Publish Markdown articles to X (Twitter) Articles editor with proper formatting. Use when user wants to publish a Markdown file/URL to X Articles, or mentions "publish to X", "post article to Twitter", "X article", or wants help with X Premium article publishing. Handles cover image upload and converts Markdown to rich text automatically.
/plugin marketplace add wshuyi/x-article-publisher-skill/plugin install wshuyi-x-article-publisher@wshuyi/x-article-publisher-skillThis skill inherits all available tools. When active, it can use any tool Claude has access to.
scripts/copy_to_clipboard.pyscripts/parse_markdown.pyPublish Markdown content to X (Twitter) Articles editor, preserving formatting with rich text conversion.
pip install Pillow pyobjc-framework-CocoaLocated in ~/.claude/skills/x-article-publisher/scripts/:
Parse Markdown and extract structured data:
python parse_markdown.py <markdown_file> [--output json|html] [--html-only]
Returns JSON with: title, cover_image, content_images (with block_index for positioning), html, total_blocks
Copy image or HTML to system clipboard:
# Copy image (with optional compression)
python copy_to_clipboard.py image /path/to/image.jpg [--quality 80]
# Copy HTML for rich text paste
python copy_to_clipboard.py html --file /path/to/content.html
Strategy: "先文后图" (Text First, Images Later)
For articles with multiple images, paste ALL text content first, then insert images at correct positions using block index.
目标: 最小化操作之间的等待时间,实现流畅的自动化体验。
大多数浏览器操作(click, type, press_key 等)都会在返回结果中包含页面状态。不要在每次操作后单独调用 browser_snapshot,直接使用操作返回的页面状态即可。
❌ 错误做法:
browser_click → browser_snapshot → 分析 → browser_click → browser_snapshot → ...
✅ 正确做法:
browser_click → 从返回结果中获取页面状态 → browser_click → ...
只在以下情况使用 browser_wait_for:
textGone="正在上传媒体")不要使用 browser_wait_for 来等待按钮或输入框出现 - 它们在页面加载完成后立即可用。
当两个操作没有依赖关系时,可以在同一个消息中并行调用多个工具:
✅ 可以并行:
- 填写标题 (browser_type) + 复制HTML到剪贴板 (Bash)
- 解析Markdown生成JSON + 生成HTML文件
❌ 不能并行(有依赖):
- 必须先点击create才能上传封面图
- 必须先粘贴内容才能插入图片
每个浏览器操作返回的页面状态包含所有需要的元素引用。直接使用这些引用进行下一步操作:
# 理想流程(每步直接执行,不额外等待):
browser_navigate → 从返回状态找create按钮 → browser_click(create)
→ 从返回状态找上传按钮 → browser_click(上传) → browser_file_upload
→ 从返回状态找应用按钮 → browser_click(应用)
→ 从返回状态找标题框 → browser_type(标题)
→ 点击编辑器 → browser_press_key(Meta+v)
→ ...
在开始浏览器操作之前,先完成所有准备工作:
这样浏览器操作阶段可以连续执行,不需要中途停下来处理数据。
Use parse_markdown.py to extract all structured data:
python ~/.claude/skills/x-article-publisher/scripts/parse_markdown.py /path/to/article.md
Output JSON:
{
"title": "Article Title",
"cover_image": "/path/to/first-image.jpg",
"content_images": [
{"path": "/path/to/img2.jpg", "block_index": 5, "after_text": "context for debugging..."},
{"path": "/path/to/img3.jpg", "block_index": 12, "after_text": "another context..."}
],
"html": "<p>Content...</p><h2>Section</h2>...",
"total_blocks": 45
}
Key fields:
block_index: The image should be inserted AFTER block element at this index (0-indexed)total_blocks: Total number of block elements in the HTMLafter_text: Kept for reference/debugging only, NOT for positioningSave HTML to temp file for clipboard:
python parse_markdown.py article.md --html-only > /tmp/article_html.html
browser_navigate: https://x.com/compose/articles
重要: 页面加载后会显示草稿列表,不是编辑器。需要:
browser_snapshot 检查页面状态# 1. 导航到页面
browser_navigate: https://x.com/compose/articles
# 2. 获取页面快照,找到 create 按钮
browser_snapshot
# 3. 点击 create 按钮(通常 ref 类似 "create" 或带有 create 标签)
browser_click: element="create button", ref=<create_button_ref>
# 4. 现在编辑器应该打开了,可以继续上传封面图等操作
注意: 不要使用 browser_wait_for text="添加标题" 来等待页面加载,因为这个文本只有在点击 create 后才出现,会导致超时。
If login needed, prompt user to log in manually.
Copy HTML to system clipboard using Python, then paste:
# Copy HTML to clipboard
python ~/.claude/skills/x-article-publisher/scripts/copy_to_clipboard.py html --file /tmp/article_html.html
Then in browser:
browser_click on editor textbox
browser_press_key: Meta+v
This preserves all rich text formatting (H2, bold, links, lists).
关键改进: 使用 block_index 精确定位,而非依赖文字匹配。
粘贴 HTML 后,编辑器中的内容结构为一系列块元素(段落、标题、引用等)。每张图片的 block_index 表示它应该插入在第 N 个块元素之后。
block_index 点击对应的块元素For each content image (from content_images array):
# 1. Copy image to clipboard (with compression)
python ~/.claude/skills/x-article-publisher/scripts/copy_to_clipboard.py image /path/to/img.jpg --quality 85
# 2. Click the block element at block_index
# Example: if block_index=5, click the 6th block element (0-indexed)
browser_click on the element at position block_index in the editor
# 3. Paste image
browser_press_key: Meta+v
# 4. Wait for upload (use short time, returns immediately when done)
browser_wait_for textGone="正在上传媒体" time=2
在 browser_snapshot 返回的结构中,编辑器内容通常是:
textbox [ref=xxx]:
generic [ref=block0]: # block_index 0
- paragraph content
heading [ref=block1]: # block_index 1
- h2 content
generic [ref=block2]: # block_index 2
- paragraph content
...
要在 block_index=5 后插入图片:
注意: 每插入一张图片后,后续图片的实际位置会偏移。建议按 block_index 从大到小的顺序插入图片,这样先插入的图片不会影响后续图片的索引。
如果有3张图片,block_index 分别为 5, 12, 27:
这样每次插入都不会影响前面已经定位好的位置。
...) - converted to blockquotes since X doesn't support <pre><code>User: "Publish /path/to/article.md to X"
# Step 1: Parse Markdown
python ~/.claude/skills/x-article-publisher/scripts/parse_markdown.py /path/to/article.md > /tmp/article.json
python ~/.claude/skills/x-article-publisher/scripts/parse_markdown.py /path/to/article.md --html-only > /tmp/article_html.html
title)python ~/.claude/skills/x-article-publisher/scripts/copy_to_clipboard.py html --file /tmp/article_html.html
Then: browser_press_key Meta+vpython copy_to_clipboard.py image /path/to/img.jpg --quality 85
block_index positionafter_text 仍保留用于人工核验关键理解: browser_wait_for 的 textGone 参数会在文字消失时立即返回,time 只是最大等待时间,不是固定等待时间。
time=5 或 time=10,如果上传只需2秒,剩余时间全浪费time=2,条件满足立即返回,最多等2秒# 正确用法:短 time 值,条件满足立即返回
browser_wait_for textGone="正在上传媒体" time=2
# 错误用法:固定长时间等待
browser_wait_for time=5 # 无条件等待5秒,浪费时间
原则: 不要预设"需要等多久",而是设置一个合理的最大值,让条件检测尽快返回。
每张图片的浏览器操作从5步减少到2步: