X Article Publisher Publish Markdown content to X (Twitter) Articles editor, preserving formatting with rich text conversion. Prerequisites - Playwright MCP for browser automation - User logged into X with Premium Plus subscription - Python 3.9+ with dependencies: - macOS: - Windows: Scripts Located in : parse markdown.py Parse Markdown and extract structured data: Returns JSON with: title, cover image, content images (with block index for positioning), html, total blocks copy to clipboard.py Copy image or HTML to system clipboard: Workflow Strategy: "先文后图" (Text First, Images Later) For arti…

, stripped):\n if current_block:\n blocks.append('\\n'.join(current_block))\n current_block = []\n blocks.append(stripped)\n continue\n\n current_block.append(line)\n\n if current_block:\n blocks.append('\\n'.join(current_block))\n\n # Handle unclosed code block\n if code_block_lines:\n blocks.append('___CODE_BLOCK_START___' + '\\n'.join(code_block_lines) + '___CODE_BLOCK_END___')\n\n return blocks\n\n\ndef extract_images_with_block_index(markdown: str, base_path: Path) -> tuple[list[dict], str, int]:\n \"\"\"Extract images with their block index position.\n\n Returns:\n (image_list, markdown_without_images, total_blocks)\n \"\"\"\n blocks = split_into_blocks(markdown)\n images = []\n clean_blocks = []\n\n img_pattern = re.compile(r'^!\\[([^\\]]*)\\]\\(([^)]+)\\)

X Article Publisher Publish Markdown content to X (Twitter) Articles editor, preserving formatting with rich text conversion. Prerequisites - Playwright MCP for browser automation - User logged into X with Premium Plus subscription - Python 3.9+ with dependencies: - macOS: - Windows: Scripts Located in : parse markdown.py Parse Markdown and extract structured data: Returns JSON with: title, cover image, content images (with block index for positioning), html, total blocks copy to clipboard.py Copy image or HTML to system clipboard: Workflow Strategy: "先文后图" (Text First, Images Later) For arti…

)\n\n for i, block in enumerate(blocks):\n match = img_pattern.match(block.strip())\n if match:\n alt_text = match.group(1)\n img_path = match.group(2)\n\n # Resolve relative paths\n if not os.path.isabs(img_path):\n full_path = str(base_path / img_path)\n else:\n full_path = img_path\n\n # block_index is the index in clean_blocks (without images)\n # i.e., this image should be inserted after clean_blocks[block_index-1]\n block_index = len(clean_blocks)\n\n # Get context from previous block for reference\n after_text = \"\"\n if clean_blocks:\n prev_block = clean_blocks[-1].strip()\n # Get last line of previous block\n lines = [l for l in prev_block.split('\\n') if l.strip()]\n after_text = lines[-1][:80] if lines else \"\"\n\n images.append({\n \"path\": full_path,\n \"alt\": alt_text,\n \"block_index\": block_index,\n \"after_text\": after_text # Keep for reference/debugging\n })\n else:\n clean_blocks.append(block)\n\n clean_markdown = '\\n\\n'.join(clean_blocks)\n return images, clean_markdown, len(clean_blocks)\n\n\ndef extract_title(markdown: str) -> tuple[str, str]:\n \"\"\"Extract title from first H1, H2, or first non-empty line.\n\n Returns:\n (title, markdown_without_title): Title string and markdown with H1 title removed.\n If title is from H1, it's removed from markdown to avoid duplication.\n \"\"\"\n lines = markdown.strip().split('\\n')\n title = \"Untitled\"\n title_line_idx = None\n\n for idx, line in enumerate(lines):\n stripped = line.strip()\n if not stripped:\n continue\n # H1 - use as title and mark for removal\n if stripped.startswith('# '):\n title = stripped[2:].strip()\n title_line_idx = idx\n break\n # H2 - use as title but don't remove (it's a section header)\n if stripped.startswith('## '):\n title = stripped[3:].strip()\n break\n # First non-empty, non-image line\n if not stripped.startswith('!['):\n title = stripped[:100]\n break\n\n # Remove H1 title line from markdown to avoid duplication\n if title_line_idx is not None:\n lines.pop(title_line_idx)\n markdown = '\\n'.join(lines)\n\n return title, markdown\n\n\ndef markdown_to_html(markdown: str) -> str:\n \"\"\"Convert markdown to HTML for X Articles rich text paste.\"\"\"\n html = markdown\n\n # Process code blocks first (marked with ___CODE_BLOCK_START___ and ___CODE_BLOCK_END___)\n # Convert to blockquote format since X Articles doesn't support \u003cpre>\u003ccode>\n def convert_code_block(match):\n code_content = match.group(1)\n lines = code_content.strip().split('\\n')\n # Join non-empty lines with \u003cbr> for display\n formatted = '\u003cbr>'.join(line for line in lines if line.strip())\n return f'\u003cblockquote>{formatted}\u003c/blockquote>'\n\n html = re.sub(r'___CODE_BLOCK_START___(.*?)___CODE_BLOCK_END___', convert_code_block, html, flags=re.DOTALL)\n\n # Headers (H2 only, H1 is title)\n html = re.sub(r'^## (.+)

X Article Publisher Publish Markdown content to X (Twitter) Articles editor, preserving formatting with rich text conversion. Prerequisites - Playwright MCP for browser automation - User logged into X with Premium Plus subscription - Python 3.9+ with dependencies: - macOS: - Windows: Scripts Located in : parse markdown.py Parse Markdown and extract structured data: Returns JSON with: title, cover image, content images (with block index for positioning), html, total blocks copy to clipboard.py Copy image or HTML to system clipboard: Workflow Strategy: "先文后图" (Text First, Images Later) For arti…

, r'\u003ch2>\\1\u003c/h2>', html, flags=re.MULTILINE)\n html = re.sub(r'^### (.+)

X Article Publisher Publish Markdown content to X (Twitter) Articles editor, preserving formatting with rich text conversion. Prerequisites - Playwright MCP for browser automation - User logged into X with Premium Plus subscription - Python 3.9+ with dependencies: - macOS: - Windows: Scripts Located in : parse markdown.py Parse Markdown and extract structured data: Returns JSON with: title, cover image, content images (with block index for positioning), html, total blocks copy to clipboard.py Copy image or HTML to system clipboard: Workflow Strategy: "先文后图" (Text First, Images Later) For arti…

