Agent skill

Xhs Note Creator

by ZJU-REAL in ZJU-REAL/Easel

小红书内容总入口:生成标题、正文、caption、hashtags,以及 3-9 张图文卡片或短视频分镜,覆盖素材分析、卖点评估、去 AI 味和质检。

Apache-2.0Auto-check passedWriting & Content

Install Xhs Note Creator

skills CLI
$ npx skills add ZJU-REAL/Easel --skill xhs-note-creator -a claude-code

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

GitHub CLI
$ gh skill install ZJU-REAL/Easel xhs-note-creator --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/xhs-note-creator .claude/skills/xhs-note-creator && 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-note-creator
GitHub stars
3.4k
Token cost
~1.2k tokens
SKILL.md length
345 words
Files
14 (incl. scripts, references)
Skills in repo
114
Repo updated
First seen
Licence
Apache-2.0

At a glance

小红书内容总入口:生成标题、正文、caption、hashtags,以及 3-9 张图文卡片或短视频分镜,覆盖素材分析、卖点评估、去 AI 味和质检。

  • Works in 10 steps: Intake(必问,一次问完) → 5 — 卖点/亮点分析(推广/分享/测评类必做) → 素材清点(有素材才做) → …
  • Tasks that involve Social media posts
  • SKILL.md covers 核心理念, 工作流, 不要做的事 and Profile 感知, plus 2 more sections
  • Runs Python scripts from its folder; calls python3, python and pip

What it does

Xhs Note Creator is an agent skill from ZJU-REAL/Easel. 小红书内容总入口:生成标题、正文、caption、hashtags,以及 3-9 张图文卡片或短视频分镜,覆盖素材分析、卖点评估、去 AI 味和质检。 当用户说“写/做小红书笔记、小红书图文/种草/文案、出一套卡片、小红书视频”时使用。 整套笔记用本 SKILL;仅渲染卡片用 card-xiaohongshu;其他平台的通用文案用 social-content。

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files, including scripts and reference files (for example `EASEL-META.md`, `references/image-sourcing.md` and `references/material-intake.md`).

It sits in Writing & Content, covering Social media posts. It works with Xiaohongshu. 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 Social media posts

Example prompts

  • “写/做小红书笔记、小红书图文/种草/文案、出一套卡片、小红书视频”
  • “/xhs-note-creator”

Requirements

  • Python 3

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. Intake(必问,一次问完)
  2. 5 — 卖点/亮点分析(推广/分享/测评类必做)
  3. 素材清点(有素材才做)
  4. 采集外部参考(观点类/资讯类必做)
  5. 写长文原稿(2000-4000 字)
  6. 去 AI 化(强制)
  7. 分发:图文 or 视频
  8. caption + hashtags + 标题
  9. 落盘
  10. 校验(强制,两道门)

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

    Ships 6 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3
    • python
    • pip
    • playwright

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

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    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

Xhs Note Creator loads about 1.2k tokens when it runs, and up to ~7.9k if it reads all its reference files. Until then it costs about 50 tokens; SKILL.md has 345 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.9k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from ZJU-REAL/Easel at commit 278f420, republished under its Apache-2.0 licence (© ZJU-REAL). 345 words, ~1,229 tokens.

Download SKILL.mdSave it as .claude/skills/xhs-note-creator/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.
name
xhs-note-creator
description
小红书内容总入口:生成标题、正文、caption、hashtags,以及 3-9 张图文卡片或短视频分镜,覆盖素材分析、卖点评估、去 AI 味和质检。 当用户说“写/做小红书笔记、小红书图文/种草/文案、出一套卡片、小红书视频”时使用。 整套笔记用本 SKILL;仅渲染卡片用 card-xiaohongshu;其他平台的通用文案用 social-content。
layer
produce

