socialdatax-skills 0.2.11 → 0.2.13

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, and 视频号 / WeChat Channels content research and analysis workflows. The public skill layer is intentionally named by media capability so supported platforms 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, and 视频号 / WeChat Channels content research and analysis workflows, plus SocialDataX 敏感检测 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
@@ -39,14 +39,19 @@ Common search phrases for this skill package:
 - `视频号 skills`
 - `SocialDataX content research`
 - `content research assistant`
+- `敏感检测 SocialDataX`
+- `sensitive check skill`
+- `content safety skill`
+- `text safety check`
 
 ## Platform MCPs
 
-- XHS hosted MCP endpoint: `https://mcp.52choujiang.com/xhs/mcp`
-- Douyin hosted MCP endpoint: `https://mcp.52choujiang.com/douyin/mcp`
-- Kuaishou hosted MCP endpoint: `https://mcp.52choujiang.com/kuaishou/mcp`
-- Weibo hosted MCP endpoint: `https://mcp.52choujiang.com/weibo/mcp`
-- WeChat Channels hosted MCP endpoint: `https://mcp.52choujiang.com/wechat/mcp`
+- 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`
+- Weibo hosted MCP endpoint: `https://mcp.socialdatax.com/weibo/mcp`
+- WeChat Channels hosted MCP endpoint: `https://mcp.socialdatax.com/wechat/mcp`
+- Sensitive 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>
@@ -60,8 +65,10 @@ Common search phrases for this skill package:
 - Weibo future platform MCP registry name: `com.socialdatax/weibo-insights`
 - WeChat Channels current platform MCP registry name: `com.52choujiang/wechat-channels-insights`
 - WeChat Channels future platform MCP registry name: `com.socialdatax/wechat-channels-insights`
+- Sensitive Check MCP server name: `sensitive-check`
+- Sensitive 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: `0.2.11`
+- Current public capability version: `0.2.13`
 
 ## Direct CLI
 
@@ -71,6 +78,7 @@ Examples:
 
 ```bash
 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
@@ -78,6 +86,7 @@ npx -y socialdatax-skills@latest xhs comments --note-id "<note_id>" --all --incl
 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 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
@@ -127,14 +136,17 @@ npx -y socialdatax-skills@latest wechat replies --object-id "<object_id>" --obje
 npx -y socialdatax-skills@latest wechat user-info --user-id "<finder_user_id>" --pretty
 npx -y socialdatax-skills@latest wechat user-posts --user-id "<finder_user_id>" --pretty
 npx -y socialdatax-skills@latest wechat user-posts --url "<wechat_video_url_or_share_text>" --pretty
+npx -y socialdatax-skills@latest sensitive-check text --text "<content>" --platform xhs --pretty
 ```
 
-The direct CLI prints a JSON envelope with `platform`, `tool`, `arguments`, and `data`.
+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.
 
 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.
 
+For search and creator content-list commands, use `--since-days <1-365>` to keep only items whose public `publish_time` is within the last N days. Search remains bounded by `--pages` and does not promise complete platform coverage; creator content lists continue until the publish-time boundary when `--pages` is omitted.
+
 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 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`.
@@ -192,6 +204,7 @@ SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" node cli.mjs douyin search --keyword
 SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" node cli.mjs kuaishou search --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 sensitive-check text --text "<content>" --platform xhs --pretty
 ```
 
 ### Docker Run
@@ -203,6 +216,7 @@ docker run --rm -i -e SOCIALDATAX_API_KEY="<SOCIALDATAX_API_KEY>" socialdatax-sk
 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 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 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:
@@ -245,6 +259,7 @@ 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 wechat hot-search --pretty
 npx -y socialdatax-skills@latest wechat search --keyword "露营" --pretty
+npx -y socialdatax-skills@latest sensitive-check text --text "<content>" --platform xhs --pretty
 ```
 
 Available skills:
@@ -256,6 +271,7 @@ Available skills:
 - `media-transcript`: submit and check video 口播转文字 / speech-to-text transcript jobs through hosted MCP tools; supports XHS, Douyin, Kuaishou, Weibo, and WeChat Channels.
 - `media-user-info`: retrieve creator profile information; supports XHS, Douyin, Kuaishou, Weibo, and WeChat Channels creators.
 - `media-user-posts`: retrieve creator content lists; supports XHS notes, Douyin works, Kuaishou works, Weibo posts, WeChat Channels videos, and Douyin creator short-drama series.
+- `sensitive-check`: run 敏感检测 text checks; supports `generic`, `xhs`, `douyin`, and `kuaishou` platform contexts.
 
 Default install locations:
 
@@ -336,6 +352,13 @@ Current WeChat Channels / 视频号 workflows include:
 - Fetch paginated creator video lists from a finder user_id or a video link/share text.
 - Submit and check WeChat Channels / 视频号 video 口播转文字 / speech-to-text transcript jobs; submit tools 提交完成后最多短等 15 秒.
 
+Current Sensitive Check workflows include:
+
+- Check draft text for 敏感检测 / sensitive-content risks before publishing.
+- Choose a platform context with `--platform generic`, `--platform xhs`, `--platform douyin`, or `--platform kuaishou`.
+- Return structured fields such as `violation`, `risk_level`, `types`, `highlights`, `summary`, `platform`, and `suggestions` when available.
+- Text checks are read-only. Image sensitive detection is reserved for a future separate tool.
+
 ## XHS Tools
 
 | Tool | Public purpose |
@@ -432,6 +455,12 @@ Current WeChat Channels / 视频号 workflows include:
 | `wechat_submit_video_speech_text_by_encrypted_object_id` | Submit a WeChat Channels / 视频号 video speech-to-text transcript job when encrypted_object_id is already known; submit waits up to 15 seconds. |
 | `wechat_get_video_speech_text_job` | Check a WeChat Channels / 视频号 speech-to-text transcript job by job_id without creating a new task. |
 
+## Sensitive Check Tools
+
+| Tool | Public purpose |
+| --- | --- |
+| `check_sensitive_text` | Check text for 敏感检测 / sensitive-content risks with `generic`, `xhs`, `douyin`, or `kuaishou` context. |
+
 ## Quick Start
 
