Agent skill

Skill Xhs Comment Reply

by ZJU-REAL in ZJU-REAL/Easel

小红书评论互动运营:列出我的笔记、抓取某条笔记下的评论、按画像语气逐条回复、以及删除评论 (含自己发的回复)。基于 Playwright + 持久化登录态,headless 即可运行,与 skill-xhs-publisher 共用同一登录态。评论抓取走接口响应拦截(稳);回复/删除走 DOM 文本定位(无坐标)+ 逐字符输入反检测; 带已回复去重、逐条间隔防风控、dry-run 预演。用…

Apache-2.0Auto-check passedTesting & QA

Install Skill Xhs Comment Reply

skills CLI
$ npx skills add ZJU-REAL/Easel --skill skill-xhs-comment-reply -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ZJU-REAL/Easel skill-xhs-comment-reply --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ZJU-REAL/Easel.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/openclaw/skill-xhs-comment-reply .claude/skills/skill-xhs-comment-reply && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
skill-xhs-comment-reply
GitHub stars
3.4k
Token cost
~865 tokens
SKILL.md length
182 words
Files
3 (incl. references)
Skills in repo
114
Repo updated
First seen
Licence
Apache-2.0

At a glance

小红书评论互动运营:列出我的笔记、抓取某条笔记下的评论、按画像语气逐条回复、以及删除评论 (含自己发的回复)。基于 Playwright + 持久化登录态,headless 即可运行,与 skill-xhs-publisher 共用同一登录态。评论抓取走接口响应拦截(稳);回复/删除走 DOM 文本定位(无坐标)+ 逐字符输入反检测; 带已回复去重、逐条间隔防风控、dry-run 预演。用…

  • Tasks that involve Browser testing
  • SKILL.md covers 运行方式(Playwright,headless 可用), 能力范围, 与其他 xhs SKILL 的分工 and 风险提示(重要), plus 5 more sections
  • Calls python

What it does

Skill Xhs Comment Reply is an agent skill from ZJU-REAL/Easel. 小红书评论互动运营:列出我的笔记、抓取某条笔记下的评论、按画像语气逐条回复、以及删除评论 (含自己发的回复)。基于 Playwright + 持久化登录态,headless 即可运行,与 skill-xhs-publisher 共用同一登录态。评论抓取走接口响应拦截(稳);回复/删除走 DOM 文本定位(无坐标)+ 逐字符输入反检测; 带已回复去重、逐条间隔防风控、dry-run 预演。用 notes 列笔记或 fetch --url 贴链接,免手动拆 token。 触发:抓小红书评论 / 回复评论 / 删除评论 / 删评 / 维护评论区 / 看我某条笔记的评论。

Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `EASEL-META.md` and `references/commands.md`).

It sits in Testing & QA, covering Browser testing. It works with Xiaohongshu and Playwright. The repository describes itself as: An open-source AI agent for social media — discover trends, create content, publish everywhere, and learn what works across Xiaohongshu, Douyin, Zhihu, Bilibili, and more.🎨一个开源的… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Browser testing

Example prompts

  • “/skill-xhs-comment-reply”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 278f420. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Skill Xhs Comment Reply loads about 865 tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 77 tokens; SKILL.md has 182 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~865
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ZJU-REAL/Easel at commit 278f420, republished under its Apache-2.0 licence (© ZJU-REAL). 182 words, ~865 tokens.

Download SKILL.mdSave it as .claude/skills/skill-xhs-comment-reply/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
skill-xhs-comment-reply
description
小红书评论互动运营:列出我的笔记、抓取某条笔记下的评论、按画像语气逐条回复、以及删除评论 (含自己发的回复)。基于 Playwright + 持久化登录态,headless 即可运行,与 skill-xhs-publisher 共用同一登录态。评论抓取走接口响应拦截(稳);回复/删除走 DOM 文本定位(无坐标)+ 逐字符输入反检测; 带已回复去重、逐条间隔防风控、dry-run 预演。用 notes 列笔记或 fetch --url 贴链接,免手动拆 token。 触发:抓小红书评论 / 回复评论 / 删除评论 / 删评 / 维护评论区 / 看我某条笔记的评论。
layer
publish

小红书评论助手(xhs-comment-reply)

你是"小红书评论互动助手"。目标:把一条笔记下的评论拉出来,并在用户确认后,用符合画像语气 的回复逐条回评。确定性 IO(抓评论/定位回复框/发送)走 xhs_comment.py;回复文案由你结合 画像生成,脚本只负责把你给定的文本发出去——脚本不编内容。