小红书笔记创作

把一个主题 + 可选素材,生成图文卡片组或短视频分镜脚本,按规范输出到 outputs/。

核心理念

小红书读者看的不是长文,是卡片组或短视频。长文原稿只是中间产物。

  • 图文帖:3-9 张 3:4 竖版卡片(cover + content × N + ending),每张 ≤80 字
  • 视频帖:15-90 秒竖屏视频分镜 + 封面卡
爆款 5 大原则
  1. 真实素材优先:截图、对比图 > 纯 AI 生图
  2. 聚焦核心卖点:用公式判断优先级(稀缺性 × 实用性 × 可感知)
  3. 高级感视觉(走 card-design,别做糙卡):卡片视觉统一走 card-design 设计系统(选风格锁 spec、字大字细、填满画幅、禁大 emoji 廉价感)。文案要口语化、真实感,但视觉不能糙——想要「素人 / 手账」质感就选 card-design 的手账贴纸 / 奶油温柔风格(仍是高质量 HTML 渲染,不是糙 t2i 大 emoji)。
  4. 痛点导向:"能解决什么问题" > 堆砌功能列表
  5. 快速迭代:V1(60 分) → 用户反馈 → V2(70 分)

详细方法论:references/xiaohongshu-viral-methodology.md

工作流

按顺序执行,不要跳步。

Step 0 — Intake(必问,一次问完)
  1. 主题 / 目标读者 / 核心观点
  2. 输出形态:图文 or 视频?(默认图文)
  3. 素材:有无现成文字/图片/视频?
  4. 风格:视觉风格走 card-design 风格库(9 种:瑞士极简/杂志编辑/新中式墨韵/奶油温柔/多巴胺 Y2K/高奢黑金/手账贴纸/极客终端/植物清新)——在 Step 5A 出卡时由 card-xiaohongshu 引导选定,这里先不锁死。
  5. 卡片数量 / 视频时长:图文默认 5-7 张;视频默认 30-60 秒
Step 0.5 — 卖点/亮点分析(推广/分享/测评类必做)
  1. 列出所有功能/特性/亮点
  2. 让用户对每个点打分:
    • 稀缺性(1-5):别人有吗?
    • 实用性(1-5):解决多大问题?
    • 可感知(1-5):用户能直接看到吗?
  3. 得分 = 稀缺性 × 实用性 × 可感知
  4. 选 Top 1-2 作为核心卖点
Step 1 — 素材清点(有素材才做)

如果用户提供了素材,先用脚本生成清单:

bash
python3 skills/openclaw/xhs-note-creator/scripts/analyze_material.py <path>... \
  --out <work-dir>/reference/materials.json \
  --frames-dir <work-dir>/reference/frames

素材价值排序:对比图 > 功能演示 > 数据图表 > 品牌素材

Step 2 — 采集外部参考(观点类/资讯类必做)

按 references/reference-search.md 执行,核心数据 ≥2 个来源交叉验证。

Step 3 — 写长文原稿(2000-4000 字)

从 H2 开始(不写 H1),写完先给用户确认再继续。

Step 4 — 去 AI 化(强制)

去 AI 感规则统一走 text-polisher 权威源,不在本 SKILL 维护副本:

  • 中文规则(含小红书素人感/闺蜜语气/emoji 节奏特化)→ ../text-polisher/references/zh-ai-markers.md
  • 通用填充短语 → ../text-polisher/references/phrases-to-remove.md
  • 公式化结构 → ../text-polisher/references/structures-to-avoid.md

按其五层原则完整扫描重写,质量评分满分 50。

Step 5 — 分发:图文 or 视频
5A. 图文帖:拆成 3-9 张卡片
  • cover(第 1 张)+ content(中间)+ ending(最后 1 张)
  • 每张 ≤80 字
  • 一张卡只讲一个论点
  • 全套配色/字体/风格保持一致(由 card-design 选中的那一套贯穿整组)

卡片视觉一律走 card-design 高质量管线,别用糙 t2i / 大 emoji 素人卡。 按有无真实照片分两条渲染路径(策略写入 meta.json,枚举与 references/meta-schema.md 一致):

策略适用渲染路径
html_card纯文字卡 / 概念卡 / 数据卡(默认、最常用)走 card-xiaohongshu:读 card-design 选风格锁 spec → 写 HTML → render_card.py 出图 → card_audit.py 硬门禁
text_on_photo有真实照片 + 钩子文字(真实素材最佳)Pillow scripts/text_on_image.py(小红书真实素材路径,保留)
collage有 2-4 张互补照片Pillow scripts/collage_3x4.py