 For agents that can execute shell commands, use the direct CLI. This is the recommended default for installed skills:
@@ -443,9 +472,10 @@ npx -y socialdatax-skills@latest douyin search --keyword "露营" --pretty
 npx -y socialdatax-skills@latest kuaishou search --keyword "露营" --pretty
 npx -y socialdatax-skills@latest weibo search --keyword "露营" --pretty
 npx -y socialdatax-skills@latest wechat search --keyword "露营" --pretty
+npx -y socialdatax-skills@latest sensitive-check text --text "<content>" --platform xhs --pretty
 ```
 
-MCP client configuration belongs to platform MCP listings. For XHS, use the `xhs-insights` docs; for Douyin, use the `douyin-insights` listing; for Kuaishou, use the `kuaishou-insights` listing; for Weibo, use the `weibo-insights` listing; for WeChat Channels / 视频号, use the `wechat-channels-insights` listing.
+MCP client configuration belongs to platform or capability MCP listings. For XHS, use the `xhs-insights` docs; for Douyin, use the `douyin-insights` listing; for Kuaishou, use the `kuaishou-insights` listing; for Weibo, use the `weibo-insights` listing; for WeChat Channels / 视频号, use the `wechat-channels-insights` listing; for 敏感检测, use the `sensitive-check` server.
 
 Aily is treated as an OpenClaw / AgentSkills ecosystem channel for this package. Use the OpenClaw skill install flow for now; a dedicated `--target aily` will be added only after its official skill import or package format is confirmed.
 
@@ -461,7 +491,7 @@ Use the key as a Bearer token in the `Authorization` request header. Do not comm
 
 Public metadata files in this repository:
 
-- [skills](skills): AgentSkills-compatible skills split by social media capability and currently backed by XHS, Douyin, Kuaishou, Weibo, and WeChat Channels tools.
+- [skills](skills): AgentSkills-compatible skills split by capability and currently backed by XHS, Douyin, Kuaishou, Weibo, WeChat Channels, and Sensitive Check tools.
 
 ## License
 

package/cli.mjs

@@ -7,7 +7,7 @@ import { dirname, join, resolve } from "node:path";
 import { fileURLToPath } from "node:url";
 
 const PACKAGE_NAME = "socialdatax-skills";
-const PACKAGE_VERSION = "0.2.11";
+const PACKAGE_VERSION = "0.2.13";
 const PACKAGE_SPEC = `${PACKAGE_NAME}@latest`;
 const LOG_PREFIX = `[${PACKAGE_NAME}]`;
 const MIN_NODE_VERSION = "20.18.1";
@@ -58,6 +58,12 @@ const AVAILABLE_SKILLS = [
       "Retrieve creator content lists for XHS, Douyin, Kuaishou, Weibo, and WeChat Channels, including Douyin creator short-drama series.",
     emoji: "🗂️",
   },
+  {
+    name: "sensitive-check",
+    summary:
+      "Check text content for generic, XHS, Douyin, and Kuaishou sensitive-content risks.",
+    emoji: "🛡️",
+  },
 ];
 const AVAILABLE_SKILL_NAMES = AVAILABLE_SKILLS.map((skill) => skill.name);
 const BOOLEAN_OPTIONS = new Set([
@@ -79,6 +85,7 @@ const XHS_DIRECT_ACTION_OPTIONS = {
     "pages",
     "all",
     "maxItems",
+    "sinceDays",
     "sortType",
     "noteType",
     "publishTimeRange",
@@ -106,7 +113,16 @@ const XHS_DIRECT_ACTION_OPTIONS = {
     "pretty",
   ],
   "user-info": ["userId", "profileUrl", "pretty"],
-  "user-posts": ["userId", "profileUrl", "pageToken", "pages", "all", "maxItems", "pretty"],
+  "user-posts": [
+    "userId",
+    "profileUrl",
+    "pageToken",
+    "pages",
+    "all",
+    "maxItems",
+    "sinceDays",
+    "pretty",
+  ],
 };
 const XHS_DIRECT_ACTION_NAMES = Object.keys(XHS_DIRECT_ACTION_OPTIONS).join(", ");
 const XHS_OPTION_DISPLAY_NAMES = {
@@ -120,6 +136,7 @@ const XHS_OPTION_DISPLAY_NAMES = {
   pageToken: "--page-token",
   pages: "--pages",
   maxItems: "--max-items",
+  sinceDays: "--since-days",
   all: "--all",
   includeReplies: "--include-replies",
   profileUrl: "--profile-url",
@@ -145,6 +162,7 @@ const DOUYIN_DIRECT_ACTION_OPTIONS = {
     "pages",
     "all",
     "maxItems",
+    "sinceDays",
     "sortType",
     "publishTimeRange",
     "durationRange",
@@ -173,7 +191,16 @@ const DOUYIN_DIRECT_ACTION_OPTIONS = {
     "pretty",
   ],
   "user-info": ["secUserId", "profileUrl", "pretty"],
-  "user-posts": ["secUserId", "profileUrl", "pageToken", "pages", "all", "maxItems", "pretty"],
+  "user-posts": [
+    "secUserId",
+    "profileUrl",
+    "pageToken",
+    "pages",
+    "all",
+    "maxItems",
+    "sinceDays",
+    "pretty",
+  ],
   "user-series": ["secUserId", "profileUrl", "pageToken", "pages", "all", "maxItems", "pretty"],
 };
 const DOUYIN_DIRECT_ACTION_NAMES = Object.keys(DOUYIN_DIRECT_ACTION_OPTIONS).join(", ");
@@ -191,6 +218,7 @@ const DOUYIN_OPTION_DISPLAY_NAMES = {
   pageToken: "--page-token",
   pages: "--pages",
   maxItems: "--max-items",
+  sinceDays: "--since-days",
   all: "--all",
   includeReplies: "--include-replies",
   sortType: "--sort-type",
@@ -205,7 +233,7 @@ const DOUYIN_OPTION_DISPLAY_NAMES = {
 };
 const KUAISHOU_DIRECT_ACTION_OPTIONS = {
   "hot-search": ["pretty"],
-  search: ["keyword", "pageToken", "pages", "all", "maxItems", "pretty"],
+  search: ["keyword", "pageToken", "pages", "all", "maxItems", "sinceDays", "pretty"],
   detail: ["photoId", "url", "pretty"],
   comments: [
     "photoId",
@@ -228,7 +256,16 @@ const KUAISHOU_DIRECT_ACTION_OPTIONS = {
     "pretty",
   ],
   "user-info": ["userId", "profileUrl", "pretty"],
-  "user-posts": ["userId", "profileUrl", "pageToken", "pages", "all", "maxItems", "pretty"],
+  "user-posts": [
+    "userId",
+    "profileUrl",
+    "pageToken",
+    "pages",
+    "all",
+    "maxItems",
+    "sinceDays",
+    "pretty",
+  ],
 };
 const KUAISHOU_DIRECT_ACTION_NAMES = Object.keys(KUAISHOU_DIRECT_ACTION_OPTIONS).join(", ");
 const KUAISHOU_OPTION_DISPLAY_NAMES = {
@@ -236,6 +273,7 @@ const KUAISHOU_OPTION_DISPLAY_NAMES = {
   pageToken: "--page-token",
   pages: "--pages",