, r'\u003ch3>\\1\u003c/h3>', html, flags=re.MULTILINE)\n\n # Bold\n html = re.sub(r'\\*\\*(.+?)\\*\\*', r'\u003cstrong>\\1\u003c/strong>', html)\n\n # Italic\n html = re.sub(r'\\*([^*]+)\\*', r'\u003cem>\\1\u003c/em>', html)\n\n # Links\n html = re.sub(r'\\[([^\\]]+)\\]\\(([^)]+)\\)', r'\u003ca href=\"\\2\">\\1\u003c/a>', html)\n\n # Blockquotes (regular markdown blockquotes, not code blocks)\n html = re.sub(r'^> (.+)

X Article Publisher Publish Markdown content to X (Twitter) Articles editor, preserving formatting with rich text conversion. Prerequisites - Playwright MCP for browser automation - User logged into X with Premium Plus subscription - Python 3.9+ with dependencies: - macOS: - Windows: Scripts Located in : parse markdown.py Parse Markdown and extract structured data: Returns JSON with: title, cover image, content images (with block index for positioning), html, total blocks copy to clipboard.py Copy image or HTML to system clipboard: Workflow Strategy: "先文后图" (Text First, Images Later) For arti…

, r'\u003cblockquote>\\1\u003c/blockquote>', html, flags=re.MULTILINE)\n\n # Unordered lists\n html = re.sub(r'^- (.+)

X Article Publisher Publish Markdown content to X (Twitter) Articles editor, preserving formatting with rich text conversion. Prerequisites - Playwright MCP for browser automation - User logged into X with Premium Plus subscription - Python 3.9+ with dependencies: - macOS: - Windows: Scripts Located in : parse markdown.py Parse Markdown and extract structured data: Returns JSON with: title, cover image, content images (with block index for positioning), html, total blocks copy to clipboard.py Copy image or HTML to system clipboard: Workflow Strategy: "先文后图" (Text First, Images Later) For arti…

, r'\u003cli>\\1\u003c/li>', html, flags=re.MULTILINE)\n\n # Ordered lists\n html = re.sub(r'^\\d+\\. (.+)

X Article Publisher Publish Markdown content to X (Twitter) Articles editor, preserving formatting with rich text conversion. Prerequisites - Playwright MCP for browser automation - User logged into X with Premium Plus subscription - Python 3.9+ with dependencies: - macOS: - Windows: Scripts Located in : parse markdown.py Parse Markdown and extract structured data: Returns JSON with: title, cover image, content images (with block index for positioning), html, total blocks copy to clipboard.py Copy image or HTML to system clipboard: Workflow Strategy: "先文后图" (Text First, Images Later) For arti…

, r'\u003cli>\\1\u003c/li>', html, flags=re.MULTILINE)\n\n # Wrap consecutive \u003cli> in \u003cul>\n html = re.sub(r'((?:\u003cli>.*?\u003c/li>\\n?)+)', r'\u003cul>\\1\u003c/ul>', html)\n\n # Paragraphs - split by double newlines\n parts = html.split('\\n\\n')\n processed_parts = []\n\n for part in parts:\n part = part.strip()\n if not part:\n continue\n # Skip if already a block element\n if part.startswith(('\u003ch2>', '\u003ch3>', '\u003cblockquote>', '\u003cul>', '\u003col>')):\n processed_parts.append(part)\n else:\n # Wrap in paragraph, convert single newlines to \u003cbr>\n part = part.replace('\\n', '\u003cbr>')\n processed_parts.append(f'\u003cp>{part}\u003c/p>')\n\n return ''.join(processed_parts)\n\n\ndef parse_markdown_file(filepath: str) -> dict:\n \"\"\"Parse a markdown file and return structured data.\"\"\"\n path = Path(filepath)\n base_path = path.parent\n\n with open(filepath, 'r', encoding='utf-8') as f:\n content = f.read()\n\n # Extract title first (and remove H1 from markdown)\n title, content = extract_title(content)\n\n # Extract images with block indices\n images, clean_markdown, total_blocks = extract_images_with_block_index(content, base_path)\n\n # Convert to HTML\n html = markdown_to_html(clean_markdown)\n\n # Separate cover image from content images\n cover_image = images[0][\"path\"] if images else None\n content_images = images[1:] if len(images) > 1 else []\n\n # Adjust block_index for content images (subtract 1 since cover image is removed)\n # The first content image's block_index was calculated including cover image's position\n\n return {\n \"title\": title,\n \"cover_image\": cover_image,\n \"content_images\": content_images,\n \"html\": html,\n \"total_blocks\": total_blocks,\n \"source_file\": str(path.absolute())\n }\n\n\ndef main():\n parser = argparse.ArgumentParser(description='Parse Markdown for X Articles')\n parser.add_argument('file', help='Markdown file to parse')\n parser.add_argument('--output', choices=['json', 'html'], default='json',\n help='Output format (default: json)')\n parser.add_argument('--html-only', action='store_true',\n help='Output only HTML content')\n\n args = parser.parse_args()\n\n if not os.path.exists(args.file):\n print(f\"Error: File not found: {args.file}\", file=sys.stderr)\n sys.exit(1)\n\n result = parse_markdown_file(args.file)\n\n if args.html_only:\n print(result['html'])\n elif args.output == 'json':\n print(json.dumps(result, ensure_ascii=False, indent=2))\n else:\n print(result['html'])\n\n\nif __name__ == '__main__':\n main()\n","content_type":"text/x-python; charset=utf-8","language":"python","size":10217,"content_sha256":"b2d3b9ad90406738d8e1dd29723c4572790936868f6b23d988f5063b826b8296"},{"filename":"skill-report.json","content":"{\n \"schema_version\": \"2.0\",\n \"meta\": {\n \"generated_at\": \"2026-01-17T08:50:28.421Z\",\n \"slug\": \"wshuyi-x-article-publisher\",\n \"source_url\": \"https://github.com/wshuyi/x-article-publisher-skill/tree/main/skills/x-article-publisher/\",\n \"source_ref\": \"main\",\n \"model\": \"claude\",\n \"analysis_version\": \"3.0.0\",\n \"source_type\": \"community\",\n \"content_hash\": \"fa7512d83d019886a6c218f24b20415400002cb11cf0afc83f3d0c7cb90f3105\",\n \"tree_hash\": \"fa569426520ba17b1ab4266800e894817cae0ca677aec8bc8288c3bd5e2b28d3\"\n },\n \"skill\": {\n \"name\": \"x-article-publisher\",\n \"description\": \"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.