OpenParable
Skip to content
← Back to skills

Convert To Markdown

Documents
convert-to-markdown

Convert To Markdown is an Agent Skill for documents published in the gupsammy/Claudest repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

This skill should be used when the user asks to "convert this page to markdown", "extract this webpage", "save this article", "grab content from URL", "get markdown from this link", "scrape this page", provides a URL to extract, or wants clean web content without ads and clutter.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/gupsammy/Claudest/blob/HEAD/plugins/claude-utilities/skills/convert-to-markdown/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/convert-to-markdown, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Web-to-Markdown via EzyCopy

Extract clean markdown from any URL using the ezycopy CLI.

Phase 1: Determine Extraction Mode

Default mode uses fast HTTP fetch. Add --browser when the page relies on client-side JavaScript to render its content or when authentication cookies are required — the default fetcher only sees the raw HTML response, not the JS-rendered DOM.

Common --browser cases: Twitter/X, single-page applications, paywalled content.

Flags

  • -c — copy output to clipboard
  • -o <path> — save to file or directory
  • --browser — use headless Chrome for JS-rendered or authenticated pages
  • --no-images — strip image links
  • -t <duration> — timeout (default: 30s)

Phase 2: Execute

Run ezycopy <URL> [flags] with the chosen mode.

In --browser mode: run as a foreground process and do not redirect stderr with 2>&1. Chrome outputs diagnostic messages to stderr that should flow naturally rather than polluting stdout capture.

Phase 3: Handle Failure

If the output is empty or suspiciously short and --browser was not used, retry with --browser — the site likely requires JS rendering.

If ezycopy is not found, ask the user before installing:

curl -sSL https://raw.githubusercontent.com/gupsammy/EzyCopy/main/install.sh | sh

Phase 4: Deliver

Present the extracted markdown to the user. If the user requested a file save, use -o. If they requested clipboard, use -c. When no explicit destination was given, display the content directly.