   maxItems: "--max-items",
+  sinceDays: "--since-days",
   all: "--all",
   includeReplies: "--include-replies",
   url: "--url",
@@ -246,7 +284,7 @@ const KUAISHOU_OPTION_DISPLAY_NAMES = {
 };
 const WEIBO_DIRECT_ACTION_OPTIONS = {
   "hot-search": ["pretty"],
-  search: ["keyword", "pageToken", "pages", "all", "maxItems", "pretty"],
+  search: ["keyword", "pageToken", "pages", "all", "maxItems", "sinceDays", "pretty"],
   detail: ["postId", "postUrl", "pretty"],
   comments: [
     "postId",
@@ -271,7 +309,16 @@ const WEIBO_DIRECT_ACTION_OPTIONS = {
   likers: ["postId", "pageToken", "pages", "all", "maxItems", "pretty"],
   reposts: ["postId", "pageToken", "pages", "all", "maxItems", "pretty"],
   "user-info": ["userId", "profileUrl", "pretty"],
-  "user-posts": ["userId", "profileUrl", "pageToken", "pages", "all", "maxItems", "pretty"],
+  "user-posts": [
+    "userId",
+    "profileUrl",
+    "pageToken",
+    "pages",
+    "all",
+    "maxItems",
+    "sinceDays",
+    "pretty",
+  ],
 };
 const WEIBO_DIRECT_ACTION_NAMES = Object.keys(WEIBO_DIRECT_ACTION_OPTIONS).join(", ");
 const WEIBO_OPTION_DISPLAY_NAMES = {
@@ -279,6 +326,7 @@ const WEIBO_OPTION_DISPLAY_NAMES = {
   pageToken: "--page-token",
   pages: "--pages",
   maxItems: "--max-items",
+  sinceDays: "--since-days",
   all: "--all",
   includeReplies: "--include-replies",
   postId: "--post-id",
@@ -295,6 +343,7 @@ const WECHAT_DIRECT_ACTION_OPTIONS = {
     "pages",
     "all",
     "maxItems",
+    "sinceDays",
     "sortType",
     "durationRange",
     "pretty",
@@ -323,7 +372,16 @@ const WECHAT_DIRECT_ACTION_OPTIONS = {
     "pretty",
   ],
   "user-info": ["userId", "pretty"],
-  "user-posts": ["userId", "url", "pageToken", "pages", "all", "maxItems", "pretty"],
+  "user-posts": [
+    "userId",
+    "url",
+    "pageToken",
+    "pages",
+    "all",
+    "maxItems",
+    "sinceDays",
+    "pretty",
+  ],
 };
 const WECHAT_DIRECT_ACTION_NAMES = Object.keys(WECHAT_DIRECT_ACTION_OPTIONS).join(", ");
 const WECHAT_SEARCH_SORT_TYPES = ["all", "latest", "popular"];
@@ -338,6 +396,7 @@ const WECHAT_OPTION_DISPLAY_NAMES = {
   pageToken: "--page-token",
   pages: "--pages",
   maxItems: "--max-items",
+  sinceDays: "--since-days",
   all: "--all",
   includeReplies: "--include-replies",
   sortType: "--sort-type",
@@ -349,6 +408,17 @@ const WECHAT_OPTION_DISPLAY_NAMES = {
   commentId: "--comment-id",
   userId: "--user-id",
 };
+const SENSITIVE_CHECK_DIRECT_ACTION_OPTIONS = {
+  text: ["text", "platform", "pretty"],
+};
+const SENSITIVE_CHECK_DIRECT_ACTION_NAMES = Object.keys(
+  SENSITIVE_CHECK_DIRECT_ACTION_OPTIONS
+).join(", ");
+const SENSITIVE_CHECK_PLATFORMS = ["generic", "xhs", "douyin", "kuaishou"];
+const SENSITIVE_CHECK_OPTION_DISPLAY_NAMES = {
+  text: "--text",
+  platform: "--platform",
+};
 const PLATFORMS = {
   xhs: {
     id: "xhs",
@@ -356,7 +426,7 @@ const PLATFORMS = {
     status: "public",
     registryName: "com.52choujiang/xhs-insights",
     futureRegistryName: "com.socialdatax/xhs-insights",
-    endpoint: "https://mcp.52choujiang.com/xhs/mcp",
+    endpoint: "https://mcp.socialdatax.com/xhs/mcp",
     apiKeyEnv: API_KEY_ENV_NAMES,
     upstreamEnv: [
       "SOCIAL_MEDIA_XHS_MCP_UPSTREAM_URL",
@@ -438,7 +508,7 @@ const PLATFORMS = {
     status: "public",
     registryName: "com.52choujiang/douyin-insights",
     futureRegistryName: "com.socialdatax/douyin-insights",
-    endpoint: "https://mcp.52choujiang.com/douyin/mcp",
+    endpoint: "https://mcp.socialdatax.com/douyin/mcp",
     apiKeyEnv: API_KEY_ENV_NAMES,
     upstreamEnv: [
       "SOCIAL_MEDIA_DOUYIN_MCP_UPSTREAM_URL",
@@ -522,7 +592,7 @@ const PLATFORMS = {
     status: "public",
     registryName: "com.52choujiang/kuaishou-insights",
     futureRegistryName: "com.socialdatax/kuaishou-insights",
-    endpoint: "https://mcp.52choujiang.com/kuaishou/mcp",
+    endpoint: "https://mcp.socialdatax.com/kuaishou/mcp",
     apiKeyEnv: API_KEY_ENV_NAMES,
     upstreamEnv: [
       "SOCIAL_MEDIA_KUAISHOU_MCP_UPSTREAM_URL",
@@ -598,7 +668,7 @@ const PLATFORMS = {
     status: "public",
     registryName: "com.52choujiang/weibo-insights",
     futureRegistryName: "com.socialdatax/weibo-insights",
-    endpoint: "https://mcp.52choujiang.com/weibo/mcp",
+    endpoint: "https://mcp.socialdatax.com/weibo/mcp",
     apiKeyEnv: API_KEY_ENV_NAMES,
     upstreamEnv: [
       "SOCIAL_MEDIA_WEIBO_MCP_UPSTREAM_URL",
@@ -682,7 +752,7 @@ const PLATFORMS = {
     status: "public",
     registryName: "com.52choujiang/wechat-channels-insights",
     futureRegistryName: "com.socialdatax/wechat-channels-insights",
-    endpoint: "https://mcp.52choujiang.com/wechat/mcp",
+    endpoint: "https://mcp.socialdatax.com/wechat/mcp",
     apiKeyEnv: API_KEY_ENV_NAMES,
     upstreamEnv: [
       "SOCIAL_MEDIA_WECHAT_MCP_UPSTREAM_URL",
@@ -748,6 +818,27 @@ const PLATFORMS = {
       },
     ],
   },
+  "sensitive-check": {
+    id: "sensitive-check",
+    displayName: "Sensitive Check / 敏感检测",
+    status: "public",
+    registryName: "sensitive-check",
+    futureRegistryName: "com.socialdatax/sensitive-check",
+    endpoint: "https://mcp.socialdatax.com/sensitive-check/mcp",
+    apiKeyEnv: API_KEY_ENV_NAMES,
+    upstreamEnv: [
+      "SOCIALDATAX_SENSITIVE_CHECK_MCP_UPSTREAM_URL",
+      "SOCIAL_MEDIA_SENSITIVE_CHECK_MCP_UPSTREAM_URL",
+      "SOCIAL_MEDIA_MCP_UPSTREAM_URL",
+    ],
+    tools: [
+      {
+        name: "check_sensitive_text",
+        description:
+          "Check text content for generic, XHS, Douyin, or Kuaishou sensitive-content risks.",
+      },
+    ],
+  },
 };
 const currentDir = dirname(fileURLToPath(import.meta.url));
 let mcpSdkModules;
@@ -787,6 +878,8 @@ if (isMainModule()) {
       await runWeiboDirectCommand(cliArgs.slice(1));
     } else if (command === "wechat") {
       await runWechatDirectCommand(cliArgs.slice(1));
+    } else if (command === "sensitive-check") {
+      await runSensitiveCheckDirectCommand(cliArgs.slice(1));
     } else if (command === "--platform" || command?.startsWith("--platform=") || command === "print-config") {
       printRemovedMcpConfigHelp(command);
       process.exitCode = 1;
@@ -947,6 +1040,21 @@ function validateWechatDirectActionOptions(action, options) {
   }
 }
 
+function validateSensitiveCheckDirectActionOptions(action, options) {
+  const allowedOptions = SENSITIVE_CHECK_DIRECT_ACTION_OPTIONS[action];
+  if (!allowedOptions) {
+    return;
+  }
+
+  validateKnownOptions(options, allowedOptions);
+  validateFlagOption(options, "pretty", "--pretty");
+  for (const key of allowedOptions) {
+    if (!DIRECT_BOOLEAN_OPTIONS.has(key)) {
+      requireOptionValue(options, key, SENSITIVE_CHECK_OPTION_DISPLAY_NAMES[key]);
+    }
+  }
+}
+
 function validateDirectPaginationOptions(platformId, action, options) {
   validateFlagOption(options, "pretty", "--pretty");
   validateFlagOption(options, "all", "--all");
@@ -960,6 +1068,9 @@ function validateDirectPaginationOptions(platformId, action, options) {
   if (options.maxItems !== undefined) {
     parsePositiveIntegerOption(options.maxItems, "--max-items");
   }
+  if (options.sinceDays !== undefined) {
+    parseSinceDaysOption(options.sinceDays);
+  }
   if (options.all && action === "search") {
     throw new Error(`--all is not supported for ${platformId} search. Use --pages instead.`);
   }
@@ -980,6 +1091,37 @@ function parsePositiveIntegerOption(value, displayName) {
   return parsed;
 }
 
+function parseSinceDaysOption(value) {
+  const text = String(value);
+  if (!/^\d+$/.test(text)) {
+    throw new Error("--since-days must be an integer between 1 and 365.");
+  }
+  const parsed = Number(text);
+  if (!Number.isSafeInteger(parsed) || parsed < 1 || parsed > 365) {
+    throw new Error("--since-days must be an integer between 1 and 365.");
+  }
+  return parsed;
+}
+
+function parseOptionalSinceDays(options) {
+  return options.sinceDays === undefined
+    ? undefined
+    : parseSinceDaysOption(options.sinceDays);
+}
+
+function nativePublishTimeRangeForSinceDays(sinceDays) {
+  if (sinceDays <= 1) {
+    return "day";
+  }
+  if (sinceDays <= 7) {
+    return "week";
+  }
+  if (sinceDays <= 180) {
+    return "half_year";
+  }
+  return undefined;
+}
+
 function parseAllowedStringOption(value, displayName, allowedValues, label) {
   const normalized = String(value).trim();
   if (!allowedValues.includes(normalized)) {
@@ -1445,6 +1587,9 @@ function printHelp() {
   console.log(`  npx -y ${PACKAGE_SPEC} xhs search --keyword "露营" --pretty`);
   console.log("      Call the XHS search tool directly and print JSON.");
   console.log("");
+  console.log(`  npx -y ${PACKAGE_SPEC} xhs search --keyword "露营" --since-days 7 --pages 2 --pretty`);
+  console.log("      Search recent XHS results and keep items published in the last 7 days.");
+  console.log("");
   console.log(`  npx -y ${PACKAGE_SPEC} xhs hot-search --pretty`);
   console.log("      Call the XHS search hot list tool directly and print JSON.");
   console.log("");
@@ -1468,6 +1613,9 @@ function printHelp() {
   console.log(`  npx -y ${PACKAGE_SPEC} xhs user-posts --user-id "<user_id>" --pretty`);
   console.log("      Call the XHS creator posts tool directly and print JSON.");
   console.log("");
+  console.log(`  npx -y ${PACKAGE_SPEC} xhs user-posts --user-id "<user_id>" --since-days 30 --pretty`);
+  console.log("      Fetch recent creator posts until the publish-time boundary is reached.");
+  console.log("");
   console.log(`  npx -y ${PACKAGE_SPEC} douyin hot-search --pretty`);
   console.log("      Call the Douyin main hot search list tool directly and print JSON.");
   console.log("");
@@ -1615,6 +1763,9 @@ function printHelp() {
   console.log(`  npx -y ${PACKAGE_SPEC} wechat user-posts --url "<wechat_video_url_or_share_text>" --pretty`);
   console.log("      Call the WeChat Channels / 视频号 creator videos tool from a video link or share text.");
   console.log("");
+  console.log(`  npx -y ${PACKAGE_SPEC} sensitive-check text --text "<content>" --platform xhs --pretty`);
+  console.log("      Call the SocialDataX 敏感检测 text tool directly and print JSON.");
+  console.log("");
   console.log(`  npx -y ${PACKAGE_SPEC} list`);
   console.log("      List available skills.");
   console.log("");
@@ -1694,12 +1845,18 @@ function printHelp() {
   console.log("  --profile-url <profile-url-or-share-text>");
   console.log("  --user-id <user_id>");
   console.log("  --sec-user-id <sec_user_id>");
+  console.log("  --text <content>");
+  console.log("      Text content for sensitive-check text.");
+  console.log("  --platform <generic|xhs|douyin|kuaishou>");
+  console.log("      Target platform for sensitive-check text; default is generic.");
   console.log("  --pages <number>");
   console.log("      Fetch and merge N pages from the current starting point for search, comments, replies, creator content lists, and creator series.");
   console.log("  --all");
   console.log("      Continue comments, replies, creator content lists, and creator series until next_page_token is empty; not supported for search.");
   console.log("  --max-items <number>");
   console.log("      Stop after collecting this many primary items.");
+  console.log("  --since-days <1-365>");
+  console.log("      Keep search or creator content-list items with publish_time in the last N days. Search stays bounded by --pages; creator lists continue until the time boundary when --pages is omitted.");
   console.log("  --include-replies");
   console.log("      For comments commands, also fetch nested second-level replies for each returned first-level comment.");
   console.log("  --sort-type <general|time_descending|like_count_descending|comment_count_descending|collect_count_descending>");
@@ -1749,18 +1906,18 @@ function printRemovedMcpConfigHelp(command) {
   console.error("  com.socialdatax/wechat-channels-insights");
   console.error("");
   console.error("Use hosted streamable HTTP when your client supports remote MCP:");
-  console.error("  https://mcp.52choujiang.com/xhs/mcp");
-  console.error("  https://mcp.52choujiang.com/douyin/mcp");
-  console.error("  https://mcp.52choujiang.com/kuaishou/mcp");
-  console.error("  https://mcp.52choujiang.com/weibo/mcp");
-  console.error("  https://mcp.52choujiang.com/wechat/mcp");
+  console.error("  https://mcp.socialdatax.com/xhs/mcp");
+  console.error("  https://mcp.socialdatax.com/douyin/mcp");
+  console.error("  https://mcp.socialdatax.com/kuaishou/mcp");
+  console.error("  https://mcp.socialdatax.com/weibo/mcp");
+  console.error("  https://mcp.socialdatax.com/wechat/mcp");
   console.error("");
   console.error("For command/stdio-only clients, use mcp-remote:");
-  console.error(`  npx -y mcp-remote https://mcp.52choujiang.com/xhs/mcp --header "Authorization: Bearer <${PRIMARY_API_KEY_ENV}>"`);
-  console.error(`  npx -y mcp-remote https://mcp.52choujiang.com/douyin/mcp --header "Authorization: Bearer <${PRIMARY_API_KEY_ENV}>"`);
-  console.error(`  npx -y mcp-remote https://mcp.52choujiang.com/kuaishou/mcp --header "Authorization: Bearer <${PRIMARY_API_KEY_ENV}>"`);
-  console.error(`  npx -y mcp-remote https://mcp.52choujiang.com/weibo/mcp --header "Authorization: Bearer <${PRIMARY_API_KEY_ENV}>"`);
-  console.error(`  npx -y mcp-remote https://mcp.52choujiang.com/wechat/mcp --header "Authorization: Bearer <${PRIMARY_API_KEY_ENV}>"`);
+  console.error(`  npx -y mcp-remote https://mcp.socialdatax.com/xhs/mcp --header "Authorization: Bearer <${PRIMARY_API_KEY_ENV}>"`);
+  console.error(`  npx -y mcp-remote https://mcp.socialdatax.com/douyin/mcp --header "Authorization: Bearer <${PRIMARY_API_KEY_ENV}>"`);
+  console.error(`  npx -y mcp-remote https://mcp.socialdatax.com/kuaishou/mcp --header "Authorization: Bearer <${PRIMARY_API_KEY_ENV}>"`);
+  console.error(`  npx -y mcp-remote https://mcp.socialdatax.com/weibo/mcp --header "Authorization: Bearer <${PRIMARY_API_KEY_ENV}>"`);
+  console.error(`  npx -y mcp-remote https://mcp.socialdatax.com/wechat/mcp --header "Authorization: Bearer <${PRIMARY_API_KEY_ENV}>"`);
 }
 
 async function runXhsDirectCommand(args) {
@@ -1898,6 +2055,30 @@ async function runWechatDirectCommand(args) {
   process.stdout.write("\n");
 }
 
+async function runSensitiveCheckDirectCommand(args) {
+  const { options, positional } = parseCommandArgs(args);
+  const action = positional[0];
+  if (!action) {
+    throw new Error(
+      `Missing sensitive-check command. Use ${SENSITIVE_CHECK_DIRECT_ACTION_NAMES}.`
+    );
+  }
+  if (positional.length > 1) {
+    throw new Error(`Unexpected argument: ${positional[1]}`);
+  }
+  validateSensitiveCheckDirectActionOptions(action, options);
+
+  const operation = buildSensitiveCheckOperation(action, options);
+  const data = await callDirectOperation(operation);
+  const envelope = {
+    platform: operation.platform.id,
+    tool: operation.tool,
+    data,
+  };
+  process.stdout.write(JSON.stringify(envelope, null, options.pretty ? 2 : 0));
+  process.stdout.write("\n");
+}
+
 function buildXhsOperation(action, options) {
   switch (action) {
     case "hot-search":
@@ -2360,6 +2541,21 @@ function buildWechatOperation(action, options) {
   }
 }
 
+function buildSensitiveCheckOperation(action, options) {
+  switch (action) {
+    case "text":
+      return buildDirectOperation(
+        "text",
+        buildSensitiveCheckTextCall(options),
+        PLATFORMS["sensitive-check"]
+      );
+    default:
+      throw new Error(
+        `Unsupported sensitive-check command "${action}". Use ${SENSITIVE_CHECK_DIRECT_ACTION_NAMES}.`
+      );
+  }
+}
+
 function buildDirectOperation(operation, { tool, toolArguments }, platform = PLATFORMS.xhs) {
   return {
     platform,
@@ -2374,8 +2570,13 @@ function buildXhsSearchCall(options) {
   if (!options.keyword) {
     throw new Error("Missing --keyword for xhs search.");
   }
+  const sinceDays = parseOptionalSinceDays(options);
+  const requestedSortType =
+    options.sortType === undefined && sinceDays !== undefined
+      ? "time_descending"
+      : options.sortType || "general";
   const sortType = parseSemanticOption(
-    options.sortType || "general",
+    requestedSortType,
     "--sort-type",
     XHS_SEARCH_SORT_TYPES,
     XHS_LEGACY_SEARCH_SORT_TYPE_ALIASES,
@@ -2403,12 +2604,19 @@ function buildXhsSearchCall(options) {
   }
   if (options.sortType !== undefined) {
     toolArguments.sort_type = sortType;
+  } else if (sinceDays !== undefined) {
+    toolArguments.sort_type = "time_descending";
   }
   if (options.noteType !== undefined) {
     toolArguments.note_type = noteType;
   }
   if (options.publishTimeRange !== undefined) {
     toolArguments.publish_time_range = publishTimeRange;
+  } else if (sinceDays !== undefined) {
+    const nativeRange = nativePublishTimeRangeForSinceDays(sinceDays);
+    if (nativeRange) {
+      toolArguments.publish_time_range = nativeRange;
+    }
   }
   return {
     tool: "xhs_search_notes",
@@ -2475,6 +2683,7 @@ function buildDouyinSearchCall(options) {
   if (!options.keyword) {
     throw new Error("Missing --keyword for douyin search.");
   }
+  const sinceDays = parseOptionalSinceDays(options);
   const toolArguments = {
     keyword: options.keyword,
   };
@@ -2485,6 +2694,8 @@ function buildDouyinSearchCall(options) {