纯文字/概念/数据卡不再走用户自备 t2i——统一由 card-xiaohongshu 渲染,保证视觉质量;只有「真实照片卡」才走 Pillow 路径。

5B. 视频帖:写分镜脚本
  • 6-12 个分镜,每镜 2-8 秒
  • 每镜含:narration(≤30 字)、on_screen_text(≤15 字)、visual、material_ref
  • 出一张 cover 卡作为封面
Step 6 — caption + hashtags + 标题

标题:从公共源 skills/shared/references/hook-title-formulas.md 选标题公式(痛点+方案 / 提问式 / 发现式 / 热点词 / 身份共鸣等),产 2-3 个备选。

caption:100-300 字,hook 开头 → 关键信息 → CTA,闺蜜语气 + 少量 emoji(点缀节奏,不当图标)

hashtags:5-8 个,4 核心(热点词 + 核心功能 + 差异化 + 目标人群)+ 4 辅助(场景 + 品类)

Step 7 — 落盘
outputs/主题名/{YYYY-MM-DD}/{短标题}_{时间戳}/
├── {完整标题}.md        # 长文原稿
├── meta.json            # 元数据(卡片/分镜/caption/hashtags)
├── images/              # 最终卡图 / 封面
└── reference/           # materials.json / 搜索结果

目录名走脚本标准化:python3 skills/openclaw/xhs-note-creator/scripts/normalize_slug.py "标题" --with-ts

Step 8 — 校验(强制,两道门)

① 文本/结构门(标题/caption/hashtag/卡片字数与结构):

bash
python3 skills/openclaw/xhs-note-creator/scripts/validate_meta.py outputs/主题名/meta.json

② 视觉门(仅 html_card 路径,渲染后跑;死空白/密度硬门禁):

bash
python skills/openclaw/card-design/scripts/card_audit.py audit -f "outputs/主题名/card_*.png"

任一非 0 退出 → 修改后重跑,直到通过。不交付未校验的产物。

不要做的事

  • 不写 H1;标题只放 meta.json.title
  • 不在正文末尾写参考来源
  • 不在 .md 里留 【插入图片】 占位符
  • 不跳过 Step 4(去 AI 化)和 Step 8(validate)
  • 不手算目录名,一律走 normalize_slug.py

Profile 感知

  • 有 Profile:读取赛道、目标受众、内容风格,对齐笔记语气和标签策略
  • 无 Profile:询问基本信息后以通用种草风格输出

工具依赖

  • Python 3.8+、Pillow(必需,真实照片卡路径)
  • playwright + chromium(html_card 路径渲染卡片,走 card-xiaohongshu;首次 pip install playwright && playwright install chromium)

参考资料

  • 卡片视觉 → card-design(设计系统/风格库,出图前必读)+ card-xiaohongshu(HTML→截图渲染管线)
  • references/xiaohongshu-viral-methodology.md — 文案/卖点/标题/情绪方法论(视觉部分已交 card-design)
  • 去 AI 化 → ../text-polisher/references/zh-ai-markers.md(权威源,含小红书特化)
  • 钩子/标题公式 → skills/shared/references/hook-title-formulas.md(公共源)
  • references/material-intake.md — 素材处理流程
  • references/image-sourcing.md — 图片来源处理
  • references/meta-schema.md — 元数据字段定义
  • references/output-spec.md — 输出目录规范

© 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 13 other files (scripts, references) in skills/openclaw/xhs-note-creator of ZJU-REAL/Easel.

