socialdatax-skills 0.2.7 → 0.2.8

package/README.md

@@ -48,7 +48,7 @@ Common search phrases for this skill package:
 - Kuaishou current platform MCP registry name: `com.52choujiang/kuaishou-insights`
 - Kuaishou future platform MCP registry name: `com.socialdatax/kuaishou-insights`
 - Unified MCP registry name: none; this package installs skills and calls explicit platform services.
-- Current public capability version: `0.2.7`
+- Current public capability version: `0.2.8`
 
 ## Direct CLI
 
@@ -93,6 +93,8 @@ npx -y socialdatax-skills@latest kuaishou user-posts --profile-url "<profile_url
 
 The direct CLI prints a JSON envelope with `platform`, `tool`, `arguments`, and `data`.
 
+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 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.

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 = "0.2.7";
+const PACKAGE_VERSION = "0.2.8";
 const PACKAGE_SPEC = `${PACKAGE_NAME}@latest`;
 const LOG_PREFIX = `[${PACKAGE_NAME}]`;
 const MIN_NODE_VERSION = "20.18.1";

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "socialdatax-skills",
-  "version": "0.2.7",
+  "version": "0.2.8",
   "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-detail/SKILL.md

@@ -87,7 +87,7 @@ If MCP tools are already available in the current agent, use one of these tools:
 ## Output Guidance
 
 Return factual fields such as title or description, content, author, publish time, interaction counts, images, and media summary when available.
-For XHS detail results, preserve any returned `note_url` exactly, 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 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.
 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.

package/skills/media-search/SKILL.md

@@ -158,7 +158,7 @@ Continue Kuaishou pagination only when `next_page_token` is not empty. Pass the
 ## Output Guidance
 
 Summarize visible evidence separately from interpretation. Include useful content IDs, URLs, titles or descriptions, authors, counts, and publish time when the user needs traceability.
-For XHS search results, preserve any returned `note_url` exactly, including `xsec_token` query parameters. Do not modify, truncate, redact, mask, normalize, rebuild, or synthesize the URL from `note_id`.
+For XHS search 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`.
 For XHS `note_id`, copy the complete 24-character lowercase hexadecimal ID exactly; do not pass or display only a prefix.
 For Douyin search results, include `content_type` when the user needs traceability.
 For Douyin image/text search results, use returned `images` and treat `video.media_type="audio"` as an audio player resource rather than a video post.

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

@@ -191,6 +191,8 @@ Use numeric `page` only for `xhs_search_notes`. Do not pass `page` to `douyin_se
 ## Output Guidance
 
 For broad research, summarize visible evidence separately from interpretation and organize findings by platform, content angles, audience needs, trend signals, comment themes, creator positioning, and practical next steps.
+For XHS search or 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 detail `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.
 For comments, group observed themes before inferring sentiment or demand.
 For creators, separate profile facts from content-list evidence; include Douyin short-drama series facts when the series command is used and Kuaishou work-list evidence when Kuaishou commands are used.
 For hot-search, report ranking signals separately from keyword search results.