       DOUYIN_SEARCH_SORT_TYPES,
       DOUYIN_SEARCH_SORT_TYPES.join(", ")
     );
+  } else if (sinceDays !== undefined) {
+    toolArguments.sort_type = "time_descending";
   }
   if (options.publishTimeRange !== undefined) {
     toolArguments.publish_time_range = parseAllowedStringOption(
@@ -2493,6 +2704,11 @@ function buildDouyinSearchCall(options) {
       DOUYIN_SEARCH_PUBLISH_TIME_RANGES,
       DOUYIN_SEARCH_PUBLISH_TIME_RANGES.join(", ")
     );
+  } else if (sinceDays !== undefined) {
+    const nativeRange = nativePublishTimeRangeForSinceDays(sinceDays);
+    if (nativeRange) {
+      toolArguments.publish_time_range = nativeRange;
+    }
   }
   if (options.durationRange !== undefined) {
     toolArguments.duration_range = parseAllowedStringOption(
@@ -2555,6 +2771,7 @@ function buildWechatSearchCall(options) {
   if (!options.keyword) {
     throw new Error("Missing --keyword for wechat search.");
   }
+  const sinceDays = parseOptionalSinceDays(options);
   const toolArguments = {
     keyword: options.keyword,
   };
@@ -2565,6 +2782,8 @@ function buildWechatSearchCall(options) {
       WECHAT_SEARCH_SORT_TYPES,
       WECHAT_SEARCH_SORT_TYPES.join(", ")
     );
+  } else if (sinceDays !== undefined) {
+    toolArguments.sort_type = "latest";
   }
   if (options.durationRange !== undefined) {
     toolArguments.duration_range = parseAllowedStringOption(
@@ -2583,6 +2802,25 @@ function buildWechatSearchCall(options) {
   };
 }
 
+function buildSensitiveCheckTextCall(options) {
+  if (!options.text) {
+    throw new Error("Missing --text for sensitive-check text.");
+  }
+  const platform = parseAllowedStringOption(
+    options.platform || "generic",
+    "--platform",
+    SENSITIVE_CHECK_PLATFORMS,
+    SENSITIVE_CHECK_PLATFORMS.join(", ")
+  );
+  return {
+    tool: "check_sensitive_text",
+    toolArguments: {
+      text: options.text,
+      platform,
+    },
+  };
+}
+
 function buildDouyinRepliesCall(options) {
   if (!options.awemeId) {
     throw new Error("Missing --aweme-id for douyin replies.");
@@ -2755,7 +2993,8 @@ function shouldUsePaginatedDirectOutput(options) {
     options.all ||
       options.pages !== undefined ||
       options.maxItems !== undefined ||
-      options.includeReplies
+      options.includeReplies ||
+      options.sinceDays !== undefined
   );
 }
 
@@ -2777,6 +3016,7 @@ function parseDirectPaginationOptions(options) {
       options.maxItems === undefined
         ? undefined
         : parsePositiveIntegerOption(options.maxItems, "--max-items"),
+    sinceDays: parseOptionalSinceDays(options),
   };
 }
 
@@ -2785,7 +3025,14 @@ async function collectPaginatedDirectData(
   pagination,
   { includeReplies = false } = {}
 ) {
-  const pageLimit = pagination.all ? Number.POSITIVE_INFINITY : pagination.pages || 1;
+  const pageLimit =
+    pagination.all || shouldAutoPaginateSinceDays(operation, pagination)
+      ? Number.POSITIVE_INFINITY
+      : pagination.pages || 1;
+  const sinceDaysCutoff =
+    pagination.sinceDays === undefined
+      ? undefined
+      : cutoffPublishTimeForSinceDays(pagination.sinceDays);
   const collectedItems = [];
   const itemDedupeState = createPaginatedItemDedupeState();
   const seenNextMarkers = initialPaginationMarkers(operation);
@@ -2794,6 +3041,7 @@ async function collectPaginatedDirectData(
   let nextMarker;
   let parentContextData = {};
   let currentOperation = cloneDirectOperation(operation);
+  let stoppedBySinceDays = false;
 
   while (pageCount < pageLimit) {
     const pageData = await callDirectOperation(currentOperation);
@@ -2806,8 +3054,12 @@ async function collectPaginatedDirectData(
       directPageItems(pageData),
       itemDedupeState
     );
+    const filteredPage = filterItemsBySinceDays(pageItems, sinceDaysCutoff);
+    if (shouldStopAtSinceDaysBoundary(operation, sinceDaysCutoff, pageItems)) {
+      stoppedBySinceDays = true;
+    }
     const candidateItems = itemsForRemainingLimit(
-      pageItems,
+      filteredPage.items,
       collectedItems.length,
       pagination.maxItems
     );
@@ -2828,6 +3080,7 @@ async function collectPaginatedDirectData(
     if (
       !nextMarker ||
       reachedMaxItems(collectedItems, pagination.maxItems) ||
+      stoppedBySinceDays ||
       pageCount >= pageLimit
     ) {
       if (markerRepeated) {
@@ -2851,6 +3104,7 @@ async function collectPaginatedDirectData(
     items: collectedItems,
     pageCount,
     nextMarker,
+    stoppedBySinceDays,
   });
 }
 
@@ -2865,6 +3119,54 @@ function directPageItems(pageData) {
   return Array.isArray(pageData?.items) ? pageData.items : [];
 }
 
+function shouldAutoPaginateSinceDays(operation, pagination) {
+  return (
+    operation.operation === "user-posts" &&
+    pagination.sinceDays !== undefined &&
+    pagination.pages === undefined
+  );
+}
+
+function cutoffPublishTimeForSinceDays(sinceDays) {
+  return Math.floor(Date.now() / 1000) - sinceDays * 86400;
+}
+
+function itemPublishTimeSeconds(item) {
+  const value = item?.publish_time;
+  const timestamp =
+    typeof value === "number"
+      ? value
+      : typeof value === "string"
+        ? Number(value)
+        : NaN;
+  if (!Number.isFinite(timestamp) || timestamp <= 0) {
+    return undefined;
+  }
+  return timestamp;
+}
+
+function filterItemsBySinceDays(items, cutoffPublishTime) {
+  if (cutoffPublishTime === undefined) {
+    return { items };
+  }
+  return {
+    items: items.filter((item) => {
+      const publishTime = itemPublishTimeSeconds(item);
+      return publishTime !== undefined && publishTime >= cutoffPublishTime;
+    }),
+  };
+}
+
+function shouldStopAtSinceDaysBoundary(operation, cutoffPublishTime, items) {
