Individual skill
web-to-markdown
Read web pages as clean, LLM-ready Markdown, one URL, up to 20 URLs in one call, or a whole site section, plus real-browser screenshots. Use when the user wants you to read, summarize, compare or extract from web pages and your own fetch fails, returns raw HTML, is blocked, or the page needs JavaScript. agentsvc.io, from $0.0025 per page, no account, failed pages are not charged.
skills/web-to-markdown/SKILL.md
Source commit 4ee85135d1e1a07005ff3cf386f5e91b56e7691f
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 5, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 0
- Repository last updated
- Nov 6, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- ai-agents Repository topic
- claude-code Repository topic
- claude-code-plugin Repository topic
- mcp Repository topic
- speech-to-text Repository topic
- web-scraping Repository topic
- x402 Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Read excerpt
# Web pages to Markdown
agentsvc.io fetches a page, drops menus, ads and footers and returns the main content as Markdown with title and meta description. Pick by what you have:
| You have | Service | Price |
|---|---|---|
| one URL | `web-scrape` | $0.0025 |
| a list of up to 20 URLs | `web-scrape-batch` (one payment, fetched in parallel) | $0.05 |
| a site or a section like /docs | `site-crawl` (follows links, up to 20 pages) | $0.005 |
| a page you need to see | `screenshot` (PNG from a real browser) | $0.009 |
## Input
- `web-scrape`: `url`, optional `max_chars` (default 8000, up to 60000), `include_links`, and `render: true` for JavaScript apps that come back empty (real browser, plain text).