oc-browser-relay 1.0.1 → 1.0.2

package/skills/oc-browser-relay-xiaohongshu/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: oc-browser-relay-xiaohongshu
-description: Publish Xiaohongshu (小红书 / RED) notes and search/list Xiaohongshu posts through the oc-browser-relay-xiaohongshu plugin tools backed by the local ChromeAgent Relay service. Use when the user wants to 发小红书、发布图文、保存草稿、搜索小红书帖子、获取帖子列表、找对标内容、导出搜索结果，或检查小红书连接是否正常。 Prefer oc-browser-relay-xiaohongshu Xiaohongshu tools over generic browser automation when this plugin is available.
+description: Publish Xiaohongshu (小红书 / RED) notes and search/list Xiaohongshu posts through the oc-browser-relay-xiaohongshu plugin tools backed by the local ChromeAgent Relay service. Use when the user wants to 发小红书、发布图文、保存草稿、搜索小红书帖子、获取帖子列表、找对标内容、导出搜索结果、打开小红书首页、打开小红书创作者中心，或检查小红书连接是否正常。 Prefer oc-browser-relay-xiaohongshu Xiaohongshu tools over generic browser automation when this plugin is available.
 ---
 
 # Oc Browser Relay Xiaohongshu
@@ -19,6 +19,8 @@ The user should feel like they are asking for:
 - 存草稿
 - 搜帖子
 - 导出结果
+- 打开小红书首页
+- 打开小红书创作者中心
 - 看看连接有没有问题
 
 Do the technical selection internally.
@@ -27,19 +29,20 @@ Do the technical selection internally.
 
 Prefer these tools first:
 
-- `xhs_publish_note`
-- `xhs_save_note_draft`
-- `xhs_search_notes`
-- `export_to_csv`
+- `xiaohongshu_open_home`
+- `xiaohongshu_open_creator_center`
+- `xiaohongshu_publish_note`
+- `xiaohongshu_save_draft`
+- `xiaohongshu_search_notes`
 
 Use these only when needed for diagnosis or lower-level handling:
 
-- `chromeagent_relay_health`
-- `chromeagent_relay_list_tools`
-- `chromeagent_relay_execute_tool`
-- `chromeagent_relay_wait_task`
-- `xhs_list_runtimes`
-- `xhs_list_tabs`
+- `browser_health`
+- `browser_list_tools`
+- `browser_execute_tool`
+- `browser_wait_task`
+- `browser_list_runtimes`
+- `browser_list_tabs`
 
 Do not default to the browser tool if oc-browser-relay-xiaohongshu can complete the task.
 
@@ -70,9 +73,34 @@ If you must use a lower-level diagnostic tool, do it silently and summarize in h
 
 ## Intent routing
 
+### 0) Open Xiaohongshu pages
+
+Use dedicated open tools when the user just wants a page opened.
+
+Typical phrases:
+
+- 打开小红书首页
+- 打开首页
+- 进入小红书首页
+- 打开小红书创作者中心
+- 打开创作者中心
+- 进入创作平台
+
+Tool selection:
+
+- Homepage intent → `xiaohongshu_open_home`
+- Creator center / 创作平台 intent → `xiaohongshu_open_creator_center`
+
+Rules:
+
+- Prefer these tools over generic browser automation.
+- Do not ask the user for URLs unless they explicitly want a custom page.
+- If the user says “打开小红书” without specifying, default to `xiaohongshu_open_home`.
+- If opening fails, explain it as a connection/browser readiness issue in plain language.
+
 ### 1) Publish now
 
-Use `xhs_publish_note` when the user clearly wants immediate posting.
+Use `xiaohongshu_publish_note` when the user clearly wants immediate posting.
 
 Typical phrases:
 
@@ -102,7 +130,7 @@ Rules:
 
 ### 2) Save draft
 
-Use `xhs_save_note_draft` when the user wants preparation without publishing.
+Use `xiaohongshu_save_draft` when the user wants preparation without publishing.
 