+  if (operation.operation !== "user-posts" || cutoffPublishTime === undefined) {
+    return false;
+  }
+  return items.some((item) => {
+    const publishTime = itemPublishTimeSeconds(item);
+    return publishTime !== undefined && publishTime < cutoffPublishTime;
+  });
+}
+
 function createPaginatedItemDedupeState() {
   return { seenKeys: new Set() };
 }
@@ -3084,6 +3386,7 @@ function buildPaginatedData({
   items,
   pageCount,
   nextMarker,
+  stoppedBySinceDays,
 }) {
   const data = {
     ...(lastPageData && typeof lastPageData === "object" ? lastPageData : {}),
@@ -3094,6 +3397,9 @@ function buildPaginatedData({
   };
   delete data.next_page;
   data.next_page_token = nextMarker || "";
+  if (stoppedBySinceDays) {
+    data.stopped_by_since_days = true;
+  }
   return data;
 }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "socialdatax-skills",
-  "version": "0.2.11",
+  "version": "0.2.13",
   "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",
@@ -56,7 +56,12 @@
     "wechat",
     "wechat-channels",
     "wechat-channels-data",
-    "wechat-channels-search"
+    "wechat-channels-search",
+    "sensitive-check",
+    "sensitive-checking",
+    "content-safety",
+    "text-safety",
+    "sensitive-detection"
   ],
   "homepage": "https://socialdatax.com",
   "bugs": {
@@ -71,5 +76,9 @@
   },
   "dependencies": {
     "@modelcontextprotocol/sdk": "^1.29.0"
+  },
+  "overrides": {
+    "hono": "4.12.27",
+    "qs": "6.15.3"
   }
 }

package/skills/media-search/SKILL.md

@@ -76,6 +76,7 @@ Optional arguments:
 - Douyin `--pages <n>`: fetch and merge N search pages from the current starting point; continue with returned `next_page_token`.
 - Kuaishou `--pages <n>`: fetch and merge N search pages from the current starting point; continue with returned `next_page_token`.
 - `--max-items <n>`: stop after collecting N search results.
+- `--since-days <1-365>`: keep only results whose public `publish_time` is within the last N days. Search remains bounded by `--pages` and does not promise complete platform coverage.
 - `--pretty`: output formatting only.
 - Kuaishou `--page-token <next_page_token>`: opaque pagination token; omit it on the first search request. Continue only with the complete returned `next_page_token` from the same search pagination chain. Do not modify, truncate, redact, mask, omit, normalize, rebuild, generate, or replace the middle with ellipses.
 - Weibo `--page-token <next_page_token>`: opaque pagination token; omit it on the first search request. Continue only with the complete returned `next_page_token` from the same search pagination chain. Do not modify, truncate, redact, mask, omit, normalize, rebuild, generate, or replace the middle with ellipses.
@@ -126,6 +127,7 @@ Douyin content type filter values:
 - `image`: image/text posts.
 
 The command prints JSON with `platform`, `tool`, `arguments`, and `data`. Search supports `--pages` and `--max-items`, but not `--all`, because search has no stable complete-result boundary. Multi-page output keeps merged results in `data.items` and adds `page_count`, `item_count`, and the next-page marker.
+With CLI `--since-days <n>`, XHS and Douyin search automatically prefer newest-first sorting and the closest native publish-time range unless the user explicitly sets sort or publish-time filters; WeChat Channels search defaults to `latest`; Kuaishou and Weibo only apply CLI-side `publish_time` filtering.
 Kuaishou search pagination:
 - Continue only when `next_page_token` is not empty.
 - Pass the complete returned `next_page_token` back unchanged as `page_token` for the same search pagination chain. Do not modify, truncate, redact, mask, omit, normalize, rebuild, generate, or replace the middle with ellipses.
@@ -198,6 +200,7 @@ Do not pass `page` to `wechat_search_videos`; omit `page_token` on the first req
 - `sort_type`: optional, one of `all`, `latest`, `popular`; omit it for the default sort.
 - `duration_range`: optional duration filter, one of `all`, `under_5_min`, `between_5_and_20_min`, `over_20_min`; omit it for no duration filter.
 Continue WeChat Channels pagination only when `next_page_token` is not empty. Pass the complete returned `next_page_token` back unchanged as `page_token` for the same keyword and filter chain.
+`--since-days` uses CLI-side filtering only and is not an MCP tool argument; for MCP-only calls, request newest-first/native publish-time filters where available and filter returned `publish_time` values in your analysis.
 
 ## Output Guidance
 

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

@@ -73,6 +73,7 @@ Optional arguments:
 - `--pages <n>`: fetch and merge N pages of creator content or creator series.
 - `--all`: continue until `next_page_token` is empty; there is no default item or page cap.
 - `--max-items <n>`: stop after collecting N creator content or series items.
+- `--since-days <1-365>`: keep only creator content whose public `publish_time` is within the last N days. When `--pages` is omitted, the CLI continues creator content lists until the publish-time boundary is reached.
 - `--pretty`: output formatting only.
 - Kuaishou `--user-id <user_id>`: preferred when the creator user_id is already known.
 - Kuaishou `--profile-url <profile_url_or_share_text>`: use for a profile URL, short link, or profile share text.
@@ -84,6 +85,7 @@ Optional arguments:
 Use either the ID option or the profile URL option for a single command, not both.
 
 The command prints JSON with `platform`, `tool`, `arguments`, and `data`. Multi-page output keeps merged creator content or series items in `data.items` and adds `page_count`, `item_count`, and `next_page_token`.
+For recent creator research, prefer CLI `--since-days 30` or another user-specified day window. `--since-days` applies to creator content lists only, not Douyin `user-series`.
 