\",\n \"summary\": \"Publish Markdown articles to X (Twitter) Articles editor with proper formatting. Use when user wants...\",\n \"icon\": \"📝\",\n \"version\": \"1.0.0\",\n \"author\": \"wshuyi\",\n \"license\": \"MIT\",\n \"category\": \"writing\",\n \"tags\": [\n \"x\",\n \"twitter\",\n \"markdown\",\n \"publishing\",\n \"articles\"\n ],\n \"supported_tools\": [\n \"claude\",\n \"codex\",\n \"claude-code\"\n ],\n \"risk_factors\": [\n \"scripts\",\n \"filesystem\"\n ]\n },\n \"security_audit\": {\n \"risk_level\": \"safe\",\n \"is_blocked\": false,\n \"safe_to_publish\": true,\n \"summary\": \"This is a legitimate content publishing skill with two Python scripts for Markdown parsing and clipboard operations. Both scripts only access user-specified files via command-line arguments, perform no network requests, no command execution, and no sensitive data access. All 103 static findings are false positives: argparse parsers were misidentified as cryptographic algorithms, and markdown code formatting was misidentified as shell execution.\",\n \"risk_factor_evidence\": [\n {\n \"factor\": \"scripts\",\n \"evidence\": [\n {\n \"file\": \"scripts/parse_markdown.py\",\n \"line_start\": 1,\n \"line_end\": 313\n },\n {\n \"file\": \"scripts/copy_to_clipboard.py\",\n \"line_start\": 1,\n \"line_end\": 180\n }\n ]\n },\n {\n \"factor\": \"filesystem\",\n \"evidence\": [\n {\n \"file\": \"scripts/parse_markdown.py\",\n \"line_start\": 253,\n \"line_end\": 260\n },\n {\n \"file\": \"scripts/copy_to_clipboard.py\",\n \"line_start\": 147,\n \"line_end\": 165\n }\n ]\n }\n ],\n \"critical_findings\": [],\n \"high_findings\": [],\n \"medium_findings\": [],\n \"low_findings\": [],\n \"dangerous_patterns\": [],\n \"files_scanned\": 4,\n \"total_lines\": 1081,\n \"audit_model\": \"claude\",\n \"audited_at\": \"2026-01-17T08:50:28.421Z\"\n },\n \"content\": {\n \"user_title\": \"Publish Markdown articles to X\",\n \"value_statement\": \"Converts Markdown files to rich text and publishes them to X (Twitter) Articles. Automates the workflow of parsing content, uploading images, and formatting for the X Articles editor.\",\n \"seo_keywords\": [\n \"X Articles publisher\",\n \"Twitter Articles markdown\",\n \"publish to X\",\n \"markdown to twitter\",\n \"claude code skill\",\n \"claude skill\",\n \"codex skill\",\n \"content publishing\"\n ],\n \"actual_capabilities\": [\n \"Parse Markdown files and extract title, images, and content\",\n \"Convert Markdown to HTML for rich text paste\",\n \"Copy images and HTML to system clipboard\",\n \"Insert images at precise positions using block index\",\n \"Compress images before uploading for better performance\"\n ],\n \"limitations\": [\n \"Requires macOS for clipboard operations\",\n \"Requires X Premium Plus subscription\",\n \"Requires Playwright MCP for browser automation\",\n \"Only saves as draft, never auto-publishes\"\n ],\n \"use_cases\": [\n {\n \"target_user\": \"Content creators\",\n \"title\": \"Publish blog posts\",\n \"description\": \"Convert Markdown blog posts and publish them to X Articles with full formatting preserved\"\n },\n {\n \"target_user\": \"Technical writers\",\n \"title\": \"Share documentation\",\n \"description\": \"Publish technical documentation with code blocks and images to X Articles\"\n },\n {\n \"target_user\": \"Social media managers\",\n \"title\": \"Cross-post articles\",\n \"description\": \"Transform existing Markdown content into X Articles format for broader reach\"\n }\n ],\n \"prompt_templates\": [\n {\n \"title\": \"Basic publish\",\n \"scenario\": \"Publish a Markdown article\",\n \"prompt\": \"Publish the Markdown file at [path_to_file] to X Articles\"\n },\n {\n \"title\": \"With custom images\",\n \"scenario\": \"Specify cover image\",\n \"prompt\": \"Publish [markdown_file] with [image_path] as the cover image to X Articles\"\n },\n {\n \"title\": \"Draft workflow\",\n \"scenario\": \"Save as draft\",\n \"prompt\": \"Parse [article.md] and prepare it for X Articles, then save it as a draft\"\n },\n {\n \"title\": \"Multi-image article\",\n \"scenario\": \"Handle complex article\",\n \"prompt\": \"Publish [long_article.md] to X Articles. Make sure to insert all content images at their correct positions.\"\n }\n ],\n \"output_examples\": [\n {\n \"input\": \"Publish my article.md to X Articles\",\n \"output\": [\n \"Draft saved to X Articles\",\n \"Title and cover image set\",\n \"All content pasted with formatting\",\n \"5 images inserted at correct positions\",\n \"Please review and publish manually\"\n ]\n },\n {\n \"input\": \"Convert this technical documentation to an X Article\",\n \"output\": [\n \"Parsed 25 content blocks from Markdown\",\n \"Extracted 8 images with block indices\",\n \"Converted code blocks to blockquote format\",\n \"Saved draft with proper formatting\"\n ]\n }\n ],\n \"best_practices\": [\n \"Always verify the draft before publishing manually\",\n \"Insert images in reverse order of block_index to maintain positioning\",\n \"Use image compression (--quality 85) for faster uploads\"\n ],\n \"anti_patterns\": [\n \"Do not try to publish directly without reviewing the draft first\",\n \"Do not skip the Markdown parsing step before editing\",\n \"Do not insert images in ascending block_index order\"\n ],\n \"faq\": [\n {\n \"question\": \"Which platforms support this skill?\",\n \"answer\": \"This skill works with Claude, Codex, and Claude Code when Playwright MCP is available.\"\n },\n {\n \"question\": \"What are the size limits for X Articles?\",\n \"answer\": \"X Articles have a content length limit. Very long articles may need to be split across multiple posts.\"\n },\n {\n \"question\": \"How does it integrate with the browser?