anbeime avatar

Content Creation Publisher

This is a complete content pipeline that chains together five separate skills to go from web URL to published article. It scrapes pages into Markdown using Chrome CDP, applies Chinese typography fixes (the formatting skill handles those pesky Chinese punctuation bold bugs), generates contextual illustrations in six types and eight styles, then publishes to WeChat or X/Twitter through browser automation. The workflow examples are actually helpful: you can see how it combines with paper analysis for academic content or ecommerce copywriting for product launches. The main gotcha is that three modules need Chrome installed and you'll probably need to manually log into accounts the first time. It's overkill if you just need one piece, but if you're running a content operation across Chinese and English platforms, having the whole chain automated saves real time.

GitHub stars
1.5K
last updated
Jun 11, 2026

Install

$ npx -y skills add anbeime/skill --skill content-creation-publisher --agent claude-code

Installs into .claude/skills of the current project.

Files

内容创作与发布全流程

任务目标

  • 本技能用于:从内容采集到发布的完整工作流
  • 能力包含:
    • 网页内容提取转Markdown
    • Markdown格式化和排版优化
    • 智能文章配图
    • 多平台自动发布(微信公众号、X/Twitter)
  • 触发条件:用户需要采集、编辑、配图、发布内容

核心功能模块

模块1:内容采集(baoyu-url-to-markdown)

功能:将任意网页转换为干净的Markdown格式

使用场景:

  • 采集文章、论文、新闻
  • 提取知识库内容
  • 保存网页内容

操作步骤:

  1. 提供网页URL
  2. 选择捕获模式:
    • 自动模式:页面加载后立即捕获
    • 等待模式:需要登录或交互的页面
  3. 自动提取并转换为Markdown

技术实现:

  • 使用Chrome CDP技术
  • 智能清理HTML标签
  • 保留文章结构和格式

模块2:格式优化(baoyu-format-markdown)

功能:格式化和优化Markdown文档

核心特性:

  1. 自动格式化

    • 添加frontmatter(标题、日期、标签)
    • 调整标题层级
    • 优化列表和代码块
  2. 排版优化

    • 修复中文标点符号导致的**加粗bug
    • 自动在中文和英文之间添加空格
    • ASCII标点转全角引号
    • CJK字符间距优化
  3. 内容增强

    • 自动生成摘要
    • 添加目录
    • 优化段落结构

使用场景:

  • 优化采集的内容
  • 格式化原创文章
  • 统一文档风格

模块3:智能配图(article-illustrator)

功能:分析文章内容,在需要视觉辅助的位置生成插图

配图类型:

  • 信息补充型:数据可视化、流程图
  • 概念具象化:抽象概念的视觉表达
  • 引导想象型:场景描绘、氛围营造

配图风格(6种类型 × 8种风格):

  • 类型:infographic、scene、flowchart、comparison、framework、timeline
  • 风格:notion、elegant、warm、minimal、blueprint、watercolor、editorial、scientific

操作步骤:

  1. 分析文章结构,识别需要配图的位置
  2. 为每个位置生成配图计划和提示词
  3. 使用图像生成能力创建插图
  4. 将图片插入到文章对应位置

模块4:多平台发布

Sponsors

Details

Repository
github.com/anbeime/skill
First seen
Jun 11, 2026

More from anbeime/skill

All 10

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps 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 int4.3Mskills.sh installs