 ## Safety Boundary
 
@@ -124,6 +126,7 @@ Weibo creator post pagination uses opaque `page_token` values; pass the complete
 - `wechat_get_user_posted_videos_by_user_id`: preferred when the WeChat Channels / 视频号 `@finder` user_id is already known.
 - `wechat_get_user_posted_videos_by_url`: use a WeChat Channels / 视频号 video link or share text to resolve the author and list that creator's videos.
 WeChat Channels / 视频号 creator video pagination uses opaque `page_token` values; pass the complete returned `next_page_token` back unchanged for the same user. Do not modify, truncate, redact, mask, omit, normalize, rebuild, generate, or replace the middle with ellipses.
+`--since-days` uses CLI-side filtering only and is not an MCP tool argument; for MCP-only calls, continue pages as needed and filter returned `publish_time` values in your analysis.
 
 ## Output Guidance
 

package/skills/sensitive-check/SKILL.md

@@ -0,0 +1,71 @@
+---
+name: "sensitive-check"
+description: "Check draft text for sensitive-content risks before publishing. Supports generic, xhs, douyin, and kuaishou contexts through SocialDataX."
+metadata:
+  openclaw:
+    requires:
+      env:
+        - "SOCIALDATAX_API_KEY"
+      bins:
+        - "node"
+        - "npm"
+    primaryEnv: "SOCIALDATAX_API_KEY"
+    install:
+      - kind: "node"
+        package: "socialdatax-skills"
+        bins: []
+    emoji: "🛡️"
+    homepage: "https://socialdatax.com/?from=npm"
+---
+<!-- AUTO-GENERATED from socialdatax-skill-source. Do not edit directly; run `node scripts/generate_socialdatax_skills.mjs`. -->
+
+# 敏感检测 SocialDataX
+
+Use this skill when the user wants 敏感检测, sensitive check, content safety review, or platform-aware review for text drafts before publishing.
+
+Current platform support:
+
+- Text sensitive-content detection through `check_sensitive_text` for `generic`, `xhs`, `douyin`, and `kuaishou` contexts.
+
+## 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。
+
+## Preferred Direct CLI
+
+Prefer the direct CLI when the agent can run shell commands. It does not require MCP server configuration:
+
+```bash
+npx -y socialdatax-skills@latest sensitive-check text --text "<content>" --platform xhs --pretty
+```
+
+Required arguments:
+
+- `sensitive-check text --text <content>`: required text to check. Use the user's draft text for analysis, but do not store it in the skill.
+
+Optional arguments:
+
+- `--platform <generic|xhs|douyin|kuaishou>`: platform context; default is `generic`.
+- `--pretty`: output formatting only.
+
+Use this skill when the user wants 敏感检测, sensitive check, content safety review, or platform-aware preflight review for draft text.
+The command prints JSON with `platform`, `tool`, and `data`; it does not echo the original text back in CLI arguments. The service returns `violation`, `risk_level`, `types`, `highlights`, `summary`, `platform`, and `suggestions` when available.
+This v1 skill checks text only. Image sensitive detection is intentionally out of scope until a separate image tool is published.
+
+## 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. Prefer the direct CLI; hosted MCP tools are optional when the current agent already supports authenticated streamable HTTP MCP.
+
+## MCP Tools
+
+MCP tools matching the direct CLI commands above:
+
+- `check_sensitive_text`
+
+If MCP tools are already available in the current agent, call `check_sensitive_text` with `text` and optional `platform`: `generic`, `xhs`, `douyin`, or `kuaishou`.
+
+## Output Guidance
+
+Report whether there is a violation, the risk level, detected types, brief highlights, and concrete rewrite suggestions.
+Do not echo the full original text back unless the user explicitly asks; prefer short highlights and safer rewrite guidance.

package/skills/sensitive-check/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "Sensitive Check"
+  short_description: "Check draft text risks"
+  default_prompt: "Use $sensitive-check to check text drafts for sensitive-content risks with SocialDataX."
+
+policy:
+  allow_implicit_invocation: true

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

@@ -168,6 +168,7 @@ Optional arguments:
 - `--pages <n>`: fetch and merge N pages for search, comments, replies, creator posts, or creator series.
 - `--all`: fetch comments, replies, creator posts, or creator series until `next_page_token` is empty; do not use it for search.
 - `--max-items <n>`: stop after collecting N primary results.
+- `--since-days <1-365>`: keep search or creator content-list items whose public `publish_time` is within the last N days. Search stays bounded by `--pages`; creator content lists continue until the publish-time boundary when `--pages` is omitted.
 - `--include-replies`: for first-level comments, also fetch nested second-level replies under each returned comment.
 - `--sort-type`, `--note-type`, `--publish-time-range`, `--duration-range`, and `--content-type`: apply only to XHS, Douyin, or WeChat Channels keyword research commands when the user asks for filtering; Kuaishou and Weibo search currently use `--keyword` and optional `--page-token`.
 - `--comment-id`: required for reply/sub-comment commands together with the content ID.
@@ -185,6 +186,7 @@ Optional arguments:
 ## Choose The Narrowest Entry
 
 Use the most specific direct CLI command for the user's task instead of forcing every request through keyword research. The command prints JSON with `platform`, `tool`, `arguments`, and `data`.
+When the user asks for recent content, pass CLI `--since-days <n>` with bounded `--pages`; keep in mind this filters returned `publish_time` values and does not promise complete platform coverage.
 
 ## Safety Boundary