\",\n \"answer\": \"It uses Playwright MCP tools for navigation, clicks, file uploads, and keyboard shortcuts.\"\n },\n {\n \"question\": \"Is my data safe with this skill?\",\n \"answer\": \"Yes. The skill only accesses files you explicitly specify and never sends data to external servers.\"\n },\n {\n \"question\": \"Why is my image upload failing?\",\n \"answer\": \"Ensure the image path is correct and the file exists. Use absolute paths for best results.\"\n },\n {\n \"question\": \"How is this different from manual publishing?\",\n \"answer\": \"Automates Markdown parsing, image positioning, and clipboard operations for faster publishing.\"\n }\n ]\n },\n \"file_structure\": [\n {\n \"name\": \"scripts\",\n \"type\": \"dir\",\n \"path\": \"scripts\",\n \"children\": [\n {\n \"name\": \"copy_to_clipboard.py\",\n \"type\": \"file\",\n \"path\": \"scripts/copy_to_clipboard.py\",\n \"lines\": 180\n },\n {\n \"name\": \"parse_markdown.py\",\n \"type\": \"file\",\n \"path\": \"scripts/parse_markdown.py\",\n \"lines\": 313\n }\n ]\n },\n {\n \"name\": \"SKILL.md\",\n \"type\": \"file\",\n \"path\": \"SKILL.md\",\n \"lines\": 362\n }\n ]\n}\n","content_type":"application/json; charset=utf-8","language":"json","size":8437,"content_sha256":"41eb6f9b6ab09685c1bda7804a0c83a711b52f7aa4060e8dafd0a6073ed8e903"}],"content_json":{"type":"doc","content":[{"type":"heading","attrs":{"level":1},"content":[{"text":"X Article Publisher","type":"text"}]},{"type":"paragraph","content":[{"text":"Publish Markdown content to X (Twitter) Articles editor, preserving formatting with rich text conversion.","type":"text"}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Prerequisites","type":"text"}]},{"type":"bullet_list","content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Playwright MCP for browser automation","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"User logged into X with Premium Plus subscription","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Python 3.9+ with dependencies:","type":"text"}]},{"type":"bullet_list","content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"macOS: ","type":"text"},{"text":"pip install Pillow pyobjc-framework-Cocoa","type":"text","marks":[{"type":"code_inline"}]}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Windows: ","type":"text"},{"text":"pip install Pillow pywin32 clip-util","type":"text","marks":[{"type":"code_inline"}]}]}]}]}]}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Scripts","type":"text"}]},{"type":"paragraph","content":[{"text":"Located in ","type":"text"},{"text":"~/.claude/skills/x-article-publisher/scripts/","type":"text","marks":[{"type":"code_inline"}]},{"text":":","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"parse_markdown.py","type":"text"}]},{"type":"paragraph","content":[{"text":"Parse Markdown and extract structured data:","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":"bash"},"content":[{"text":"python parse_markdown.py \u003cmarkdown_file> [--output json|html] [--html-only]","type":"text"}]},{"type":"paragraph","content":[{"text":"Returns JSON with: title, cover_image, content_images (with block_index for positioning), html, total_blocks","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"copy_to_clipboard.py","type":"text"}]},{"type":"paragraph","content":[{"text":"Copy image or HTML to system clipboard:","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":"bash"},"content":[{"text":"# Copy image (with optional compression)\npython copy_to_clipboard.py image /path/to/image.jpg [--quality 80]\n\n# Copy HTML for rich text paste\npython copy_to_clipboard.py html --file /path/to/content.html","type":"text"}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Workflow","type":"text"}]},{"type":"paragraph","content":[{"text":"Strategy: \"先文后图\" (Text First, Images Later)","type":"text","marks":[{"type":"strong"}]}]},{"type":"paragraph","content":[{"text":"For articles with multiple images, paste ALL text content first, then insert images at correct positions using block index.","type":"text"}]},{"type":"ordered_list","attrs":{"order":1,"listStyle":"number"},"content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Parse Markdown with Python script → get title, images with block_index, HTML","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Navigate to X Articles editor","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Upload cover image (first image)","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Fill title","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Copy HTML to clipboard (Python) → Paste with Cmd+V","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Insert content images at positions specified by block_index","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Save as draft (NEVER auto-publish)","type":"text"}]}]}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"高效执行原则 (Efficiency Guidelines)","type":"text"}]},{"type":"paragraph","content":[{"text":"目标","type":"text","marks":[{"type":"strong"}]},{"text":": 最小化操作之间的等待时间，实现流畅的自动化体验。","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"1. 避免不必要的 browser_snapshot","type":"text"}]},{"type":"paragraph","content":[{"text":"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。","type":"text"},{"text":"不要","type":"text","marks":[{"type":"strong"}]},{"text":"在每次操作后单独调用 ","type":"text"},{"text":"browser_snapshot","type":"text","marks":[{"type":"code_inline"}]},{"text":"，直接使用操作返回的页面状态即可。","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":""},"content":[{"text":"❌ 错误做法：\nbrowser_click → browser_snapshot → 分析 → browser_click → browser_snapshot → ...\n\n✅ 正确做法：\nbrowser_click → 从返回结果中获取页面状态 → browser_click → ...","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"2. 避免不必要的 browser_wait_for","type":"text"}]},{"type":"paragraph","content":[{"text":"只在以下情况使用 ","type":"text"},{"text":"browser_wait_for","type":"text","marks":[{"type":"code_inline"}]},{"text":"：","type":"text"}]},{"type":"bullet_list","content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"等待图片上传完成（","type":"text"},{"text":"textGone=\"正在上传媒体\"","type":"text","marks":[{"type":"code_inline"}]},{"text":"）","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"等待页面初始加载（极少数情况）","type":"text"}]}]}]},{"type":"paragraph","content":[{"text":"不要","type":"text","marks":[{"type":"strong"}]},{"text":"使用 ","type":"text"},{"text":"browser_wait_for","type":"text","marks":[{"type":"code_inline"}]},{"text":" 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。","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"3. 并行执行独立操作","type":"text"}]},{"type":"paragraph","content":[{"text":"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：","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":""},"content":[{"text":"✅ 可以并行：\n- 填写标题 (browser_type) + 复制HTML到剪贴板 (Bash)\n- 解析Markdown生成JSON + 生成HTML文件\n\n❌ 不能并行（有依赖）：\n- 必须先点击create才能上传封面图\n- 必须先粘贴内容才能插入图片","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"4. 连续执行浏览器操作","type":"text"}]},{"type":"paragraph","content":[{"text":"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：","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":""},"content":[{"text":"# 理想流程（每步直接执行，不额外等待）：\nbrowser_navigate → 从返回状态找create按钮 → browser_click(create)\n→ 从返回状态找上传按钮 → browser_click(上传) → browser_file_upload\n→ 从返回状态找应用按钮 → browser_click(应用)\n→ 从返回状态找标题框 → browser_type(标题)\n→ 点击编辑器 → browser_press_key(Meta+v)\n→ ...","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"5. 准备工作前置","type":"text"}]},{"type":"paragraph","content":[{"text":"在开始浏览器操作之前，先完成所有准备工作：","type":"text"}]},{"type":"ordered_list","attrs":{"order":1,"listStyle":"number"},"content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"解析 Markdown 获取 JSON 数据","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"生成 HTML 文件到 /tmp/","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"记录 title、cover_image、content_images 等信息","type":"text"}]}]}]},{"type":"paragraph","content":[{"text":"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。","type":"text"}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Step 1: Parse Markdown (Python)","type":"text"}]},{"type":"paragraph","content":[{"text":"Use ","type":"text"},{"text":"parse_markdown.py","type":"text","marks":[{"type":"code_inline"}]},{"text":" to extract all structured data:","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":"bash"},"content":[{"text":"python ~/.claude/skills/x-article-publisher/scripts/parse_markdown.py /path/to/article.md","type":"text"}]},{"type":"paragraph","content":[{"text":"Output JSON:","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":"json"},"content":[{"text":"{\n \"title\": \"Article Title\",\n \"cover_image\": \"/path/to/first-image.jpg\",\n \"content_images\": [\n {\"path\": \"/path/to/img2.jpg\", \"block_index\": 5, \"after_text\": \"context for debugging...\"},\n {\"path\": \"/path/to/img3.jpg\", \"block_index\": 12, \"after_text\": \"another context...\"}\n ],\n \"html\": \"\u003cp>Content...\u003c/p>\u003ch2>Section\u003c/h2>...\",\n \"total_blocks\": 45\n}","type":"text"}]},{"type":"paragraph","content":[{"text":"Key fields:","type":"text","marks":[{"type":"strong"}]}]},{"type":"bullet_list","content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"block_index","type":"text","marks":[{"type":"code_inline"}]},{"text":": The image should be inserted AFTER block element at this index (0-indexed)","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"total_blocks","type":"text","marks":[{"type":"code_inline"}]},{"text":": Total number of block elements in the HTML","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"after_text","type":"text","marks":[{"type":"code_inline"}]},{"text":": Kept for reference/debugging only, NOT for positioning","type":"text"}]}]}]},{"type":"paragraph","content":[{"text":"Save HTML to temp file for clipboard:","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":"bash"},"content":[{"text":"python parse_markdown.py article.md --html-only > /tmp/article_html.html","type":"text"}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Step 2: Open X Articles Editor","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":""},"content":[{"text":"browser_navigate: https://x.com/compose/articles","type":"text"}]},{"type":"paragraph","content":[{"text":"重要","type":"text","marks":[{"type":"strong"}]},{"text":": 页面加载后会显示草稿列表，不是编辑器。需要：","type":"text"}]},{"type":"ordered_list","attrs":{"order":1,"listStyle":"number"},"content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"等待页面加载完成","type":"text","marks":[{"type":"strong"}]},{"text":": 使用 ","type":"text"},{"text":"browser_snapshot","type":"text","marks":[{"type":"code_inline"}]},{"text":" 检查页面状态","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"立即点击 \"create\" 按钮","type":"text","marks":[{"type":"strong"}]},{"text":": 不要等待 \"添加标题\" 等编辑器元素，它们只有点击 create 后才出现","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"等待编辑器加载","type":"text","marks":[{"type":"strong"}]},{"text":": 点击 create 后，等待编辑器元素出现","type":"text"}]}]}]},{"type":"code_block","attrs":{"wrap":false,"language":""},"content":[{"text":"# 1. 导航到页面\nbrowser_navigate: https://x.com/compose/articles\n\n# 2. 获取页面快照，找到 create 按钮\nbrowser_snapshot\n\n# 3. 点击 create 按钮（通常 ref 类似 \"create\" 或带有 create 标签）\nbrowser_click: element=\"create button\", ref=\u003ccreate_button_ref>\n\n# 4. 