{"skill":{"slug":"cf-markdown-agents","displayName":"cf markdown agents","summary":"Fetch web content using Cloudflare's Markdown for Agents protocol. Automatically converts HTML to Markdown with 80% token reduction. Use when fetching web pa...","description":"---\nname: cf-markdown-agents\ndescription: Fetch web content using Cloudflare's Markdown for Agents protocol. Automatically converts HTML to Markdown with 80% token reduction. Use when fetching web pages for AI processing, web scraping, content extraction, or when the user mentions \"Markdown for Agents\", \"cf-markdown\", or needs structured web content in Markdown format.\n---\n\n# Cloudflare Markdown for Agents\n\nThis skill enables fetching web content using Cloudflare's Markdown for Agents protocol, which automatically converts HTML pages to clean, structured Markdown format.\n\n## What is Markdown for Agents?\n\nCloudflare's Markdown for Agents is a content negotiation feature that:\n- Automatically converts HTML to Markdown at the edge\n- Reduces token usage by ~80% compared to raw HTML\n- Returns clean, structured content perfect for AI processing\n- Adds `x-markdown-tokens` header showing estimated token count\n- Includes `Content-Signal` headers for AI usage permissions\n\n## Usage\n\n### Basic Fetch\n\nUse the provided script to fetch any URL with Markdown for Agents support:\n\n```bash\nscripts/fetch-markdown.sh <URL>\n```\n\nExample:\n```bash\nscripts/fetch-markdown.sh \"https://developers.cloudflare.com/agents/\"\n```\n\n### In Code\n\nTypeScript/JavaScript example:\n```typescript\nconst response = await fetch(\"https://example.com/page\", {\n  headers: {\n    Accept: \"text/markdown, text/html\",\n  },\n});\n\nconst tokenCount = response.headers.get(\"x-markdown-tokens\");\nconst markdown = await response.text();\n```\n\ncURL example:\n```bash\ncurl https://example.com/page -H \"Accept: text/markdown\"\n```\n\n## Response Headers\n\n- `content-type: text/markdown; charset=utf-8` - Content is Markdown\n- `x-markdown-tokens: <number>` - Estimated token count\n- `content-signal: ai-train=yes, search=yes, ai-input=yes` - Usage permissions\n\n## Supported Sites\n\nAny site using Cloudflare with Markdown for Agents enabled:\n- Cloudflare Developer Documentation (developers.cloudflare.com)\n- Cloudflare Blog (blog.cloudflare.com)\n- Any site with the feature enabled in Cloudflare dashboard\n\n## Benefits\n\n| Aspect | HTML | Markdown |\n|--------|------|----------|\n| Tokens | 16,180 | 3,150 |\n| Reduction | - | ~80% |\n| Structure | Complex | Clean |\n| AI Parsing | Hard | Easy |\n\n## References\n\n- Full protocol details: [references/protocol.md](references/protocol.md)\n- API examples: [references/examples.md](references/examples.md)\n","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":513,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1773399700335,"updatedAt":1778491880948},"latestVersion":{"version":"1.0.0","createdAt":1773399700335,"changelog":"Initial release of cf-markdown-agents.\n\n- Enables fetching web content using Cloudflare's Markdown for Agents protocol.\n- Automatically converts HTML pages to clean, structured Markdown format with ~80% token reduction.\n- Provides examples for usage with shell scripts, TypeScript/JavaScript, and cURL.\n- Describes response headers including token count and AI usage permissions.\n- Lists supported sites and summarizes key benefits for AI processing.","license":"MIT-0"},"metadata":null,"owner":{"handle":"xinian5216","userId":"s17f28d5hcake33q7ye0wmw34h885q0v","displayName":"xinian5216","image":"https://avatars.githubusercontent.com/u/59920440?v=4"},"moderation":null}