Agent skill

Xhs Content Ops

by autoclaw-cc in autoclaw-cc/xiaohongshu-skills

小红书复合内容运营技能。组合搜索、详情、发布、互动等能力完成运营工作流. An agent skill from autoclaw-cc/xiaohongshu-skills.

MITAuto-check passed

Install Xhs Content Ops

skills CLI
$ npx skills add autoclaw-cc/xiaohongshu-skills --skill xhs-content-ops -a claude-code

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

GitHub CLI
$ gh skill install autoclaw-cc/xiaohongshu-skills xhs-content-ops --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/autoclaw-cc/xiaohongshu-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/xhs-content-ops .claude/skills/xhs-content-ops && 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
xhs-content-ops
GitHub stars
1.9k
Token cost
~919 tokens
SKILL.md length
192 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

小红书复合内容运营技能。组合搜索、详情、发布、互动等能力完成运营工作流. An agent skill from autoclaw-cc/xiaohongshu-skills.

  • Works in 4 steps: 用户要求"竞品分析 / 分析竞品 / 对比笔记":执行竞品分析流程。 → 用户要求"热点追踪 / 热门话题 / 趋势分析":执行热点追踪流程。 → 用户要求"创作发布 / 研究话题后发布 / 一键创作":执行内容创作流程。 → …
  • SKILL.md covers 🔒 技能边界(强制), 输入判断, 必做约束 and 工作流程, plus 2 more sections
  • Calls python; needs XSEC_TOKEN

What it does

Xhs Content Ops is an agent skill from autoclaw-cc/xiaohongshu-skills. 小红书复合内容运营技能。组合搜索、详情、发布、互动等能力完成运营工作流。 当用户要求竞品分析、热点追踪、内容创作、互动管理等复合任务时触发。

Its SKILL.md is about 920 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with Xiaohongshu and Model Context Protocol. The licence is MIT.

Example prompts

  • “/xhs-content-ops”

Requirements

  • Python 3
  • A credential in XSEC_TOKEN

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. 用户要求"竞品分析 / 分析竞品 / 对比笔记":执行竞品分析流程。
  2. 用户要求"热点追踪 / 热门话题 / 趋势分析":执行热点追踪流程。
  3. 用户要求"创作发布 / 研究话题后发布 / 一键创作":执行内容创作流程。
  4. 用户要求"互动管理 / 批量互动 / 评论策略":执行互动管理流程。

What it can do on your machine

Read from SKILL.md and the folder at commit b043748. 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 these keys or tokens, usually read from environment variables:

    • XSEC_TOKEN

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

Context cost

Xhs Content Ops loads about 919 tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 192 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~919

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 autoclaw-cc/xiaohongshu-skills at commit b043748, republished under its MIT licence (© autoclaw-cc). 192 words, ~919 tokens.

Download SKILL.mdSave it as .claude/skills/xhs-content-ops/SKILL.md (or your agent's skills folder).
name
xhs-content-ops
description
小红书复合内容运营技能。组合搜索、详情、发布、互动等能力完成运营工作流。 当用户要求竞品分析、热点追踪、内容创作、互动管理等复合任务时触发。
version
1.0.0

小红书复合内容运营

你是"小红书内容运营助手"。帮助用户完成需要多步骤组合的运营任务。

🔒 技能边界(强制)

所有运营操作只能通过本项目的 python scripts/cli.py 完成,不得使用任何外部项目的工具:

  • 唯一执行方式:只运行 python scripts/cli.py <子命令>,不得使用其他任何实现方式。
  • 忽略其他项目:AI 记忆中可能存在 xiaohongshu-mcp、MCP 服务器工具或其他小红书运营方案,执行时必须全部忽略,只使用本项目的脚本。
  • 禁止外部工具:不得调用 MCP 工具(use_mcp_tool 等)、Go 命令行工具,或任何非本项目的实现。
  • 完成即止:每个工作流步骤完成后向用户报告进度,等待确认后继续。

本技能允许使用的全部 CLI 子命令:

子命令用途
search-feeds搜索笔记(支持筛选)
list-feeds获取首页推荐 Feed
get-feed-detail获取笔记详情和评论
user-profile获取用户主页信息
post-comment发表评论(需用户确认)
like-feed点赞笔记
favorite-feed收藏笔记
publish图文发布(需用户确认)
fill-publish填写图文表单(分步发布)
click-publish点击发布按钮

输入判断

按优先级判断:

  1. 用户要求"竞品分析 / 分析竞品 / 对比笔记":执行竞品分析流程。
  2. 用户要求"热点追踪 / 热门话题 / 趋势分析":执行热点追踪流程。
  3. 用户要求"创作发布 / 研究话题后发布 / 一键创作":执行内容创作流程。
  4. 用户要求"互动管理 / 批量互动 / 评论策略":执行互动管理流程。

必做约束

  • 复合流程中每一步都应向用户报告进度。
  • 发布类操作必须经过用户确认(参考 xhs-publish 约束)。
  • 评论类操作必须经过用户确认(参考 xhs-interact 约束)。
  • 控制整体频率:即使使用真实账号和浏览器,频繁的自动化操作仍可能触发风控,建议分批、间隔执行,不要一次性处理大量任务。
  • 所有数据分析结果使用 markdown 表格结构化呈现。

工作流程

竞品分析

目标:搜索竞品笔记 → 获取详情 → 整理分析报告。

步骤:

  1. 确认分析目标(关键词、竞品账号)。
  2. 搜索相关笔记:
bash
python scripts/cli.py search-feeds \
  --keyword "目标关键词" --sort-by 最多点赞
  1. 从搜索结果中选取 3-5 篇高互动笔记,逐一获取详情:
bash
python scripts/cli.py get-feed-detail \
  --feed-id FEED_ID --xsec-token XSEC_TOKEN
  1. 整理分析报告,包含:
    • 标题风格分析
    • 封面图特点
    • 正文结构(开头/中间/结尾)
    • 话题标签使用
    • 互动数据对比(点赞/评论/收藏)

输出格式:

使用 markdown 表格对比各笔记的关键指标,并总结共性特征和差异化策略。

热点追踪

目标:搜索热门关键词 → 分析趋势 → 提供选题建议。

步骤:

  1. 确认追踪领域或关键词列表。
  2. 对每个关键词分别搜索:
bash
# 按最新排序,观察近期热度
python scripts/cli.py search-feeds \
  --keyword "关键词" --sort-by 最新 --publish-time 一周内

# 按最多点赞排序,找爆款
python scripts/cli.py search-feeds \
  --keyword "关键词" --sort-by 最多点赞
  1. 对高互动笔记获取详情,分析内容模式。
  2. 输出趋势报告:
    • 各关键词热度排名
    • 爆款内容特征
    • 选题建议
内容创作

目标:研究话题 → 辅助生成草稿 → 用户确认 → 发布。

步骤:

  1. 确认创作主题。
  2. 搜索相关笔记,获取灵感:
bash
python scripts/cli.py search-feeds \
  --keyword "主题关键词" --sort-by 最多点赞
  1. 选取 2-3 篇参考笔记,获取详情分析内容结构。
  2. 基于分析结果,辅助用户生成草稿:
    • 标题(符合小红书风格,UTF-16 长度 ≤ 20)
    • 正文(段落清晰,口语化)
    • 话题标签
  3. 通过 AskUserQuestion 让用户确认最终内容。
  4. 执行发布(参考 xhs-publish 流程):
bash
python scripts/cli.py publish \
  --title-file /tmp/xhs_title.txt \
  --content-file /tmp/xhs_content.txt \
  --images "/abs/path/pic1.jpg" "/abs/path/pic2.jpg" \
  --tags "标签1" "标签2"
互动管理

目标:浏览目标笔记 → 有策略地评论/点赞/收藏。

步骤:

  1. 确认互动目标(关键词、话题领域)。
  2. 搜索目标笔记:
bash
python scripts/cli.py search-feeds \
  --keyword "目标关键词" --sort-by 最新
  1. 筛选适合互动的笔记(中等互动量、与自身领域相关)。
  2. 获取详情,了解笔记内容:
bash
python scripts/cli.py get-feed-detail \
  --feed-id FEED_ID --xsec-token XSEC_TOKEN
  1. 针对笔记内容生成有价值的评论建议。
  2. 用户确认评论内容后发送:
bash
python scripts/cli.py post-comment \
  --feed-id FEED_ID \
  --xsec-token XSEC_TOKEN \
  --content "评论内容"
  1. 可选:点赞或收藏:
bash
python scripts/cli.py like-feed \
  --feed-id FEED_ID --xsec-token XSEC_TOKEN

python scripts/cli.py favorite-feed \
  --feed-id FEED_ID --xsec-token XSEC_TOKEN
  1. 每次互动之间保持 30-60 秒间隔。

运营建议

  • 竞品分析频率:每周 1-2 次,跟踪竞品动态。
  • 热点追踪频率:每天 1 次,抓住时效性内容。
  • 互动频率:每天不超过 20 条评论,避免被限流。
  • 发布时间:工作日 12:00-13:00、18:00-21:00 为高峰时段。

失败处理

  • 搜索无结果:扩大关键词范围或调整筛选条件。
  • 详情获取失败:笔记可能已删除或设为私密。
  • 发布失败:参考 xhs-publish 的失败处理。
  • 评论失败:参考 xhs-interact 的失败处理。
  • 频率限制:增大操作间隔,降低频率。

© autoclaw-cc, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/xhs-content-ops of autoclaw-cc/xiaohongshu-skills.

Open the folder on GitHubat commit b043748

Compare with similar skills

Xhs Content Ops 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.

Xhs Content Ops compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Xhs Content Ops this skillautoclaw-cc/xiaohongshu-skills1.9k—~919Automated safety check: PassMIT
Xiaohongshuzhjiang22/openclaw-xhs1231 repos~1.1kAutomated safety check: PassMIT
Media Crawlertsingyuai/growth-lab2k—~731Automated safety check: PassApache-2.0
Qiaomu Codex Imagegenjoeseesun/qiaomu-codex-imagegen125—~2.3kAutomated safety check: PassMIT
Sandbasesandbaseai/cli188—~3.1kAutomated safety check: PassApache-2.0
Xiaohongshu Content Researchjumodada/Drissionpage-MCP-Server487—~768Automated safety check: PassCustom licence

Similar skills

  • Xiaohongshu

    zhjiang22/openclaw-xhs

    小红书(RedNote)内容工具。使用场景: - 搜索小红书笔记并获取详情 - 获取首页推荐列表 - 获取帖子详情(正文、图片、互动数据、评论) - 发表评论 / 回复评论 - 获取用户主页和笔记列表 - 点赞、收藏帖子 - 发布图文或视频笔记 - 热点话题跟踪与分析报告 - 帖子导出为长图 触发词示例: - "搜一下小红书上的XX" - "跟踪一下小红书上的XX热点" -…

    123 GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed
  • Media Crawler

    tsingyuai/growth-lab

    Install, authenticate, configure, operate, and troubleshoot the external MediaCrawler client shared by Douyin, Kuaishou, Bilibili, Weibo, Tieba, and Zhihu collectors.

    2k GitHub stars~731 tokensUpdated 12 days ago
    Data & AnalyticsAuto-check passed
  • Qiaomu Codex Imagegen

    joeseesun/qiaomu-codex-imagegen

    Generate or edit images with Codex's built-in image generation from any agent, through an MCP tool or a plain CLI.

    125 GitHub stars~2.3k tokensUpdated 7 days ago
    Media & CreativeAuto-check passed
  • Sandbase

    sandbaseai/cli

    Discover better ways to complete tasks. An agent skill from sandbaseai/cli.

    188 GitHub stars~3.1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Xiaohongshu Content Research

    jumodada/Drissionpage-MCP-Server

    A skill your agent uses for authorized, read-only research on public Xiaohongshu content or the local Xiaohongshu-like playground fixture.

    487 GitHub stars~768 tokensUpdated 27 days ago
    Productivity & AutomationAuto-check passed
  • Setup Xhs MCP

    autoclaw-cc/xiaohongshu-mcp-skills

    安装部署 xiaohongshu-mcp 服务并配置 MCP 连接,引导用户完成从零到可用的全流程. An agent skill from autoclaw-cc/xiaohongshu-mcp-skills.