运行方式(Playwright,headless 可用)

统一走确定性脚本 ../../shared/scripts/xhs_comment.py(CWD=项目根)。与 xhs_publish.py 共用同一持久化登录态(~/.easel-browser-profiles/XiaohongshuProfile), 登录一次两处通用——登录用 xhs_publish.py login(本 SKILL 不重复实现登录)。

依赖说明
playwright + chromium 内核xhs_comment.py check 验证
已扫码登录复用 xhs-publisher 的登录态;未登录先 xhs_publish.py login
定位笔记不用手动拆 token:notes 子命令列出你自己的笔记(标题+note_id+从接口取的 xsec_token);或抓某篇时直接 fetch --url '<完整笔记链接>'(自动解析 note-id 与 xsec_token)。仅在已有裸 id+token 时才用 --note-id+--xsec-token
干净网络 IP小红书对机房/代理出口常判风险,评论抓取/回复建议 --no-proxy 直连

能力范围

  • 列我的笔记 notes:从创作后台列出自己已发布的笔记(标题 + note_id + 尽力带的 xsec_token)——用户说"这条/某条笔记"时先用它定位,别自己写脚本捞 token。
  • 抓评论 fetch:--url '<笔记链接>'(推荐,自动解析)或 --note-id+--xsec-token;拦截 comment/page 接口响应,输出评论 JSON(id/昵称/内容/时间/属地/子评论)。
  • 回复 reply:按昵称定位评论 → 点「回复」→ 逐字符输入 → 发送;带去重与防风控间隔。
  • 删除 delete:删自己笔记下的评论(含自己发的回复)。按昵称(+内容片段去歧义)定位 → hover 出「···」→ 点「删除评论」→ 确认,全程文本/结构定位、无坐标;默认 dry-run,加 --exec 才真删(不可恢复)。
  • 不做:点赞/收藏/私信——需要时再按同法移植(选择器同源)。

与其他 xhs SKILL 的分工

  • xhs-comment-reply(本 SKILL) = 评论区互动:抓评论 + 回评。
  • xhs-publisher = 发布:发图文/视频。
  • xhs-analyzer = 分析:爆款规律、关键词矩阵、限流检测。
  • comment-insights = 评论情感/高频词/诉求量化分析(拿本 SKILL fetch 的评论 JSON 喂进去)。

风险提示(重要)

自动化回复存在被平台风控、限流、封号的风险。 默认提醒用户优先用测试号、小批量运行,回复内容 人工复核。脚本已内置反检测(--disable-blink-features=AutomationControlled + 逐字符输入 + zh-CN + 登录态持久化)+ 逐条间隔(默认 4s),但风险不可完全消除,使用者自行评估承担。

删除不可恢复:delete 默认 dry-run,只有用户在看过 dry-run 清单、明确确认后才加 --exec 真删; 用 --content 内容片段给同名评论去歧义,避免误删。

执行流程

check(环境就绪?)
  → 未登录 → 用 xhs_publish.py login 扫码(一次即可)
  → 用户说"这条/某条笔记" → notes 列出你的笔记,定位是哪条(拿到 note_id / 可用链接)
  → fetch(--url 或 note_id+token,抓评论 JSON)— 展示给用户看有哪些评论
  → 你按画像语气为选定评论逐条拟回复([{id,nickname,reply}])
  → 发布前人设检查(见下,回复也是对外发言)
  → reply(先默认 dry-run 让用户确认最终回复;确认后 --exec 真发)
  → 用 --replied-file 记录已回复 id,重跑自动跳过(防重复打扰)

别再手动捞 token:用户提到某条笔记时,先 notes 定位;能直接抓就 fetch --url(贴笔记链接即可)。只有拿不到链接时才引导用户去笔记页复制分享/打开链接。

Profile 感知(回复语气)

有 Profile 时:读 style.md(语气/口头禅)、audience.md(受众关系,粉丝叫法)、 preferences.md(红线/不回什么),据此拟回复——高赞/提问优先、按人设口吻、不同评论不用同一句。 无 Profile 时退到通用友好语气,并提示"指定画像回复更贴人设"。

发布前人设检查(有 Profile 时)

回复是以账号身份对外发言,同样走 AGENTS.md「发布前人设一致性检查」:用 skill-persona-check 比对 待发回复 × 画像,评分喂 python skills/shared/scripts/persona_gate.py check --score 85—— 低于 80 分时警告并给修改建议,但不阻断回复;用户已明确要发布就继续执行。批量回复可对整批语气统一评一次。