 Typical phrases:
 
@@ -115,7 +143,7 @@ Use the same validation rules as publish.
 
 ### 3) Search or get a list of posts
 
-Use `xhs_search_notes` when the user wants discovery, examples, competitors, or note lists.
+Use `xiaohongshu_search_notes` when the user wants discovery, examples, competitors, or note lists.
 
 Typical phrases:
 
@@ -137,6 +165,7 @@ Useful inputs:
 - `filters`
 - `detailTargetCount` — when the user wants detailed note info (title, content, comments, interactions), not just the search list
 - `randomizeOrder` — randomize the order of detail collection (default true)
+- `saveToCsv` — pass `true`（默认）自动生成文件名并保存到 workspace 下的 `xhs/` 目录（`xhs/xhs_{keyword}_{timestamp}.csv`），或传自定义路径，`false` 不保存
 - optional legacy shorthands: `sort`, `noteType`
 
 Prefer `filters` over shorthand parameters.
@@ -155,24 +184,18 @@ If the user asks for “获取列表”, return a concise summary first. Offer C
 
 ### 4) Export results
 
-Use `export_to_csv` after search when the user wants:
+Use `xiaohongshu_search_notes` with `saveToCsv` parameter when the user wants:
 
 - 导出结果
 - 保存成 CSV
 - 发给同事分析
 - 留档
 
-Prefer a clear absolute output path.
-
-If the user did not give one, suggest a sensible path and ask once.
-
-Example:
-
-- `/Users/rui/Desktop/xiaohongshu-results.csv`
+The tool saves results as CSV by default to the workspace `xhs/` directory with auto-generated filename (`xhs/xhs_{keyword}_{timestamp}.csv`). You can also specify a custom path.
 
 ### 5) Check whether the setup is working
 
-When the user asks why publishing/searching failed, first treat it as a connection problem, not a technical debugging session.
+When the user asks why publishing/searching/opening failed, first treat it as a connection problem, not a technical debugging session.
 
 Typical phrases:
 
@@ -183,10 +206,10 @@ Typical phrases:
 
 Diagnosis order:
 
-1. `chromeagent_relay_health`
-2. `xhs_list_tabs`
-3. `xhs_list_runtimes` only if needed internally
-4. `chromeagent_relay_list_tools` only if tool exposure looks wrong
+1. `browser_health`
+2. `browser_list_tabs`
+3. `browser_list_runtimes` only if needed internally
+4. `browser_list_tools` only if tool exposure looks wrong
 
 Translate the result into plain language.
 
@@ -250,6 +273,8 @@ Preferred progress updates:
 - 我先帮你存成草稿
 - 我先搜一批结果
 - 已经导出成 CSV
+- 我先帮你打开首页
+- 我先帮你打开创作者中心
 
 Preferred result style:
 
@@ -257,6 +282,8 @@ Preferred result style:
 - 草稿已保存，还没发布
 - 已搜到 30 条图文笔记
 - 连接正常
+- 首页已打开
+- 创作者中心已打开
 - 现在还发不了，因为浏览器扩展没连上
 
 Avoid long technical explanations by default.
@@ -266,6 +293,7 @@ Avoid long technical explanations by default.
 - If publish intent is ambiguous, choose draft.
 - If search scope is vague, use a moderate `targetCount` first.
 - If export is likely useful, offer it after summarizing search results.
+- If the user asks to open Xiaohongshu and does not specify which page, default to `xiaohongshu_open_home`.
 - If a lower-level tool returns an async action, wait properly instead of repeatedly retrying the original request.
 - Prefer one clean answer over multiple fragmented status messages.
 
