小红书账号诊断 · XHS Account Analyzer — 用你的创作者后台官方数据体检 + 对标爆款
用你自己的创作者后台官方数据做账号体检。导出最近 N 条笔记的官方数据(曝光/封面点击率/涨粉/人均观看时长),逐条提炼关键词搜同题材爆款做对标,生成含①数据总表②转化漏斗健康度诊断③逐条笔记对标爆款+改进动作的 HTML 报告。不需要任何第三方 API key 或付费额度,用你 Chrome 里已登录的账号跑。当用户要分析"我自己的账号"最近笔记表现、点击…
石建
@fatmind
Install
$ openclaw skills install @fatmind/xhs-note-analyst账号分析(xhs-note-analyst)
⚠️ 本 skill 无法独立运行,必须先安装 webclaw3。
它依赖 webclaw3 提供的本地浏览器运行时(Relay
:3459+ pipeline:3460),直接复用你 Chrome 里已登录的账号——不必重新登录、不必交出密码、不易被站点访问限制拦截。没有 webclaw3,本 skill 的每一步浏览器操作都会立即失败。npx clawhub@latest install fatmind/webclaw3-browser-automation主品页面:https://clawhub.ai/fatmind/skills/webclaw3-browser-automation 源码与安装指南(3 步,约 5 分钟):https://github.com/fatmind/webclaw3
装好后对你的 Agent 说一句「检查 webclaw3 环境」确认 Relay 与 pipeline 就绪,再回来跑本 skill。
功能描述
分析你自己的账号,数据来自你的创作者后台官方看板(导出 Excel),不是爬来的第三方估算数字。流程:导出最近 N 条笔记(按首发时间倒序)→ 逐条提炼精准关键词 → 搜该词下的同题材爆款做对标 → 输出一份 HTML 报告:
- 数据总表:
min(notes_count, 实际笔记数)条,含标题/类型(图文/视频)/首发时间/已发布天数/曝光/日均曝光/观看量/封面点击率/点赞/评论/收藏/涨粉/分享/人均观看时长,按首发时间倒序; - 转化漏斗健康度诊断:点击率 → 内容留存 → 互动 → 涨粉 四层,各有数值与合格/偏弱/断档判断(点击率 10%–20% 合格;互动率 5%–10% 为爆款线;留存断档线按体裁分设);
- 逐条笔记:每条含 对标爆款表(同题材、过点赞门槛的高赞笔记,含标题+作者+点赞数)+ 3 条具体可执行的改进动作。
目标口径(2026-09-17 定,见 goal/business_plan.md):核心目标是涨粉,逐条笔记的改进动作必须能落到涨粉链路上(关注钩子/系列感/封面 CTR),「有用但不涨粉」型结论要显式指出。输出强制收成三段,逐条笔记最后汇总为一节:诊断(哪层漏斗断了,官方数据说话)→ 归因(封面/标题/正文结构/关注钩子的哪一环)→ 动作(下一条笔记具体改什么,一句话一条)。动作写完还要回填实验记录:对 goal/note-experiments.jsonl 里 outcomeDue 已到的 pending 实验,用本次官方数据判 verdict 并更新(outcome/verdict/attribution 三字段)。
和市面上的 skill 有什么不同:
- 大多数是爬别人的数据(榜单、竞品、KOL),本 skill 看的是你自己的后台真实数据——曝光、封面点击率、人均观看时长、涨粉数这些指标只有账号主人拿得到,爬虫拿不到;
- 不需要任何第三方数据平台的 API key,也不消耗付费额度:数据源就是你自己的创作者后台,浏览器动作由本机 webclaw3 运行时驱动;
- 竞对侧只取搜索结果页公开可见的标题、作者与点赞数,不抓取任何登录后才可见的他人数据。
前置条件
- webclaw3 已安装并运行(见顶部安装说明):它提供浏览器扩展与 Relay(HTTP
:3459),以及本地 pipeline 服务(:3460)——本 skill 内嵌的 LLM 子会话(关键词提炼 / 对标爆款筛选 / 改进动作生成)都经 pipeline 代跑。 - 浏览器已登录创作者后台(creator 后台)与主站——你日常 Chrome 的登录态由 webclaw3 直接复用,无需重新登录。
- 本机安装
python3与openpyxl(用于解析创作者后台导出的 Excel 明细表)。 - 浏览器下载目录为
~/Downloads(导出 Excel 会落到这里)。
使用方式
node skill.mjs
从当前目录 input.json 读取入参;input.json 不存在时使用默认值。
入参(input.json)
| 字段 | 类型 | 默认值 | 说明 |
|---|---|---|---|
notes_count | int | 5 | 分析最近多少条笔记(按首发时间倒序) |
keyword_per_note | int | 1 | 每条笔记提炼的关键词数量 |
report_path | string | <cwd>/账号分析报告_<日期>.html | 报告输出路径 |
output_dir | string | /tmp/xhs-note-analyst-output | 产出 res.json / data.md / HTML 报告的目录 |
output_files.result | string | res.json | 状态摘要文件名 |
output_files.data | string | data.md | 数据明细文件名 |
输出
report_path:HTML 报告(本地可直接打开预览),含三个板块与 full/partial 标注;res.json:{ status, summary, notes_count, note_count_analyzed, keywords, benchmark_shortages, report_path, output_dir },status∈ success / partial / failed;data.md:报告的数据明细版(总表/漏斗/逐条笔记/执行过程记录);- stdout:一行 JSON 摘要
{ status, summary, output_dir }。
Top skills in this category
