CCM
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
plugins-world avatar

Pw Redbook Image

plugins-world/pw-skills
272 installs22 stars
Summary

This takes an article from a URL, file, or text and breaks it down into a series of Xiaohongshu-style vertical images with cartoon aesthetics, pastel colors, and hand-drawn text. It creates 2-10 images depending on content complexity: a cover, content slides focusing on one point each, and a closing image. The workflow is structured: it fetches your content, analyzes it using templates, generates English prompts for each slide, then calls an image generation tool like pw-danger-gemini-web. Everything gets organized into a timestamped directory with prompts and images numbered sequentially. You can merge the results into a long image, PPT, or PDF afterward. It confirms style after the first image before batch-generating the rest, which is smart for consistency.

Install to Claude Code

npx -y skills add plugins-world/pw-skills --skill pw-redbook-image --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
ego lite browserego lite browser
ego lite browser
Fastest browser for AI agents to run web automation tasks, always free.
Download Free life-time →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Open Steps
Open Steps
Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Agent, connect blockchain
Agent, connect blockchain
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →
Granola, the best AI meeting recorder
Granola, the best AI meeting recorder
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
CodeHealth MCP ServerCodeHealth MCP Server
CodeHealth MCP Server
Protect your code quality, stop the AI slop.
Try For Free →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
ego lite browserego lite browser
ego lite browser
Fastest browser for AI agents to run web automation tasks, always free.
Download Free life-time →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Open Steps
Open Steps
Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Agent, connect blockchain
Agent, connect blockchain
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →
Granola, the best AI meeting recorder
Granola, the best AI meeting recorder
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
CodeHealth MCP ServerCodeHealth MCP Server
CodeHealth MCP Server
Protect your code quality, stop the AI slop.
Try For Free →
Files
SKILL.mdView on GitHub

小红书风格图片生成

将文章内容智能拆解为小红书风格的系列配图,包含封面图、内容图和结尾图。

核心功能

  • 智能拆解文章为多张配图 (2-10 张)
  • 自动生成符合小红书风格的图片提示词
  • 支持多种输入源 (URL、文件路径、文本内容)
  • 自动创建结构化的工作目录
  • 支持后处理 (合并长图、PPT、PDF)

使用时机

用户明确要求生成小红书风格配图时:

  • "生成小红书配图"
  • "制作小红书系列图"
  • "将这篇文章做成小红书图片"
  • "帮我做小红书风格的图文"

不适用场景:

  • 用户只是询问如何制作 (提供建议即可)
  • 用户需要单张封面图 (使用 pw-cover-image)
  • 用户需要其他风格的图片 (使用通用图片生成工具)

使用方法

# 从 URL 生成
/pw-redbook-image https://example.com/article

# 从文本内容生成
/pw-redbook-image "文章内容..."

# 从 markdown 文件生成
/pw-redbook-image path/to/article.md

参数说明

  • 输入源 (必需): 支持三种格式
    • URL: 以 http:// 或 https:// 开头的网址
    • 文件路径: 相对或绝对路径,支持 .md、.txt 等文本文件
    • 文本内容: 直接传入的文章内容字符串

小红书风格特征

  • 比例: 竖版(3:4 或 9:16)
  • 风格: 卡通风格、手绘风格
  • 配色: 莫兰迪色系、奶油色、米白色、浅粉、薄荷绿
  • 文字: 手绘风格文字,大标题突出,荧光笔划线强调
  • 装饰: 卡通元素、emoji 图标、手绘贴纸、对话气泡
  • 排版: 信息精简,多留白,要点分条呈现

内容拆解原则

  • 封面图: 强烈视觉冲击力,包含核心标题
  • 内容图: 每张聚焦 1 个核心观点
  • 结尾图: 总结/行动号召/金句

图片数量:

  • 简单观点: 2-3 张
  • 中等复杂度: 4-6 张
  • 深度干货: 7-10 张

文件管理

输出目录

每个会话创建一个以主题命名的独立目录:

redbook-{topic-slug}/
├── source.md              # 源文章
├── prompts/               # 提示词文件
│   ├── 01_封面图.md
│   ├── 02_内容图_核心观点1.md
│   ├── 03_内容图_核心观点2.md
│   └── 04_结尾图.md
└── images/                # 生成的图片
    ├── 01_封面图.png
    ├── 02_内容图_核心观点1.png
    ├── 03_内容图_核心观点2.png
    └── 04_结尾图.png

主题命名规则:

  1. 从文章标题/内容中提取主题(2-4 个词,kebab-case)
  2. 示例: "如何提升工作效率" → improve-work-efficiency

冲突解决

如果 redbook-{topic-slug}/ 已存在:

  • 追加时间戳: {topic-slug}-YYYYMMDD-HHMMSS
  • 示例: improve-work-efficiency 已存在 → improve-work-efficiency-20260123-143052

源文件

使用 source.md 或 source-{原文件名} 保存源文章。

工作流程

步骤 1: 获取文章内容

处理输入源:

  • URL: 使用 WebFetch 抓取网页内容
  • 文件路径: 使用 Read 读取文件内容
  • 文本: 直接使用传入的内容

保存源内容:

  • 创建工作目录 redbook-{topic-slug}/
  • 保存源文件到 source.md 或 source-{原文件名}

步骤 2: 分析和拆解文章

使用 ${SKILL_DIR}/references/文章拆解模板.md 分析文章:

  • 提取主题和核心观点
  • 确定图片数量 (2-10 张)
  • 生成拆解方案,明确每张图的核心内容

图片数量建议:

  • 简单观点: 2-3 张
  • 中等复杂度: 4-6 张
  • 深度干货: 7-10 张

步骤 3: 生成提示词文件

创建 redbook-{topic-slug}/prompts/ 目录,根据图片类型选择模板:

  • 封面图: ${SKILL_DIR}/references/封面图模板.md
  • 内容图: ${SKILL_DIR}/references/内容图模板.md
  • 结尾图: ${SKILL_DIR}/references/结尾图模板.md

为每张图生成独立的提示词文件:

  • 命名格式: 01_封面图.md, 02_内容图_关键词.md, 03_结尾图.md
  • 提示词使用英文,避免 Markdown 格式
  • 包含风格关键词和配色方案

步骤 4: 生成图片

检查可用的图片生成技能:

  • 优先使用 pw-danger-gemini-web
  • 如有多个技能可用,询问用户选择

逐张生成图片:

  • 输出目录: redbook-{topic-slug}/images/
  • 显示生成进度
  • 图片按序号排序
  • 第一张图生成后,确认风格再继续批量生成

步骤 5: 后处理 (可选)

合并长图 (需要 ImageMagick):

brew install imagemagick
node ~/.claude/skills/pw-image-generation/scripts/merge-to-long-image.js \
  redbook-{topic-slug}/images \
  redbook-{topic-slug}/长图.png

合并为 PPT:

node ~/.claude/skills/pw-image-generation/scripts/merge-to-pptx.js \
  redbook-{topic-slug}/images \
  redbook-{topic-slug}/配图.pptx

合并为 PDF:

node ~/.claude/skills/pw-image-generation/scripts/merge-to-pdf.js \
  redbook-{topic-slug}/images \
  redbook-{topic-slug}/配图.pdf

步骤 6: 输出摘要

生成完成后输出:

小红书系列图已生成!

主题: [主题]
图片数量: [数量] 张
工作目录: redbook-{topic-slug}/

后续步骤:
- 预览所有图片确认风格一致性
- 如需要可使用合并工具生成长图、PPT 或 PDF

最佳实践

风格一致性:

  • 第一张图生成后确认风格,再批量生成其余图片
  • 所有图片使用相同的风格关键词和配色方案
  • 作者信息统一放在右下角,格式保持一致

内容设计:

  • 每张图聚焦一个核心观点,不要放太多内容
  • 多留白,提高可读性
  • 标题要大而突出,关键词用荧光笔划线强调

提示词优化:

  • 使用英文提示词,效果更好
  • 避免 Markdown 格式,使用纯文本描述
  • 明确指定比例 (3:4 或 9:16)、风格 (卡通/手绘)、配色 (莫兰迪色系)

常见问题

问题: 生成的图片风格不一致 解决: 在提示词中明确指定相同的风格关键词,如 "cartoon style, hand-drawn, pastel colors"

问题: 图片内容太多,不够简洁 解决: 减少每张图的文字量,拆分为更多张图片,每张聚焦一个观点

问题: URL 抓取失败 解决: 检查网址是否可访问,或直接复制文章内容作为文本输入

问题: 目录已存在 解决: 自动追加时间戳,如 improve-work-efficiency-20260123-143052

问题: 图片生成失败 解决: 检查图片生成技能是否可用,确认 API 配置正确

模板参考

模板文件用途位置
文章拆解模板.md将文章拆解为系列图的分析模板${SKILL_DIR}/references/
封面图模板.md封面图提示词生成模板${SKILL_DIR}/references/
内容图模板.md内容图提示词生成模板${SKILL_DIR}/references/
结尾图模板.md结尾图提示词生成模板${SKILL_DIR}/references/

扩展配置

通过 EXTEND.md 支持自定义配置,检查路径 (优先级顺序):

  1. .pw-skills/pw-redbook-image/EXTEND.md (项目级)
  2. ~/.pw-skills/pw-redbook-image/EXTEND.md (用户级)

如果找到,在工作流程之前加载。扩展内容会覆盖默认值。

可自定义内容:

  • 默认图片数量范围
  • 风格关键词和配色方案
  • 作者信息格式
  • 输出目录命名规则
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
ego lite browserego lite browser
ego lite browser
Fastest browser for AI agents to run web automation tasks, always free.
Download Free life-time →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Open Steps
Open Steps
Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Agent, connect blockchain
Agent, connect blockchain
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →
Granola, the best AI meeting recorder
Granola, the best AI meeting recorder
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
CodeHealth MCP ServerCodeHealth MCP Server
CodeHealth MCP Server
Protect your code quality, stop the AI slop.
Try For Free →
First SeenJun 3, 2026
View on GitHub

More from plugins-world/pw-skills

All 2 skills →
  • Pw Embedded C Style223

Recommended

juliusbrussee avatar
caveman

juliusbrussee/caveman

Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
443.2k
98.9k
mattpocock avatar
grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.
896.5k
221k
shadcn avatar
improve

shadcn/improve

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.
29.7k
8.9k
obra avatar
systematic-debugging

obra/superpowers

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
229.2k
273.5k
forrestchang avatar
karpathy-guidelines

forrestchang/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.
17.9k
191.7k
vercel-labs avatar
find-skills

vercel-labs/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
3M
28.2k