必做约束

  • 回复前必须让用户确认最终回复文案(先跑 reply(不加 --exec)dry-run 展示)。
  • 每条回复需含 nickname + reply;带上 id 可启用去重(强烈建议,避免重复回评)。
  • 同名昵称只能定位到第一个匹配——遇到重名评论提醒用户人工核对。
  • 抓评论/回复默认 --no-proxy(小红书走代理常被判风险)。
  • 首次回复或疑似平台改版:先加 --headed 观察,校验通过再 headless 批量。
  • 页面结构异常时改 xhs_comment.py 顶部的 SELECTORS 字典(单点集中维护),不要散改流程。

命令样例

全部命令(check/fetch/reply 参数、去重、首次 --headed 校验、与 comment-insights 串联)见 references/commands.md。

© ZJU-REAL, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/openclaw/skill-xhs-comment-reply of ZJU-REAL/Easel.

  • SKILL.md
  • EASEL-META.md
  • references/commands.md

Open the folder on GitHubat commit 278f420

Compare with similar skills

Skill Xhs Comment Reply next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Skill Xhs Comment Reply compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Xhs Comment Reply this skillZJU-REAL/Easel3.4k—~865Automated safety check: PassApache-2.0
Xhs Auto PublisherDjangoPeng/agentic-ai152—~570Automated safety check: PassMIT
Xiaohongshu WriterEXboys/skilllite170—~737Automated safety check: PassMIT
Xhs Article To ImagesPluviobyte/rnskill1.6k—~985Automated safety check: PassMIT
Xhs Video Linksdragon-hh/ai-boshu-crawler106—~653Automated safety check: PassNone
Web Application Testinganthropics/skills180k51 repos~966Automated safety check: PassApache-2.0

Similar skills

  • Xhs Auto Publisher

    DjangoPeng/agentic-ai

    面向云服务器的小红书图文自动发布 Skill。适用于需要在 Linux 云服务器上,通过 Playwright/CDP、二维码人工接管、登录缓存、龙虾代发飞书群图片消息、截图留痕与审计日志来完成小红书草稿或发布流程的场景。

    152 GitHub stars~570 tokensUpdated 3 mo ago
    Testing & QAAuto-check passed
  • Xiaohongshu Writer

    EXboys/skilllite

    小红书图文内容创作助手。必须传入 content(含 title、body、hashtags、thumbnail),建议 generatethumbnail=true。优先 Playwright HTML 截图生成封面,失败时回退 Pillow。

    170 GitHub stars~737 tokensUpdated 15 days ago
    Testing & QAAuto-check passed
  • Xhs Article To Images

    Pluviobyte/rnskill

    把 Markdown 长文转成小红书 3:4(1080×1440)图片组的 Agent skill。内置五套设计皮肤(E 雅刊·默认 / A 暖杏奶咖 / B 雾松青 / C 黛墨描金 / D 夜读鎏金)+ 女性向三主题(F 粉色王国 / G 乙游夜境 / H 吉卜力)× 多种页型;Agent 负责读文章、拆页和填 HTML,Playwright 渲染器负责逐张截图导出…

    1.6k GitHub stars~985 tokensUpdated 20 days ago
    Testing & QAAuto-check passed
  • Xhs Video Links

    dragon-hh/ai-boshu-crawler

    Extract Xiaohongshu user profile video/note links from a provided profile URL.

    106 GitHub stars~653 tokensUpdated 2 mo ago
    Testing & QAAuto-check passed
  • Web Application Testing

    anthropics/skills

    Official

    Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.

    180k GitHub starsUsed in 51 repos~966 tokens
    Testing & QAAuto-check passed
  • Playwright CLI

    sanity-io/sanity

    Official

    Automates browser interactions for web testing, form filling, screenshots, and data extraction.

    6.4k GitHub starsUsed in 18 repos~1.9k tokens
    Testing & QAAuto-check passed

More from ZJU-REAL/Easel

All 114 skills in this repo
  • Gzh Design

    ZJU-REAL/Easel

    微信公众号文章排版引擎:把 Markdown / Word(.docx) / PDF / 纯文本转成可直接粘贴进公众号编辑器的 HTML,自动章节编号、关键词标记、引言卡、目录、代码块、图片/GIF、作者签名;主题从 references/theme-index.md…

    3.4k GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • 微信公众号文章自动创作与发布工具。给定参考文章、文字或文档,自动搜索整理全网相关信息、生成图文并茂的公众号文章,并发布到微信公众号草稿箱。特别强调反 AI 检测写作。

    3.4k GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Card Design

    ZJU-REAL/Easel

    社媒卡片视觉设计系统:提供配色、中文字体层级、满画幅布局、品类骨架和死空白/密度质检,避免模板化 PPT 与廉价 AI 感。

    3.4k GitHub stars~657 tokensUpdated today
    Auto-check passed
  • Ecom Details Image

    ZJU-REAL/Easel

    生成电商商品视觉方案:主图概念、场景图、详情页视觉方向和 AI 生图 Prompt. An agent skill from ZJU-REAL/Easel.