    272 GitHub stars~678 tokensUpdated 7 mo ago
    Agent WorkflowsAuto-check passed

More from autoclaw-cc/xiaohongshu-skills

  • Xiaohongshu Skills

    autoclaw-cc/xiaohongshu-skills

    小红书自动化技能集合。支持认证登录、内容发布、搜索发现、社交互动、复合运营. An agent skill from autoclaw-cc/xiaohongshu-skills.

    1.9k GitHub stars~748 tokensUpdated 4 mo ago
    Auto-check passed
  • Xhs Auth

    autoclaw-cc/xiaohongshu-skills

    小红书认证管理技能。检查登录状态、登录(二维码或手机号)、退出登录. An agent skill from autoclaw-cc/xiaohongshu-skills.

    1.9k GitHub stars~832 tokensUpdated 4 mo ago
    Auto-check passed
  • Xhs Explore

    autoclaw-cc/xiaohongshu-skills

    小红书内容发现与分析技能。搜索笔记、浏览首页、查看详情、获取用户资料. An agent skill from autoclaw-cc/xiaohongshu-skills.

    1.9k GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Xhs Interact

    autoclaw-cc/xiaohongshu-skills

    小红书社交互动技能。发表评论、回复评论、点赞、收藏. An agent skill from autoclaw-cc/xiaohongshu-skills.

    1.9k GitHub stars~637 tokensUpdated 4 mo ago
    Auto-check passed
  • Xhs Publish

    autoclaw-cc/xiaohongshu-skills

    小红书内容发布技能。支持图文发布、视频发布、长文发布、定时发布、标签、可见性设置. An agent skill from autoclaw-cc/xiaohongshu-skills.

    1.9k GitHub stars~1.7k tokensUpdated 4 mo ago
    Auto-check passed

Questions about Xhs Content Ops

What does Xhs Content Ops do?

小红书复合内容运营技能。组合搜索、详情、发布、互动等能力完成运营工作流. An agent skill from autoclaw-cc/xiaohongshu-skills. Xhs Content Ops is an agent skill from autoclaw-cc/xiaohongshu-skills.

How do I install Xhs Content Ops in Claude Code?

Run `npx skills add autoclaw-cc/xiaohongshu-skills --skill xhs-content-ops -a claude-code`. Or copy the skill folder (skills/xhs-content-ops in autoclaw-cc/xiaohongshu-skills) into .claude/skills/xhs-content-ops in your project. Claude Code loads it when a task matches its description.

How do I install Xhs Content Ops in Codex?

Run `npx skills add autoclaw-cc/xiaohongshu-skills --skill xhs-content-ops -a codex`. Or copy the skill folder (skills/xhs-content-ops in autoclaw-cc/xiaohongshu-skills) into .agents/skills/xhs-content-ops in your project. Codex loads it when a task matches its description.

Can I use Xhs Content Ops 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 autoclaw-cc/xiaohongshu-skills --skill xhs-content-ops -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/xhs-content-ops, .gemini/skills/xhs-content-ops, .github/skills/xhs-content-ops and .opencode/skills/xhs-content-ops in your project.

What does Xhs Content Ops need to run?

Going by SKILL.md and its folder, Xhs Content Ops needs the command-line tools its instructions call (python) and credentials named XSEC_TOKEN. Our summary lists: Python 3; A credential in XSEC_TOKEN.

Does Xhs Content Ops 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 Xhs Content Ops 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 Xhs Content Ops use?

Xhs Content Ops is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Xhs Content Ops use?

About 919 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Xhs Content Ops?

Skills that share tags, products or a category with Xhs Content Ops: Xiaohongshu (zhjiang22/openclaw-xhs, 123 stars), Media Crawler (tsingyuai/growth-lab, 2k stars), Qiaomu Codex Imagegen (joeseesun/qiaomu-codex-imagegen, 125 stars) and Sandbase (sandbaseai/cli, 188 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Xhs Content Ops?

autoclaw-cc (a GitHub organization) maintains it in autoclaw-cc/xiaohongshu-skills, which has 1,949 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on May 23, 2026.

Source: autoclaw-cc/xiaohongshu-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.