现在编辑器应该打开了，可以继续上传封面图等操作","type":"text"}]},{"type":"paragraph","content":[{"text":"注意","type":"text","marks":[{"type":"strong"}]},{"text":": 不要使用 ","type":"text"},{"text":"browser_wait_for text=\"添加标题\"","type":"text","marks":[{"type":"code_inline"}]},{"text":" 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。","type":"text"}]},{"type":"paragraph","content":[{"text":"If login needed, prompt user to log in manually.","type":"text"}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Step 3: Upload Cover Image","type":"text"}]},{"type":"ordered_list","attrs":{"order":1,"listStyle":"number"},"content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Click \"添加照片或视频\" button","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Use browser_file_upload with the cover image path (from JSON output)","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Verify image uploaded","type":"text"}]}]}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Step 4: Fill Title","type":"text"}]},{"type":"bullet_list","content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Find textbox with \"添加标题\" placeholder","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Use browser_type to input title (from JSON output)","type":"text"}]}]}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Step 5: Paste Text Content (Python Clipboard)","type":"text"}]},{"type":"paragraph","content":[{"text":"Copy HTML to system clipboard using Python, then paste:","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":"bash"},"content":[{"text":"# Copy HTML to clipboard\npython ~/.claude/skills/x-article-publisher/scripts/copy_to_clipboard.py html --file /tmp/article_html.html","type":"text"}]},{"type":"paragraph","content":[{"text":"Then in browser:","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":""},"content":[{"text":"browser_click on editor textbox\nbrowser_press_key: Meta+v","type":"text"}]},{"type":"paragraph","content":[{"text":"This preserves all rich text formatting (H2, bold, links, lists).","type":"text"}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Step 6: Insert Content Images (Block Index Positioning)","type":"text"}]},{"type":"paragraph","content":[{"text":"关键改进","type":"text","marks":[{"type":"strong"}]},{"text":": 使用 ","type":"text"},{"text":"block_index","type":"text","marks":[{"type":"code_inline"}]},{"text":" 精确定位，而非依赖文字匹配。","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"定位原理","type":"text"}]},{"type":"paragraph","content":[{"text":"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 ","type":"text"},{"text":"block_index","type":"text","marks":[{"type":"code_inline"}]},{"text":" 表示它应该插入在第 N 个块元素之后。","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"操作步骤","type":"text"}]},{"type":"ordered_list","attrs":{"order":1,"listStyle":"number"},"content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"获取所有块元素","type":"text","marks":[{"type":"strong"}]},{"text":": 使用 browser_snapshot 获取编辑器内容，找到 textbox 下的所有子元素","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"按索引定位","type":"text","marks":[{"type":"strong"}]},{"text":": 根据 ","type":"text"},{"text":"block_index","type":"text","marks":[{"type":"code_inline"}]},{"text":" 点击对应的块元素","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"粘贴图片","type":"text","marks":[{"type":"strong"}]},{"text":": 复制图片到剪贴板后粘贴","type":"text"}]}]}]},{"type":"paragraph","content":[{"text":"For each content image (from ","type":"text"},{"text":"content_images","type":"text","marks":[{"type":"code_inline"}]},{"text":" array):","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":"bash"},"content":[{"text":"# 1. Copy image to clipboard (with compression)\npython ~/.claude/skills/x-article-publisher/scripts/copy_to_clipboard.py image /path/to/img.jpg --quality 85","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":""},"content":[{"text":"# 2. Click the block element at block_index\n# Example: if block_index=5, click the 6th block element (0-indexed)\nbrowser_click on the element at position block_index in the editor\n\n# 3. Paste image\nbrowser_press_key: Meta+v\n\n# 4. Wait for upload (use short time, returns immediately when done)\nbrowser_wait_for textGone=\"正在上传媒体\" time=2","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"定位策略","type":"text"}]},{"type":"paragraph","content":[{"text":"在 browser_snapshot 返回的结构中，编辑器内容通常是：","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":"yaml"},"content":[{"text":"textbox [ref=xxx]:\n generic [ref=block0]: # block_index 0\n - paragraph content\n heading [ref=block1]: # block_index 1\n - h2 content\n generic [ref=block2]: # block_index 2\n - paragraph content\n ...","type":"text"}]},{"type":"paragraph","content":[{"text":"要在 ","type":"text"},{"text":"block_index=5","type":"text","marks":[{"type":"code_inline"}]},{"text":" 后插入图片：","type":"text"}]},{"type":"ordered_list","attrs":{"order":1,"listStyle":"number"},"content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"找到编辑器 textbox 下的第 6 个子元素（索引从0开始）","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"点击该元素","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"粘贴图片","type":"text"}]}]}]},{"type":"paragraph","content":[{"text":"注意","type":"text","marks":[{"type":"strong"}]},{"text":": 每插入一张图片后，后续图片的实际位置会偏移。建议按 ","type":"text"},{"text":"block_index","type":"text","marks":[{"type":"code_inline"}]},{"text":" ","type":"text"},{"text":"从大到小","type":"text","marks":[{"type":"strong"}]},{"text":"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。","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"反向插入示例","type":"text"}]},{"type":"paragraph","content":[{"text":"如果有3张图片，block_index 分别为 5, 12, 27：","type":"text"}]},{"type":"ordered_list","attrs":{"order":1,"listStyle":"number"},"content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"先插入 block_index=27 的图片","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"再插入 block_index=12 的图片","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"最后插入 block_index=5 的图片","type":"text"}]}]}]},{"type":"paragraph","content":[{"text":"这样每次插入都不会影响前面已经定位好的位置。","type":"text"}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Step 7: Save Draft","type":"text"}]},{"type":"ordered_list","attrs":{"order":1,"listStyle":"number"},"content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Verify content pasted (check word count indicator)","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Draft auto-saves, or click Save button if needed","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Click \"预览\" to verify formatting","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Report: \"Draft saved. Review and publish manually.