socialdatax-skills 0.2.20 → 0.2.21

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 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.
+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 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
@@ -42,7 +42,9 @@ Common search phrases for this skill package:
 - `mp.weixin.qq.com article detail`
 - `SocialDataX content research`
 - `content research assistant`
-- `敏感检测 SocialDataX`
+- `敏感词检测`
+- `违禁词检测`
+- `文案发布前检查`
 - `sensitive check skill`
 - `content safety skill`
 - `text safety check`
@@ -54,7 +56,7 @@ Common search phrases for this skill package:
 - Kuaishou hosted MCP endpoint: `https://mcp.socialdatax.com/kuaishou/mcp`
 - Weibo hosted MCP endpoint: `https://mcp.socialdatax.com/weibo/mcp`
 - WeChat / 微信 hosted MCP endpoint: `https://mcp.socialdatax.com/wechat/mcp`
-- Sensitive Check hosted MCP endpoint: `https://mcp.socialdatax.com/sensitive-check/mcp`
+- Sensitive Words Check hosted MCP endpoint: `https://mcp.socialdatax.com/sensitive-check/mcp`
 - Hosted transport: `streamable-http`
 - Authentication: `Authorization: Bearer <SOCIALDATAX_API_KEY>`
 - Website: <https://socialdatax.com>
@@ -68,10 +70,10 @@ Common search phrases for this skill package:
 - Weibo future platform MCP registry name: `com.socialdatax/weibo-insights`
 - WeChat / 微信 current platform MCP registry name: `com.52choujiang/wechat-channels-insights`
 - WeChat / 微信 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`
+- 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: `0.2.20`
+- Current public capability version: `0.2.21`
 
 ## Direct CLI
 
@@ -174,7 +176,7 @@ For commands that accept `--page-token`, continue only with the complete returne
 
 Search pagination uses `--page-token` when continuing with a returned `next_page_token`. Omit `--page-token` on the first search request and pass the complete returned `next_page_token` only when continuing the same search chain.
 
-Transcript commands submit a bounded video speech-to-text job or check an existing job. Pass exactly one entrypoint for each call: URL/share text, platform content ID, or `--job-id`.
+Transcript commands submit a bounded video speech-to-text job or check an existing job. Pass exactly one entrypoint for each call: URL/share text, platform content ID, or `--job-id`. Completed get-job responses return transcript plus content context, not summary.
 
 Generated Agent Skill examples include `--source-client socialdatax-skills --source-platform <marketplace> --source-skill <skill-slug>` so SocialDataX can attribute direct CLI usage to the current marketplace Skill. Keep those values unchanged when running commands from a Skill; omit them for ad hoc CLI use. The direct CLI also accepts `SOCIALDATAX_SOURCE_CLIENT`, `SOCIALDATAX_SOURCE_PLATFORM`, and `SOCIALDATAX_SOURCE_SKILL` as environment-variable fallbacks.
 
@@ -301,7 +303,7 @@ Available skills:
 - `media-transcript`: submit and check video 口播转文字 / speech-to-text transcript jobs through direct CLI commands or 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.
+- `sensitive-check`: run 敏感词检测 / 违禁词检查 text checks; supports `generic`, `xhs`, `douyin`, and `kuaishou` platform contexts.
 
 Default install locations:
 
@@ -383,12 +385,12 @@ Current WeChat / 微信 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 提交后最多等待 15 秒.
 
-Current Sensitive Check workflows include:
+Current Sensitive Words Check workflows include:
 
-- Check draft text for 敏感检测 / sensitive-content risks before publishing.
+- Check draft text for 敏感词检测 / 违禁词检查 / 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.
+- Text checks are read-only. The service records submitted text and structured detection results for history, billing, and troubleshooting. Image sensitive detection is reserved for a future separate tool.
 
 ## XHS Tools
 
@@ -407,7 +409,7 @@ Current Sensitive Check workflows include:
 | `xhs_get_user_posted_notes_by_profile_url` | Fetch a paginated list of notes published by a creator from a profile link, short link, or share text. |
 | `xhs_submit_video_speech_text_by_note_url` | Submit an XHS video note speech-to-text transcript job from a note link, short link, or share text; submit waits up to 15 seconds. |
 | `xhs_submit_video_speech_text_by_note_id` | Submit an XHS video note speech-to-text transcript job when the caller already has a note ID; submit waits up to 15 seconds. |
-| `xhs_get_video_speech_text_job` | Check an XHS speech-to-text transcript job by job_id without creating a new task. |
+| `xhs_get_video_speech_text_job` | Check an XHS speech-to-text transcript job by job_id without creating a new task. Returns transcript plus content context, not summary. |
 