API Gateway
@byungkyuCall third-party APIs through the Maton gateway, which injects the credential for an app the user has already connected. Use this skill when the user names a connected app and a concrete action in it - read a mailbox, query a CRM, file an issue, update a spreadsheet, etc.
HubSpot
@hith3shHubSpot CRM API integration with managed OAuth. Manage contacts, companies, deals, pipelines, tickets, products, line items, marketing emails, and workflows....
Master Marketing
@tevfikgulepAll-in-one marketing engine combining growth strategy, content remixing, and trend monitoring. Drive growth with data-driven strategies, repurposed content across all platforms, and real-time trend analysis.
Feishu Bridge
@alexanysConnect a Feishu (Lark) bot to Clawdbot via WebSocket long-connection. No public server, domain, or ngrok required. Use when setting up Feishu/Lark as a messaging channel, troubleshooting the Feishu bridge, or managing the bridge service (start/stop/logs). Covers bot creation on Feishu Open Platform, credential setup, bridge startup, macOS launchd auto-restart, and group chat behavior tuning.
Zoho CRM
@byungkyuZoho CRM API integration with managed OAuth. Manage leads, contacts, accounts, deals, and other CRM records. Use this skill when users want to read, create, update, or delete CRM records, search contacts, manage sales pipelines, access organization settings, manage users, or retrieve module metadata in Zoho CRM. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Requires network access and valid Maton API key. Calls run through the `maton` CLI with OAuth login, or over raw HTTP with a Maton API key where the CLI cannot be installed. Every call is authenticated as the user's connection and reaches only what that connection's authorization allows, which the provider enforces on every request; the endpoints documented here are the ones this skill uses, and any other endpoint of this app needs the user to ask for it by name. Default to read and list calls, and confirm every write or new connection with the user. This file also documents the three constructs that turn a Zoho CRM connection into automation, in the order they are used: the connection (the first step), a hosted function that runs a Zoho CRM action through the Maton SDK, and a trigger that calls that function on a schedule or on an event. Those sections are the platform's own reference text, shared with the api-gateway skill, with Zoho CRM examples; they add no Zoho CRM capability - Zoho CRM is not an event source, a trigger cannot read Zoho CRM data, and the files under `references/<source>/triggers.md` are the platform's event catalogues for the sources Maton offers (time, Calendly, GitHub, Gmail, HubSpot, Linear, Notion, Slack, Stripe).