\"","type":"text"}]}]}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Critical Rules","type":"text"}]},{"type":"ordered_list","attrs":{"order":1,"listStyle":"number"},"content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"NEVER publish","type":"text","marks":[{"type":"strong"}]},{"text":" - Only save draft","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"First image = cover","type":"text","marks":[{"type":"strong"}]},{"text":" - Upload first image as cover image","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Rich text conversion","type":"text","marks":[{"type":"strong"}]},{"text":" - Always convert Markdown to HTML before pasting","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Use clipboard API","type":"text","marks":[{"type":"strong"}]},{"text":" - Paste via clipboard for proper formatting","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Block index positioning","type":"text","marks":[{"type":"strong"}]},{"text":" - Use block_index for precise image placement","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Reverse order insertion","type":"text","marks":[{"type":"strong"}]},{"text":" - Insert images from highest to lowest block_index","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"H1 title handling","type":"text","marks":[{"type":"strong"}]},{"text":" - H1 is used as title only, not included in body","type":"text"}]}]}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Supported Formatting","type":"text"}]},{"type":"bullet_list","content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"H2 headers (## )","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Blockquotes (> )","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Code blocks (","type":"text"},{"text":"...","type":"text","marks":[{"type":"code_inline"}]},{"text":") - converted to blockquotes since X doesn't support ","type":"text"},{"text":"\u003cpre>\u003ccode>","type":"text","marks":[{"type":"code_inline"}]}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Bold text (**)","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Hyperlinks (","type":"text"},{"text":"text","type":"text","marks":[{"type":"link","attrs":{"href":"url","title":null}}]},{"text":")","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Ordered lists (1. 2. 3.)","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Unordered lists (- )","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Paragraphs","type":"text"}]}]}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Example Flow","type":"text"}]},{"type":"paragraph","content":[{"text":"User: \"Publish /path/to/article.md to X\"","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":"bash"},"content":[{"text":"# Step 1: Parse Markdown\npython ~/.claude/skills/x-article-publisher/scripts/parse_markdown.py /path/to/article.md > /tmp/article.json\npython ~/.claude/skills/x-article-publisher/scripts/parse_markdown.py /path/to/article.md --html-only > /tmp/article_html.html","type":"text"}]},{"type":"ordered_list","attrs":{"order":2,"listStyle":"number"},"content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Navigate to https://x.com/compose/articles","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Upload cover image (browser_file_upload for cover only)","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Fill title (from JSON: ","type":"text"},{"text":"title","type":"text","marks":[{"type":"code_inline"}]},{"text":")","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Copy & paste HTML:","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":"bash"},"content":[{"text":"python ~/.claude/skills/x-article-publisher/scripts/copy_to_clipboard.py html --file /tmp/article_html.html","type":"text"}]},{"type":"paragraph","content":[{"text":"Then: browser_press_key Meta+v","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"For each content image, ","type":"text"},{"text":"in reverse order of block_index","type":"text","marks":[{"type":"strong"}]},{"text":":","type":"text"}]},{"type":"code_block","attrs":{"wrap":false,"language":"bash"},"content":[{"text":"python copy_to_clipboard.py image /path/to/img.jpg --quality 85","type":"text"}]},{"type":"bullet_list","content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Click block element at ","type":"text"},{"text":"block_index","type":"text","marks":[{"type":"code_inline"}]},{"text":" position","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"browser_press_key Meta+v","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Wait until upload complete","type":"text"}]}]}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"Verify in preview","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"\"Draft saved. Please review and publish manually.\"","type":"text"}]}]}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Best Practices","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"为什么用 block_index 而非文字匹配？","type":"text"}]},{"type":"ordered_list","attrs":{"order":1,"listStyle":"number"},"content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"精确定位","type":"text","marks":[{"type":"strong"}]},{"text":": 不依赖文字内容，即使多处文字相似也能正确定位","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"可靠性","type":"text","marks":[{"type":"strong"}]},{"text":": 索引是确定性的，不会因为文字相似而混淆","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"调试方便","type":"text","marks":[{"type":"strong"}]},{"text":": ","type":"text"},{"text":"after_text","type":"text","marks":[{"type":"code_inline"}]},{"text":" 仍保留用于人工核验","type":"text"}]}]}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"为什么用 Python 而非浏览器内 JavaScript？","type":"text"}]},{"type":"ordered_list","attrs":{"order":1,"listStyle":"number"},"content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"本地处理更可靠","type":"text","marks":[{"type":"strong"}]},{"text":": Python 