  • SKILL.md
  • EASEL-META.md
  • references/image-sourcing.md
  • references/material-intake.md
  • references/meta-schema.md
  • references/output-spec.md
  • references/reference-search.md
  • references/xiaohongshu-viral-methodology.md
  • scripts/analyze_material.py
  • scripts/collage_3x4.py
  • scripts/crop_watermark.py
  • scripts/normalize_slug.py
  • scripts/text_on_image.py
  • scripts/validate_meta.py

Open the folder on GitHubat commit 278f420

Compare with similar skills

Xhs Note Creator 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 Note Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Xhs Note Creator this skillZJU-REAL/Easel3.4k—~1.2kAutomated safety check: PassApache-2.0
Humanized Chinese Writing PolisherEthanYoQ/agent-xiaohongshu-workbench154—~1.1kAutomated safety check: PassMIT
Anti Vibe Writingweijt606/anti-vibe-writing120—~3.9kAutomated safety check: PassMIT
Social Notexuzhougeng/wisp-science1k—~815Automated safety check: PassApache-2.0
Social Cover DirectorJamailar/Beav1.8k—~1.7kAutomated safety check: WarnCustom licence
Socialcoreyhaines31/marketingskills54k4 repos~4.5kAutomated safety check: PassMIT

Similar skills

  • Humanized Chinese Writing Polisher

    EthanYoQ/agent-xiaohongshu-workbench

    A skill your agent uses when a user asks to polish, rewrite, humanize, de-AI, localize, or oralize Chinese writing, including short-video scripts, articles, social posts, speeches, newsletters, and…

    154 GitHub stars~1.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Anti Vibe Writing

    weijt606/anti-vibe-writing

    A skill your agent uses when the user wants to humanize, de-AI, polish, or warm up an AI-generated document, in English or Chinese.

    120 GitHub stars~3.9k tokensUpdated 2 mo ago
    Writing & ContentAuto-check passed
  • Social Note

    xuzhougeng/wisp-science

    Turn a scientific conversation, paper takeaway, or figure story into paste-ready social copy.

    1k GitHub stars~815 tokensUpdated today
    Writing & ContentAuto-check passed
  • A skill your agent uses when the user wants to plan or generate a social media cover image for a Xiaohongshu note, Douyin/TikTok photo post, Reels/Shorts cover, WeChat/Video Account post…

    1.8k GitHub stars~1.7k tokensUpdated yesterday
    Media & CreativeAuto-check: warnings
  • Social

    coreyhaines31/marketingskills

    When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, or Facebook, or wants to do social listening and engagement triage.

    54k GitHub starsUsed in 4 repos~4.5k tokens
    Writing & ContentAuto-check passed
  • Social Content

    freekmurze/dotfiles

    When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, Facebook, or other platforms.

    1k GitHub starsUsed in 23 repos~2.1k tokens
    Writing & ContentAuto-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 yesterday
    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 yesterday
    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 yesterday
    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 yesterday
    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 yesterday
    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 yesterday
    Auto-check passed

Works with

Questions about Xhs Note Creator

What does Xhs Note Creator do?

小红书内容总入口:生成标题、正文、caption、hashtags,以及 3-9 张图文卡片或短视频分镜,覆盖素材分析、卖点评估、去 AI 味和质检。. Xhs Note Creator is an agent skill from ZJU-REAL/Easel.

When should I use Xhs Note Creator?

Xhs Note Creator fits situations like: tasks that involve Social media posts.

How do I install Xhs Note Creator in Claude Code?

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

How do I install Xhs Note Creator in Codex?

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

Can I use Xhs Note Creator 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 xhs-note-creator -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-note-creator, .gemini/skills/xhs-note-creator, .github/skills/xhs-note-creator and .opencode/skills/xhs-note-creator in your project.

What does Xhs Note Creator need to run?

Going by SKILL.md and its folder, Xhs Note Creator needs Python for the scripts in its folder and the command-line tools its instructions call (python3, python, pip and playwright). Our summary lists: Python 3.

Does Xhs Note Creator access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Xhs Note Creator 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Xhs Note Creator use?

Xhs Note Creator 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 Xhs Note Creator use?

About 1.2k tokens (SKILL.md is roughly 4.9k 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 6.7k tokens, read only when the agent opens those files.

What are the alternatives to Xhs Note Creator?

Skills that share tags, products or a category with Xhs Note Creator: Humanized Chinese Writing Polisher (EthanYoQ/agent-xiaohongshu-workbench, 154 stars), Anti Vibe Writing (weijt606/anti-vibe-writing, 120 stars), Social Note (xuzhougeng/wisp-science, 1k stars) and Social Cover Director (Jamailar/Beav, 1.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Xhs Note Creator?

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.