    3.4k GitHub stars~1.1k tokensUpdated today
    Auto-check: notes
  • Infographic

    ZJU-REAL/Easel

    将数据或文字内容转化为可视化信息图,支持静态(AntV)和动画 GIF 两种模式。当用户需要制作信息图、数据可视化、流程图、对比图、动画图表、GIF 图表、思维导图、SWOT 分析图时调用。本地渲染信息图/GIF 动画;要单张静态图片 URL 用 chart-visualization,要 CSV/JSON→整页报告用 data-report

    3.4k GitHub stars~643 tokensUpdated today
    Auto-check passed
  • Novel Writer

    ZJU-REAL/Easel

    长篇小说/网文连载创作:从世界观、人设和三级大纲写到逐章正文,并用文件化状态维护伏笔、前情和跨章一致性. An agent skill from ZJU-REAL/Easel.

    3.4k GitHub stars~1k tokensUpdated today
    Auto-check passed

Categories

Questions about Skill Xhs Comment Reply

What does Skill Xhs Comment Reply do?

小红书评论互动运营:列出我的笔记、抓取某条笔记下的评论、按画像语气逐条回复、以及删除评论 (含自己发的回复)。基于 Playwright + 持久化登录态,headless 即可运行,与 skill-xhs-publisher 共用同一登录态。评论抓取走接口响应拦截(稳);回复/删除走 DOM 文本定位(无坐标)+ 逐字符输入反检测; 带已回复去重、逐条间隔防风控、dry-run 预演。用…. Skill Xhs Comment Reply is an agent skill from ZJU-REAL/Easel.

When should I use Skill Xhs Comment Reply?

Skill Xhs Comment Reply fits situations like: tasks that involve Browser testing.

How do I install Skill Xhs Comment Reply in Claude Code?

Run `npx skills add ZJU-REAL/Easel --skill skill-xhs-comment-reply -a claude-code`. Or copy the skill folder (skills/openclaw/skill-xhs-comment-reply in ZJU-REAL/Easel) into .claude/skills/skill-xhs-comment-reply in your project. Claude Code loads it when a task matches its description.

How do I install Skill Xhs Comment Reply in Codex?

Run `npx skills add ZJU-REAL/Easel --skill skill-xhs-comment-reply -a codex`. Or copy the skill folder (skills/openclaw/skill-xhs-comment-reply in ZJU-REAL/Easel) into .agents/skills/skill-xhs-comment-reply in your project. Codex loads it when a task matches its description.

Can I use Skill Xhs Comment Reply in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ZJU-REAL/Easel --skill skill-xhs-comment-reply -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-xhs-comment-reply, .gemini/skills/skill-xhs-comment-reply, .github/skills/skill-xhs-comment-reply and .opencode/skills/skill-xhs-comment-reply in your project.

What does Skill Xhs Comment Reply need to run?

Going by SKILL.md and its folder, Skill Xhs Comment Reply needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Skill Xhs Comment Reply access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Skill Xhs Comment Reply safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Skill Xhs Comment Reply use?

Skill Xhs Comment Reply is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skill Xhs Comment Reply use?

About 865 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.5k tokens, read only when the agent opens those files.

What are the alternatives to Skill Xhs Comment Reply?

Skills that share tags, products or a category with Skill Xhs Comment Reply: Xhs Auto Publisher (DjangoPeng/agentic-ai, 152 stars), Xiaohongshu Writer (EXboys/skilllite, 170 stars), Xhs Article To Images (Pluviobyte/rnskill, 1.6k stars) and Xhs Video Links (dragon-hh/ai-boshu-crawler, 106 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Xhs Comment Reply?

ZJU-REAL (a GitHub organization) maintains it in ZJU-REAL/Easel, which has 3,376 GitHub stars. The repository holds 114 skills in this directory. The repository was last updated on October 9, 2026.

Source: ZJU-REAL/Easel on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.