直接操作系统剪贴板，不受浏览器沙盒限制","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"图片压缩","type":"text","marks":[{"type":"strong"}]},{"text":": 上传前压缩图片 (--quality 85)，减少上传时间","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"代码复用","type":"text","marks":[{"type":"strong"}]},{"text":": 脚本固定不变，无需每次重新编写转换逻辑","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"调试方便","type":"text","marks":[{"type":"strong"}]},{"text":": 脚本可单独测试，问题易定位","type":"text"}]}]}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"等待策略","type":"text"}]},{"type":"paragraph","content":[{"text":"关键理解","type":"text","marks":[{"type":"strong"}]},{"text":": ","type":"text"},{"text":"browser_wait_for","type":"text","marks":[{"type":"code_inline"}]},{"text":" 的 ","type":"text"},{"text":"textGone","type":"text","marks":[{"type":"code_inline"}]},{"text":" 参数会在文字消失时","type":"text"},{"text":"立即返回","type":"text","marks":[{"type":"strong"}]},{"text":"，","type":"text"},{"text":"time","type":"text","marks":[{"type":"code_inline"}]},{"text":" 只是最大等待时间，不是固定等待时间。","type":"text"}]},{"type":"bullet_list","content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"❌ 保守等待: ","type":"text"},{"text":"time=5","type":"text","marks":[{"type":"code_inline"}]},{"text":" 或 ","type":"text"},{"text":"time=10","type":"text","marks":[{"type":"code_inline"}]},{"text":"，如果上传只需2秒，剩余时间全浪费","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"✅ 短间隔轮询: ","type":"text"},{"text":"time=2","type":"text","marks":[{"type":"code_inline"}]},{"text":"，条件满足立即返回，最多等2秒","type":"text"}]}]}]},{"type":"code_block","attrs":{"wrap":false,"language":""},"content":[{"text":"# 正确用法：短 time 值，条件满足立即返回\nbrowser_wait_for textGone=\"正在上传媒体\" time=2\n\n# 错误用法：固定长时间等待\nbrowser_wait_for time=5 # 无条件等待5秒，浪费时间","type":"text"}]},{"type":"paragraph","content":[{"text":"原则","type":"text","marks":[{"type":"strong"}]},{"text":": 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。","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"图片插入效率","type":"text"}]},{"type":"paragraph","content":[{"text":"每张图片的浏览器操作从5步减少到2步：","type":"text"}]},{"type":"bullet_list","content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"旧: 点击 → 添加媒体 → 媒体 → 添加照片 → file_upload","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"新: 点击段落 → Meta+v","type":"text"}]}]}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"封面图 vs 内容图","type":"text"}]},{"type":"bullet_list","content":[{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"封面图","type":"text","marks":[{"type":"strong"}]},{"text":": 使用 browser_file_upload（因为有专门的上传按钮）","type":"text"}]}]},{"type":"list_item","content":[{"type":"paragraph","content":[{"text":"内容图","type":"text","marks":[{"type":"strong"}]},{"text":": 使用 Python 剪贴板 + 粘贴（更高效）","type":"text"}]}]}]},{"type":"hr","attrs":{"markup":"---"}}]},"metadata":{"date":"2026-06-05","name":"x-article-publisher","author":"@skillopedia","source":{"stars":336,"repo_name":"marketplace","origin_url":"https://github.com/aiskillstore/marketplace/blob/HEAD/skills/wshuyi/x-article-publisher/SKILL.md","repo_owner":"aiskillstore","body_sha256":"3672b31bd3af92a07d181fcb7cbeb0fd1362410561cee49609edcae6a5e81207","cluster_key":"6b8c5dc03c0cd2cd3c632e98fa4701b4cb82dc44a11f419c1097880fe833ebcc","clean_bundle":{"format":"clean-skill-bundle-v1","source":"aiskillstore/marketplace/skills/wshuyi/x-article-publisher/SKILL.md","attachments":[{"id":"b68269a9-763b-594d-ad8e-c74b2c98989a","key":"uploads/10433ee7-ad12-4ae0-b34e-97553e46c6c8/b68269a9-763b-594d-ad8e-c74b2c98989a/attachment.json","path":"EVALUATION.json","size":12793,"sha256":"073a9351f4dff135334bd8ecfb652e838edbdb5b1bcdccc553181a0997fa6035","contentType":"application/json; charset=utf-8"},{"id":"6df7c9a0-b1c8-5db4-9cc8-794eee0972c4","key":"uploads/10433ee7-ad12-4ae0-b34e-97553e46c6c8/6df7c9a0-b1c8-5db4-9cc8-794eee0972c4/attachment.py","path":"scripts/copy_to_clipboard.py","size":9554,"sha256":"a9869731357753dac38f1f5ea44674b1cf6d108ff1447d1f33669ab604422ec2","contentType":"text/x-python; charset=utf-8"},{"id":"a720e034-20e7-5fbc-9a0a-1f8712add170","key":"uploads/10433ee7-ad12-4ae0-b34e-97553e46c6c8/a720e034-20e7-5fbc-9a0a-1f8712add170/attachment.py","path":"scripts/parse_markdown.py","size":10217,"sha256":"b2d3b9ad90406738d8e1dd29723c4572790936868f6b23d988f5063b826b8296","contentType":"text/x-python; charset=utf-8"},{"id":"52495cb2-ec57-563c-8904-47144cbce8da","key":"uploads/10433ee7-ad12-4ae0-b34e-97553e46c6c8/52495cb2-ec57-563c-8904-47144cbce8da/attachment.json","path":"skill-report.json","size":8437,"sha256":"41eb6f9b6ab09685c1bda7804a0c83a711b52f7aa4060e8dafd0a6073ed8e903","contentType":"application/json; charset=utf-8"}],"bundle_sha256":"f5c4632d7ea2cb2d92db8747b223cd1a4bc70f9f57d87910276b6b91f816fcad","attachment_count":4,"text_attachments":4,"attachment_storage":"skillopedia-attachments-v1","binary_attachments":0,"excluded_attachments":[]},"cluster_size":1,"skill_md_path":"skills/wshuyi/x-article-publisher/SKILL.md","import_metadata":{"date":"2026-06-05","author":"@skillopedia","version":"v1","category":"media-content","category_label":"Media"},"exact_dupes_collapsed_into_this":0},"version":"v1","category":"media-content","import_tag":"clean-skills-v1","description":"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."}},"renderedAt":1782988305490}

X Article Publisher Publish Markdown content to X (Twitter) Articles editor, preserving formatting with rich text conversion. Prerequisites - Playwright MCP for browser automation - User logged into X with Premium Plus subscription - Python 3.9+ with dependencies: - macOS: - Windows: Scripts Located in : parse markdown.py Parse Markdown and extract structured data: Returns JSON with: title, cover image, content images (with block index for positioning), html, total blocks copy to clipboard.py Copy image or HTML to system clipboard: Workflow Strategy: "先文后图" (Text First, Images Later) For arti…