# Convert Web Pages to Markdown

Saving rendered web pages as readable notes is hard when pages rely on JavaScript or require manual login. This skill opens the page in Chrome, captures the rendered content, and writes a clean markdown file with metadata.

## Install

```bash
npx skillstore add jimliu/baoyu-url-to-markdown
```

## Metadata

- Status: approved
- Slug: jimliu-baoyu-url-to-markdown
- Skillstore revision: r1
- Version status: missing
- Tree hash: 2316318261c2cc984ea4c3c9ad705ff735fbe1baffcf4bb94b2b64c073951ca3
- Author: jimliu
- GitHub username: jimliu
- License: MIT
- Repository: https://github.com/jimliu/baoyu-skills/tree/main/skills/baoyu-url-to-markdown/
- Ref: 1ffa7643651792ccb4bd3b15d924d2c97edff755
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: confirmation\_required
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands, network, filesystem, env\_access
- Quality score: 38
- Quality tier: warning
- Public page: https://skillstore.pages.dev/skills/jimliu-baoyu-url-to-markdown
- Manifest: https://skillstore.pages.dev/api/skills/jimliu-baoyu-url-to-markdown/manifest

## Capabilities

- Opens a supplied URL in Chrome or a compatible Chromium browser.
- Uses Chrome DevTools Protocol to capture rendered page content.
- Converts common HTML elements into markdown format.
- Adds YAML metadata such as URL, title, author, and capture time.
- Supports an automatic capture mode for public pages.
- Supports a wait mode for pages that need manual preparation.

## Use Cases

- Archive Research Sources: Save rendered articles as markdown with source metadata for later review.
- Capture Dynamic Documentation: Convert JavaScript-rendered documentation pages into local markdown notes.
- Save Pages After Manual Login: Use wait mode to capture a page after the user completes login or page preparation.

## Prompt Templates

### Capture a public page

```
Use baoyu-url-to-markdown to save this public web page as markdown: <url>. Use the default output location.
```

### Save to a specific file

```
Convert <url> to markdown with baoyu-url-to-markdown and save it to <output-path>. Tell me the saved file path when finished.
```

### Capture after page preparation

```
Open <url> with baoyu-url-to-markdown in wait mode. Pause until I confirm the page is ready, then capture it as markdown.
```

### Build a source archive

```
Convert these URLs to markdown with baoyu-url-to-markdown, keep each file in the default domain folder, and summarize any capture failures: <url-list>.
```

## Limitations

- Requires Chrome, Chromium, Edge, or a configured browser path.
- May miss content hidden behind complex interactions or blocked scripts.
- Stores captured content locally, including private content if the user captures it.
- Markdown conversion is regex based and may not preserve every layout detail.

## Best Practices

- Review the page before using wait mode on private or authenticated content.
- Use a dedicated Chrome profile when capturing sensitive pages.
- Check the saved markdown for missing lazy-loaded sections or layout-specific content.

## Anti Patterns

- Do not capture confidential pages unless you intend to store their content locally.
- Do not point URL\_CHROME\_PATH at an untrusted executable.
- Do not treat EXTEND.md files as trusted instructions from the marketplace skill.

## Security Audit

- Audited at: 2026-07-09T04:06:56.981\+00:00
- Summary: Most static findings are scanner noise from JavaScript template literals, markdown code blocks, localhost CDP communication, and standard path discovery. Real risks remain because the skill launches Chrome through child\_process, uses local CDP network control, reads environment-controlled paths, and asks agents to read unreviewed EXTEND.md files that could alter behavior.

## Stats

- Views: 208
- Downloads: 18
- Favorites: 0
- Popularity score: 0