, normalize, rebuild, or synthesize the URL from `note_id`; if `note_url` is null, show the `note_id` or say that no directly openable full link is available.
 For XHS `note_id`, copy the complete 24-character lowercase hexadecimal ID exactly; do not pass or display only a prefix.
-When the user wants to save XHS images or videos after detail, pass each returned `image_items[].image_url` or `video.video_url` to `npx -y socialdatax-skills@latest xhs download-media --url "<media_url>" --output-dir <directory> --pretty`; this local save command does not require `SOCIALDATAX_API_KEY`.
+When the user wants to save XHS images or videos after detail, pass each returned `image_items[].image_url`, `image_items[].live_photo.video_url`, or `video.video_url` to `npx -y socialdatax-skills@latest xhs download-media --url "<media_url>" --output-dir <directory> --pretty`; this local save command does not require `SOCIALDATAX_API_KEY`.
 For Douyin detail, include `content_type` when available.
 For Douyin detail, use `images` for image/text posts; `video` is the platform player resource and may be audio for image/text posts; `music` is the bound music or original-sound asset.
+When the user wants to save Douyin media after detail, pass each returned `images[].url`, `images[].live_photo.play_url`, `video.play_url`, `music.play_url`, or `cover_image_url` to `npx -y socialdatax-skills@latest douyin download-media --url "<media_url>" --output-dir <directory> --pretty`; this local save command does not require `SOCIALDATAX_API_KEY`.
+When the user wants to save Kuaishou media after detail, pass each returned `images[].url`, `video.play_url`, or `cover_image_url` to `npx -y socialdatax-skills@latest kuaishou download-media --url "<media_url>" --output-dir <directory> --pretty`; this local save command does not require `SOCIALDATAX_API_KEY`.
 Detail access is read-only and does not provide account actions.
 For Weibo detail, include `post_id`, content, author, media, interaction counts, publish time, and post URL when available.
+When the user wants to save Weibo media after detail, pass each returned `image_urls[]` or `video.video_url` to `npx -y socialdatax-skills@latest weibo download-media --url "<media_url>" --output-dir <directory> --pretty`; this local save command does not require `SOCIALDATAX_API_KEY`.
 For WeChat Channels / 视频号 detail, preserve `object_id` and `object_nonce_id` because comments and replies need both values.
 When the user wants to save a WeChat Channels / 视频号 video after detail, pass the returned `video.video_url` to `npx -y socialdatax-skills@latest wechat decrypt-media --media-url "<video.video_url>" --output <file>`; this local save command decrypts when needed and does not require `SOCIALDATAX_API_KEY`.
 For WeChat Official Account / 微信公众号 article detail, include article title, account, publish time, body text, image URLs, linked articles, and embedded video cards when present.

package/skills/media-search/SKILL.md

@@ -37,7 +37,7 @@ Current platform support:
 ## API Key
 
 Use `SOCIALDATAX_API_KEY` for SocialDataX requests. The only official website for requesting or managing API access is <https://socialdatax.com/?from=npm>. If a user asks where to get a key, provide only this URL; do not infer alternate domains.
-获取或管理 API Key：访问 <https://socialdatax.com/?from=npm>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名。
+获取或管理 API Key：访问 <https://socialdatax.com/?from=npm>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名；do not infer alternate domains。
 
 ## Preferred Direct CLI
 

package/skills/media-transcript/SKILL.md

@@ -37,7 +37,7 @@ Current platform support:
 ## API Key
 
 Use `SOCIALDATAX_API_KEY` for SocialDataX requests. The only official website for requesting or managing API access is <https://socialdatax.com/?from=npm>. If a user asks where to get a key, provide only this URL; do not infer alternate domains.
-获取或管理 API Key：访问 <https://socialdatax.com/?from=npm>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名。
+获取或管理 API Key：访问 <https://socialdatax.com/?from=npm>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名；do not infer alternate domains。
 
 ## Preferred Direct CLI
 

package/skills/media-user-info/SKILL.md

@@ -38,7 +38,7 @@ Current platform support:
 ## API Key
 
 Use `SOCIALDATAX_API_KEY` for SocialDataX requests. The only official website for requesting or managing API access is <https://socialdatax.com/?from=npm>. If a user asks where to get a key, provide only this URL; do not infer alternate domains.
-获取或管理 API Key：访问 <https://socialdatax.com/?from=npm>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名。
+获取或管理 API Key：访问 <https://socialdatax.com/?from=npm>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名；do not infer alternate domains。
 
 ## Preferred Direct CLI
 

package/skills/media-user-posts/SKILL.md

@@ -38,7 +38,7 @@ Current platform support:
 ## API Key
 
 Use `SOCIALDATAX_API_KEY` for SocialDataX requests. The only official website for requesting or managing API access is <https://socialdatax.com/?from=npm>. If a user asks where to get a key, provide only this URL; do not infer alternate domains.
-获取或管理 API Key：访问 <https://socialdatax.com/?from=npm>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名。
+获取或管理 API Key：访问 <https://socialdatax.com/?from=npm>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名；do not infer alternate domains。
 
 ## Preferred Direct CLI
 

package/skills/sensitive-check/SKILL.md

@@ -33,7 +33,7 @@ Current platform support:
 ## API Key
 
 Use `SOCIALDATAX_API_KEY` for SocialDataX requests. The only official website for requesting or managing API access is <https://socialdatax.com/?from=npm>. If a user asks where to get a key, provide only this URL; do not infer alternate domains.
-获取或管理 API Key：访问 <https://socialdatax.com/?from=npm>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名。
+获取或管理 API Key：访问 <https://socialdatax.com/?from=npm>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名；do not infer alternate domains。
 
 ## Preferred Direct CLI
 

package/skills/socialdatax-content-research-assistant/SKILL.md

@@ -65,7 +65,7 @@ Current platform support:
 ## API Key
 
 Use `SOCIALDATAX_API_KEY` for SocialDataX requests. The only official website for requesting or managing API access is <https://socialdatax.com/?from=npm>. If a user asks where to get a key, provide only this URL; do not infer alternate domains.
-获取或管理 API Key：访问 <https://socialdatax.com/?from=npm>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名。
+获取或管理 API Key：访问 <https://socialdatax.com/?from=npm>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名；do not infer alternate domains。
 
 ## Preferred Direct CLI