 ## Douyin Tools
 
@@ -428,7 +430,7 @@ Current Sensitive Check workflows include:
 | `douyin_get_user_series_by_profile_url` | Fetch a paginated list of short-drama series by a creator from a profile link, short link, or share text. |
 | `douyin_submit_video_speech_text_by_video_url` | Submit a Douyin video speech-to-text transcript job from a content page link, short link, or share text; submit waits up to 15 seconds. |
 | `douyin_submit_video_speech_text_by_aweme_id` | Submit a Douyin video speech-to-text transcript job when the caller already has an aweme_id; submit waits up to 15 seconds. |
-| `douyin_get_video_speech_text_job` | Check a Douyin speech-to-text transcript job by job_id without creating a new task. |
+| `douyin_get_video_speech_text_job` | Check a Douyin speech-to-text transcript job by job_id without creating a new task. Returns transcript plus content context, not summary. |
 
 ## Kuaishou Tools
 
@@ -447,7 +449,7 @@ Current Sensitive Check workflows include:
 | `kuaishou_get_user_posted_videos_by_profile_url` | Fetch a paginated list of works published by a creator 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. |
 | `kuaishou_submit_video_speech_text_by_video_url` | Submit a Kuaishou video speech-to-text transcript job from a work page link, short link, or share text; submit waits up to 15 seconds. |
 | `kuaishou_submit_video_speech_text_by_photo_id` | Submit a Kuaishou video speech-to-text transcript job when the caller already has a photo_id; submit waits up to 15 seconds. |
-| `kuaishou_get_video_speech_text_job` | Check a Kuaishou speech-to-text transcript job by job_id without creating a new task. |
+| `kuaishou_get_video_speech_text_job` | Check a Kuaishou speech-to-text transcript job by job_id without creating a new task. Returns transcript plus content context, not summary. |
 
 ## Weibo Tools
 
@@ -466,7 +468,7 @@ Current Sensitive Check workflows include:
 | `weibo_get_user_posts_by_profile_url` | Fetch a paginated list of posts published by a creator from a profile link, short link, or share text. |
 | `weibo_submit_video_speech_text_by_post_url` | Submit a Weibo video speech-to-text transcript job from a post URL, short link, or share text; submit waits up to 15 seconds. |
 | `weibo_submit_video_speech_text_by_post_id` | Submit a Weibo video speech-to-text transcript job when the caller already has a post_id; submit waits up to 15 seconds. |
-| `weibo_get_video_speech_text_job` | Check a Weibo speech-to-text transcript job by job_id without creating a new task. |
+| `weibo_get_video_speech_text_job` | Check a Weibo speech-to-text transcript job by job_id without creating a new task. Returns transcript plus content context, not summary. |
 
 ## WeChat Tools
 
@@ -485,13 +487,13 @@ Current Sensitive Check workflows include:
 | `wechat_get_user_posted_videos_by_url` | Fetch a paginated list of videos published by a creator from a video link or share text. |
 | `wechat_submit_video_speech_text_by_video_url` | Submit a WeChat Channels / 视频号 video speech-to-text transcript job from a video link or share text; submit waits up to 15 seconds. |
 | `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. |
+| `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. Returns transcript plus content context, not summary. |
 
-## Sensitive Check Tools
+## Sensitive Words 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. |
+| `check_sensitive_text` | Check text for 敏感词检测 / 违禁词检查 / sensitive-content risks with `generic`, `xhs`, `douyin`, or `kuaishou` context. |
 
 ## Quick Start
 
@@ -507,7 +509,7 @@ 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 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 / 微信, use the `wechat-channels-insights` listing; for 敏感检测, use the `sensitive-check` server.
+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 / 微信, use the `wechat-channels-insights` listing; for 敏感词检测 / 违禁词检查, 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.
 
