skilllite: Skill for Claude Code

.skills/xiaohongshu-writer/SKILL.md

xiaohongshu-writer is a skill for Claude Code, Codex from EXboys/skilllite. It costs 56 tokens per session (1,288 once invoked), scanned A, original, MIT.

A writing and cover-making helper for Xiaohongshu, a Chinese social platform for image-and-text posts. It creates a title, post text, hashtags, and a vertical thumbnail image.

In plain words
What is it for?
Use it to turn a topic into a ready-to-publish Xiaohongshu post, including a 3:4 cover image with a title, summary, and hashtags.
Why use it?
It removes the need to plan the post and design its cover separately. It also gives the content a consistent structure and format for the platform.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is EXboys/skilllite's own configuration. It tells Claude Code and Codex how to work on skilllite 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 skilllite configures →

Reuse

Borrowing it

Nothing to install: this file belongs to EXboys/skilllite. 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/EXboys/skilllite/main/.skills/xiaohongshu-writer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/EXboys/skilllite

Made for: Claude Code, Codex.

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 xiaohongshu-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/exboys/skilllite/xiaohongshu-writer/github.svg)](https://agentmods.dev/skills/exboys/skilllite/xiaohongshu-writer)
Your own site
<a href="https://agentmods.dev/skills/exboys/skilllite/xiaohongshu-writer"><img src="https://agentmods.dev/badge/skills/exboys/skilllite/xiaohongshu-writer/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 xiaohongshu-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/exboys/skilllite/xiaohongshu-writer"><img src="https://agentmods.dev/badge/skills/exboys/skilllite/xiaohongshu-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,288 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00056 $0.01288
Opus 5.5 $0.00022 $0.00515
Sonnet 5.5 $0.00011 $0.00258
Haiku 4.5 $0.00006 $0.00129

Measured 2mo ago against content hash 1cc725b6271f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

xiaohongshu-writer 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/main.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.skills/xiaohongshu-writer/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

小红书图文创作助手

工作流程

  1. Agent 用本 Skill 的指引,根据用户主题生成完整内容(标题、正文、标签、封面设计)
  2. 调用本工具,传入生成的 content,建议 generate_thumbnail: true
  3. 脚本:优先用 Playwright 渲染 HTML 并截图(效果好、排版一致),失败时回退 Pillow;返回 base64 及保存到 image_path

无需 OpenAI,优先 Playwright HTML 截图,回退 Pillow 绘图。


输出结构(工具返回)

{
  "success": true,
  "title": "吸睛标题,带 emoji",
  "body": "正文内容",
  "hashtags": ["#话题1", "#话题2"],
  "thumbnail": {
    "cover_title": "封面显示标题",
    "accent_color": "#FF6B6B",
    "style": "gradient",
    "image_base64": "封面图 base64(仅当未保存到文件时返回,避免输出过大)",
    "image_path": "项目根目录下保存的图片路径,如 xiaohongshu_thumbnail.png",
    "image_source": "playwright 或 pillow"
  }
}

标题规则

  • 长度:15-25 字为宜,信息密度高
  • 必备:至少 1 个 emoji,放在开头或关键词处
  • 禁止:标题党、夸张承诺、违禁词
  • 技巧:数字+结果、反常识、疑问式、场景代入

正文规则

  • 分段:每段 2-4 行,多用空行隔开
  • 语气:口语化、像朋友分享,用"我"、"你"
  • emoji:适当点缀,每段 0-2 个,不过度
  • 结构:开头抓人 → 干货/故事 → 总结/互动
  • 禁止:硬广感、堆砌关键词、违禁词

标签规则

  • 数量:3-5 个
  • 搭配:1 个大类话题 + 2-3 个细分 + 1 个热门
  • 示例:#生活好物 #平价好物 #宿舍党必备 #618攻略

缩略图(封面)设计

封面为高质量图文风格,包含三部分:主标题、正文摘要(2–5 行)、话题标签。由 Playwright 渲染 HTML 并截图(主)或 Pillow 绘制(备选)生成,竖版 3:4。成功后保存到项目根目录 xiaohongshu_thumbnail.png。

Agent 生成 content 时,thumbnail 需包含:

字段 说明 示例
cover_title 封面上显示的主标题(可略,默认用 title) "3 件办公室好物"
accent_color 主色调,十六进制或中文 "#FF6B6B" 或 "暖橙"
style 风格 "gradient" / "minimal" / "vibrant"

风格说明

  • gradient:渐变背景,主色到深色(默认)
  • minimal:简约灰白
  • vibrant:纯色块

使用方式

工具调用:传入 content(必填),即 Agent 已生成的内容。格式:

{
  "content": {
    "title": "🛒 打工人的 3 件办公室好物!",
    "body": "正文...",
    "hashtags": ["#办公室好物", ...],
    "thumbnail": {
      "cover_title": "3 件办公室好物",
      "accent_color": "#FF6B6B",
      "style": "gradient"
    }
  },
  "generate_thumbnail": true
}

前置条件:

  • pip install playwright 且执行 playwright install chromium(优先,skilllite init 时会安装)
  • 可选回退:pip install Pillow 及中文字体(macOS 自带 PingFang;Linux: apt install fonts-noto-cjk;或于 .skills/xiaohongshu-writer/fonts/ 放入 NotoSansCJKsc-Regular.otf)

Read the full file on GitHub · 137 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 137 lines · 56 tokens per session scan A 1cc725b6271f

Subscribe to this mod's changes

xiaohongshu-writer is a skill published in the GitHub repository EXboys/skilllite (152 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 1,288 once invoked, about $0.0002 per session on Opus 5.5. 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.

Related

xiaohongshu-writer compared with skills from other repositories

xiaohongshu-writer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
xiaohongshu-writerEXboys/skillliteSkill1524d agoMITA56Claude Code, Codex
analyzing-malware-behavior-with-cuckoo-sandboxMikaru0Mystic/sectinelSkill124mo agoApache-2.0A78Claude Code
ops-demoSnowflake-Labs/cocoplusSkill7272d agoMITA46Claude Code
diarySnowflake-Labs/cocoplusSkill7272d agoMITA12Claude Code, Codex
pulse-configureSnowflake-Labs/cocoplusSkill7272d agoMITA12Claude Code, Codex
stall-resetSnowflake-Labs/cocoplusSkill7272d agoMITA14Claude Code, Codex
code-reviewmagnus919/agent-skillsSkill1662d agoMITA196Claude Code, Codex