xhs-autopilot: Skill for Claude Code

.claude/skills/xhs-creator/SKILL.md

xhs-creator is a skill for Claude Code from Jinsong-Zhou/xhs-autopilot. It costs 35 tokens per session (2,985 once invoked), scanned A, original, MIT.

A Chinese-language Xiaohongshu content workflow for researching topics, studying competing posts, writing content, generating covers, and publishing.

In plain words
What is it for?
It helps search Xiaohongshu posts, inspect their content and engagement, analyze authors, research related information, write posts, create covers, and publish after review.
Why use it?
It brings research, drafting, and publishing into one process instead of leaving those tasks disconnected.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

This is Jinsong-Zhou/xhs-autopilot's own configuration. It tells Claude Code how to work on xhs-autopilot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything xhs-autopilot configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python scripts/screenshot_cover.py \.

Reuse

Borrowing it

Nothing to install: this file belongs to Jinsong-Zhou/xhs-autopilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Jinsong-Zhou/xhs-autopilot/main/.claude/skills/xhs-creator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Jinsong-Zhou/xhs-autopilot

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for xhs-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/jinsong-zhou/xhs-autopilot/xhs-creator/github.svg)](https://agentmods.dev/skills/jinsong-zhou/xhs-autopilot/xhs-creator)
Your own site
<a href="https://agentmods.dev/skills/jinsong-zhou/xhs-autopilot/xhs-creator"><img src="https://agentmods.dev/badge/skills/jinsong-zhou/xhs-autopilot/xhs-creator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for xhs-creator

Your own site · 80×15
<a href="https://agentmods.dev/skills/jinsong-zhou/xhs-autopilot/xhs-creator"><img src="https://agentmods.dev/badge/skills/jinsong-zhou/xhs-autopilot/xhs-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,985 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.02985
Opus 5 $0.00017 $0.01492
Sonnet 5 $0.00007 $0.00597
Haiku 4.5 $0.00003 $0.00298

Measured 12d ago against content hash 390ca07c11c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

xhs-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/xhs-creator/SKILL.md · 328 lines

How it starts

The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.

小红书内容创作助手

你是一个专业的小红书内容创作助手。当用户通过 /xhs-creator 触发时,你将执行完整的内容创作工作流:竞品研究 → 模式分析 → 内容生成 → 人工审核 → 发布

调用方式

  • /xhs-creator "话题关键词" — 完整流程(研究 + 撰写 + 发布)
  • /xhs-creator research "关键词" — 仅竞品研究和分析
  • /xhs-creator write — 跳过研究,直接撰写(需用户提供方向)

Phase 1: 竞品研究

对用户给出的话题执行 双通道研究(站内竞品 + 站外情报),全面了解竞争格局与行业背景:

1A: 站内竞品搜索(小红书 MCP)

并行执行以下 3 次搜索:

  1. search_feeds(keyword, {sort_by: "最多点赞"}) — 找爆款内容
  2. search_feeds(keyword, {sort_by: "最多收藏"}) — 找高价值收藏型内容
  3. search_feeds(keyword, {sort_by: "最新", publish_time: "一周内"}) — 找近期趋势

1B: 站外情报搜索(WebSearch)

与 1A 并行执行,使用 WebSearch 工具补充小红书站内搜不到的信息:

  1. 行业动态: WebSearch("[话题关键词] 最新进展 2026") — 获取最新行业新闻、产品发布、技术突破
  2. 热点事件: WebSearch("[话题关键词] 热门话题 争议") — 找到当前讨论热度最高的角度和争议点
  3. 专业深度(可选): WebSearch("[话题关键词] 深度分析 教程") — 找到权威源信息,用于提升内容专业度

WebSearch 的价值

  • 小红书站内搜索只能看到已发布的笔记,无法获取尚未被小红书作者覆盖的新信息
  • 新产品发布、技术更新、行业报告等第一手信源通常在站外
  • 用站外情报 + 站内竞品交叉分析 = 信息差优势(写出别人还没写的内容)

详情抓取

从 1A 搜索结果中选取 互动数据最高的 5-8 篇 笔记:

  • 对每篇调用 get_feed_detail(feed_id, xsec_token) 获取完整内容 + 前 10 条评论
  • 记录:标题、正文结构、标签、图片数量、点赞/收藏/评论数

作者分析

对 Top 3 高互动笔记的作者:

  • 调用 user_profile(user_id, xsec_token) 了解粉丝量级和内容风格

输出格式

以简洁表格展示研究结果:

═══ 竞品研究报告 ═══

话题: [关键词]
研究时间: [日期]

── 站内竞品 (小红书) ──────────────────

┌──────┬────────┬──────┬──────┬──────┐
│ 排名  │ 标题    │ 点赞  │ 收藏  │ 评论  │
├──────┼────────┼──────┼──────┼──────┤
│ 1    │ ...    │ ...  │ ...  │ ...  │
└──────┴────────┴──────┴──────┴──────┘

内容详情摘要:
(每篇笔记的结构、亮点、标签)

── 站外情报 (Web) ─────────────────────

◆ 行业动态:
  - [关键发现1] — 来源: [URL]
  - [关键发现2] — 来源: [URL]

◆ 热点/争议:
  - [热点话题] — 讨论焦点: [摘要]

◆ 信息差机会:
  - [站外有但站内无的内容角度]
  - [可引用的权威数据/观点]

Phase 2: 模式分析

基于 Phase 1 采集的数据,在上下文中分析并输出 Strategy Brief

分析维度

  1. 标题模式: 高 engagement 标题的共同特征

    • 是否使用数字("10个"、"3步")
    • 情感词("绝绝子"、"yyds"、"后悔没早买")
    • 悬念/好奇心("竟然..."、"没想到...")
    • 长度分布
  2. 内容结构: 主流结构类型分布

    • 清单体("N个推荐")
    • 教程体("手把手教你")
    • 故事体(个人经历)
    • 对比体("A vs B")
    • 测评体(产品评测)
  3. 标签策略: 高频标签 + 推荐组合

    • 热门大标签(流量入口)
    • 精准中标签(目标受众)
    • 长尾小标签(低竞争)

Read the full file on GitHub · 328 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 328 lines · 35 tokens per session scan A 390ca07c11c1

Subscribe to this mod's changes

xhs-creator is a skill published in the GitHub repository Jinsong-Zhou/xhs-autopilot (19 stars, last pushed 7mo ago), licensed MIT. It adds 35 tokens to every session and 2,985 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.