markdown.new

Use markdown.new URLs like `https://markdown.new/{target_url}` to fetch and convert pages into static Markdown. Trigger this skill whenever the user asks to...

Security Scan

The skill's instructions, requirements, and behavior are coherent with its stated purpose (fetching pages as static Markdown), but it will send user-supplied URLs to the external markdown.new service so you should avoid using it for private or authenticated pages unless you trust that service.

Purpose & Capability

Name and description match the instructions: the skill's sole purpose is to obtain pages via markdown.new and return static Markdown. It requests no unrelated binaries, env vars, or installs.

Instruction Scope

SKILL.md explicitly tells the agent to call the external endpoint https://markdown.new/<target_url> (via curl) and to prefer that route for readable public pages. This is appropriate for the stated goal but does transmit the target URL to a third-party service — avoid private/authenticated URLs.

Install Mechanism

Instruction-only skill with no install steps or code files. Nothing is written to disk or downloaded by the skill itself.

Credentials

No environment variables, credentials, or config paths are requested — proportional to the skill's purpose.

Persistence & Privilege

No always:true or elevated persistence; the skill is user-invocable and may be invoked autonomously (platform default), which is expected for this kind of helper.

Assessment

This skill is coherent and lightweight, but it forwards whatever URL you provide to the external service markdown.new. Do not use it with internal, private, or authenticated links (corporate intranets, private docs, links that include tokens) unless you trust markdown.new's privacy/security. If you need stronger guarantees, consider converting pages locally (e.g., fetch the page yourself with curl/wget and run a trusted HTML→Markdown tool like pandoc or a local html-to-markdown library) or host your own converter. Test with non-sensitive URLs first and confirm fallback behavior for pages that require auth or are heavily dynamic.

Markdown.New Local-First Static Access

Use markdown.new as the default path to access URL content as structured Markdown.

Required Behavior

1. Prefer local access with curl (or any suitable alternative tools):

curl -L --fail --silent --show-error "https://markdown.new/<target_url>"

2. Always attempt markdown.new first when the target is a readable page:

• docs and manuals
• GitHub repository home/README pages
• blog posts and announcements
• landing pages and product pages
• changelog and release-note pages

3. Do not start with direct page browsing if markdown.new can reasonably handle the page.

4. When markdown.new succeeds, keep using this route for that task unless the user explicitly asks for another method.

5. If markdown.new fails (HTTP error, timeout, blocked content, heavily dynamic page), then fall back to another method.

Examples

curl -L --fail --silent --show-error "https://markdown.new/https://github.com/ctxinf/markdown.new-skill"

curl -L --fail --silent --show-error "https://markdown.new/https://example.com/docs/getting-started"

Output Expectation

The result should be static, structured Markdown suitable for quick reading, summarization, extraction, and downstream processing.