@@ -523,7 +525,7 @@ 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 capability and currently backed by XHS, Douyin, Kuaishou, Weibo, WeChat Channels, and Sensitive Check tools.
+- [skills](skills): AgentSkills-compatible skills split by capability and currently backed by XHS, Douyin, Kuaishou, Weibo, WeChat Channels, and Sensitive Words 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 = "0.2.20";
+const PACKAGE_VERSION = "0.2.21";
 const PACKAGE_SPEC = `${PACKAGE_NAME}@latest`;
 const LOG_PREFIX = `[${PACKAGE_NAME}]`;
 const MIN_NODE_VERSION = "20.18.1";
@@ -25,6 +25,13 @@ const SOURCE_CLIENT_HEADER = "X-SocialDataX-Client";
 const SOURCE_PLATFORM_HEADER = "X-SocialDataX-Source-Platform";
 const SOURCE_SKILL_HEADER = "X-SocialDataX-Source-Skill";
 const SOURCE_ATTRIBUTION_PATTERN = /^[a-z0-9][a-z0-9-]{0,99}$/;
+export const TRANSCRIPT_JOB_DESCRIPTION_SUFFIX =
+  "Returns transcript plus content context, not summary.";
+
+export function buildTranscriptJobDescription(subject) {
+  return `Check ${subject} by job_id without starting a new task. ${TRANSCRIPT_JOB_DESCRIPTION_SUFFIX}`;
+}
+
 const AVAILABLE_SKILLS = [
   {
     name: "socialdatax-content-research-assistant",
@@ -524,7 +531,7 @@ const PLATFORMS = {
       {
         name: "xhs_get_video_speech_text_job",
         description:
-          "Check a video note speech-to-text transcript job by job_id without starting a new task.",
+          buildTranscriptJobDescription("a video note speech-to-text transcript job"),
       },
     ],
   },
@@ -608,7 +615,7 @@ const PLATFORMS = {
       {
         name: "douyin_get_video_speech_text_job",
         description:
-          "Check a Douyin video speech-to-text transcript job by job_id without starting a new task.",
+          buildTranscriptJobDescription("a Douyin video speech-to-text transcript job"),
       },
     ],
   },
@@ -688,7 +695,7 @@ const PLATFORMS = {
       {
         name: "kuaishou_get_video_speech_text_job",
         description:
-          "Check a Kuaishou video speech-to-text transcript job by job_id without starting a new task.",
+          buildTranscriptJobDescription("a Kuaishou video speech-to-text transcript job"),
       },
     ],
   },
@@ -772,7 +779,7 @@ const PLATFORMS = {
       {
         name: "weibo_get_video_speech_text_job",
         description:
-          "Check a Weibo video speech-to-text transcript job by job_id without starting a new task.",
+          buildTranscriptJobDescription("a Weibo video speech-to-text transcript job"),
       },
     ],
   },
@@ -849,13 +856,15 @@ const PLATFORMS = {
       {
         name: "wechat_get_video_speech_text_job",
         description:
-          "Check a WeChat Channels / 视频号 video speech-to-text transcript job by job_id without starting a new task.",
+          buildTranscriptJobDescription(
+            "a WeChat Channels / 视频号 video speech-to-text transcript job"
+          ),
       },
     ],
   },
   "sensitive-check": {
     id: "sensitive-check",
-    displayName: "Sensitive Check / 敏感检测",
+    displayName: "Sensitive Words Check / 敏感词检测",
     status: "public",
     registryName: "sensitive-check",
     futureRegistryName: "com.socialdatax/sensitive-check",
@@ -1901,7 +1910,7 @@ function printHelp() {
   console.log("      Submit or check a WeChat Channels / 视频号 video speech-to-text transcript job.");
   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("      Call the SocialDataX 敏感词检测 / 违禁词检查 text tool directly and print JSON.");
   console.log("");
   console.log(`  npx -y ${PACKAGE_SPEC} list`);
   console.log("      List available skills.");

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "socialdatax-skills",
-  "version": "0.2.20",
+  "version": "0.2.21",
   "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-transcript/SKILL.md

@@ -109,5 +109,7 @@ Do not start a duplicate transcript job only to poll status. Use the platform ge
 
 ## Output Guidance
 
-Return the transcript text when available. When a job is still running, include the `job_id`, status, and next action so the user or agent can check later.
+Return the transcript text and content context when available; include content IDs, titles or descriptions, author facts, and duration when the response provides them.
+This v1 surface does not return summary.
+When a job is still running, include the `job_id`, status, and next action so the user or agent can check later.
 If the result says no processable video resource is available or the job failed, report that as the observed job result instead of retrying with another platform.

package/skills/sensitive-check/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: "sensitive-check"
-description: "Check draft text for sensitive-content risks before publishing. Supports generic, xhs, douyin, and kuaishou contexts through SocialDataX."
+description: "Check draft text for 敏感词检测, 违禁词检查, content safety, copy compliance, and safer rewrite suggestions before publishing. Supports generic, xhs, douyin, and kuaishou contexts through SocialDataX."
 source_client: "socialdatax-skills"
 source_platform: "npm"
 source_skill: "sensitive-check"
@@ -22,9 +22,9 @@ metadata:
 ---
 <!-- AUTO-GENERATED from socialdatax-skill-source. Do not edit directly; run `node scripts/generate_socialdatax_skills.mjs`. -->
 
-# 敏感检测 SocialDataX
+# 敏感词检测与违禁词检查
 
-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.
+Use this skill when the user wants 敏感词检测, 违禁词检查, 敏感检测, 文案合规, 发布前检查, 能不能发, sensitive words, prohibited words, content safety review, or platform-aware review for text drafts before publishing.
 
 Current platform support:
 
@@ -53,8 +53,9 @@ Optional arguments:
 - `--pretty`: output formatting only.
 - `--source-client socialdatax-skills --source-platform npm --source-skill sensitive-check`: usage attribution for this Agent Skill; keep these values unchanged when running examples from this Skill.
 
-适用于文本敏感检测、content safety review、发布前风险检查和 safer rewrite suggestions for draft text.
+适用于敏感词检测、违禁词检查、文案发布前检查、content safety review、文案合规审核、能不能发判断和 safer rewrite suggestions 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.
+Service note: SocialDataX service records the submitted text and structured detection result for history, billing, and troubleshooting; the local CLI does not write API keys to local files or write local text copies.
 This v1 skill checks text only. Image sensitive detection is intentionally out of scope until a separate image tool is published.
 
 ## Safety Boundary

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

@@ -1,7 +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."
+  display_name: "敏感词检测"
+  short_description: "Check sensitive words"
+  default_prompt: "Use $sensitive-check to check draft text for sensitive words, prohibited words, and publishing risks with SocialDataX."
 
 policy:
   allow_implicit_invocation: true