@@ -275,6 +303,6 @@ The skill is working well when the user experience feels like this:
 
 - they ask in plain Chinese
 - the agent responds in plain Chinese
-- posting/search/export works without exposing internal terms
+- opening/posting/search/export works without exposing internal terms
 - failures are explained in everyday language
 - the user never has to think about runtimes or bridge internals unless they explicitly want debugging

package/skills/oc-sycm-live-metrics/SKILL.md

@@ -0,0 +1,109 @@
+---
+name: oc-sycm-live-metrics
+description: Capture live metrics from SYCM (生意参谋) home page through the oc-sycm-live-metrics plugin tools backed by the local ChromeAgent Relay service. Use when the user wants to 采集生意参谋实时数据、抓取生意参谋首页指标、获取实时经营数据，或检查生意参谋采集连接是否正常。
+---
+
+# Oc SYCM Live Metrics
+
+Use oc-sycm-live-metrics as the default path for SYCM live metrics data collection.
+
+## Main goal
+
+Make SYCM live metrics collection feel simple and straightforward.
+
+The user should feel like they are asking for:
+
+- 帮我采集生意参谋实时数据
+- 抓一下生意参谋首页的指标
+- 看看现在的实时经营数据
+- 导出生意参谋数据
+- 看看连接有没有问题
+
+Do the technical selection internally.
+
+## Default tool preference
+
+Prefer this tool first:
+
+- `sycm_capture_live_metrics`
+
+Use these only when needed for diagnosis:
+
+- `browser_health`
+- `browser_list_runtimes`
+- `browser_list_tabs`
+
+## User-facing language
+
+Use plain language.
+
+Prefer saying:
+
+- 生意参谋连接
+- 浏览器连接
+- 连接正常
+- 还没连上
+- 我先帮你检查一下
+- 我开始帮你采集
+
+Avoid technical terms unless debugging.
+
+## Intent routing
+
+### 1) Capture live metrics
+
+Use `sycm_capture_live_metrics` when the user wants SYCM live data.
+
+Typical phrases:
+
+- 帮我采集生意参谋实时数据
+- 抓一下生意参谋首页的指标
+- 看看现在的经营数据
+- 采集生意参谋数据
+
+Optional inputs:
+
+- `url` — SYCM home page URL (default: https://sycm.taobao.com/portal/home.htm)
+- `metricPeriodLabel` — metric period label (default: "实时")
+
+Rules:
+
+- Data is automatically saved to workspace `sycm/` directory as JSON
+- Filename format: `sycm-live-metrics-{timestamp}.json`
+
+### 2) Check connection
+
+When the user asks why collection failed:
+
+Typical phrases:
+
+- 为什么采集不了
+- 怎么没反应
+- 帮我检查一下
+- 看看连接是不是坏了
+
+Diagnosis order:
+
+1. `browser_health`
+2. `browser_list_tabs`
+3. `browser_list_runtimes` if needed
+
+Translate results into plain language.
+
+## Response style
+
+Be short, calm, and action-first.
+
+Preferred updates:
+
+- 我先检查一下连接
+- 我开始帮你采集
+- 正在打开生意参谋页面
+- 正在采集实时数据
+
+Preferred results:
+
+- 已采集完成，实时数据都拿到了
+- 连接正常
+- 现在还采集不了，因为浏览器扩展没连上
+- 数据已保存到 /path/to/file.json

package/bundled-relay/public/configs/task-templates/xiaohongshu_open_website.json

@@ -1,24 +0,0 @@
-{
-  "taskType": "open_website",
-  "platform": "xiaohongshu",
-  "name": "打开小红书网站",
-  "description": "打开小红书网站首页或创作平台",
-  "requiredFields": [],
-  "optionalFields": [
-    {
-      "name": "page",
-      "type": "string",
-      "description": "要打开的页面：home(首页) 或 creator(创作平台)",
-      "default": "home"
-    }
-  ],
-  "workflow": [
-    {
-      "stepId": "s1",
-      "tool": "open_tab",
-      "args": {
-        "url": "https://www.xiaohongshu.com"
-      }
-    }
-  ]
-}