Capture URL content into structured markdown snapshot files.
npx skills add https://github.com/zby/llm-do --skill snapshot-web
Please help me install this Agent Skill. Skill: snapshot-web Source: https://github.com/zby/llm-do/tree/main/project_claw/skills/snapshot-web Command: npx skills add https://github.com/zby/llm-do --skill snapshot-web
This Skill automates the process of capturing content from various online sources (web pages, PDFs, GitHub, X/Twitter) and saving it as structured markdown files, eliminating manual copy-pasting and formatting.
Use the snapshot-web skill to capture the content from the URL https://example.com/article.
High-intent search queries and answers about installing and using this skill.
To capture web content into markdown, you can use a snapshot tool that fetches any URL and saves the extracted text and structure as a markdown file. This eliminates manual copy-pasting and preserves key formatting.
Yes, you can extract content from a PDF URL and save it as markdown. The tool routes the PDF URL to specific scripts that extract the main content and store it locally as a structured markdown file.
The best way to save a GitHub issue or PR is to use a URL snapshot tool that supports GitHub routing. It automatically captures the issue content and saves it as an organized markdown file in your local sources directory.
Yes, web capture works with X/Twitter posts. The tool includes specific routing for X/Twitter URLs to extract the post content and metadata, saving it consistently as a markdown snapshot alongside other captured sources.
To prevent duplicate snapshots, the capture tool checks existing files in the sources directory before fetching. If the URL content has already been saved as markdown, it skips the redundant snapshot process.
When you snapshot a URL, the tool determines and saves metadata like the content title, author, and type within the markdown file. This ensures your captured sources remain structured and easy to reference later.
u9401066Extract text, figures, and citations from PDFs into Markdown.
JoranHonigBuilds a deterministic semantic vector index for registered library files using FastEmbed and Qdrant.
zbyCapture URLs into markdown-formatted snapshots with metadata.
eddmannRender dynamic web pages with Playwright to capture HTML, text, and screenshots.
