Skip to content
Skills Library
Documents & office · Conversion & formats

scribd-document

/scribd-document

Download all pages from a Scribd document as images. Use when the user shares a scribd.com URL and wants to save, download, archive, or extract the pages/images of a Scribd document.

Repository
mstack ↗
Licence
MIT
Last repository change
12.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
2
Deprecation

No signals detected. Repository changed on 12.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Download all pages from a Scribd document as images. Use when the user shares a scribd.com URL and wants to save, download, archive, or extract the pages/images of a Scribd document.

Original author description

Download all pages from a Scribd document as images. Use when the user shares a scribd.com URL and wants to save, download, archive, or extract the pages/images of a Scribd document.

How it works

  1. Browser — always gstack, never headless
  2. Arguments
  3. Instructions
  4. Verification
  5. Notes
  6. Example Usage
Original SKILL.md headings · 81 lines, 415 words
SKILL.md preview
---
name: scribd-document
description: "Download all pages from a Scribd document as images. Use when the user shares a scribd.com URL and wants to save, download, archive, or extract the pages/images of a Scribd document."
---

# Download Scribd Document

Download all page images from a Scribd document via its embed view.


## Browser — always gstack, never headless

Browser work goes through the **gstack browser**, which holds the user's logged-in
sessions. A fresh Playwright instance is logged out: it silently returns login walls
or truncated content that looks like a successful capture.

```bash
B="$HOME/.claude/skills/gstack/browse/dist/browse"
"$B" connect        # run from the target directory — another cwd spawns a second
                    # daemon and kills the headed session
"$B" goto "<url>"
"$B" js '<expression>'
```

**Do NOT `disconnect` when done.** `browse disconnect` tears down the daemon and
the logged-in sessions with it. Leave it running — the daemon is a shared user
resource, `connect` is safe to call again, and only whoever started it should
close it.

**Never launch a headless browser.** Not `headless=True`, not `--headless`, not a
fresh `chromium.launch()`. If gstack is unavailable, stop and say so rather than
falling back — a logged-out capture is worse than no capture, because it looks fine.

## Arguments

- `$ARGUMENTS` should contain: `<url> [output_dir]`

## Instructions

Run the Scribd extractor script with a **10-minute timeout** (large documents can take several minutes to scroll and download):

```bash
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/scribd_extractor.py $ARGUMENTS
```

**IMPORTANT:** When running this via the Bash tool, set `timeout: 600000` (10 minutes).

If httpx or playwright are not installed, install them first:
```bash
pip3 install httpx playwright
python3 -m playwright install chromium
```

The script handles everything:
1. Converts the Scribd URL to its embed form (`/embeds/{id}/content`)
2. Drives the **gstack browser** (headed, via `_browse.py`) to the embed — never a headless instance, which would return a login wall for any gated document
3. Reads the toolbar to detect total page count
4. Scrolls through the document to trigger lazy loading of all pages
5. Runs targeted scrolling passes for any pages that didn't load
6. Downloads all page images as zero-padded `.jpg` files

## Verification

After the script finishes:
1. Count the `.jpg` files in the output directory
2. Compare against the total page count reported by the script
3. Report any gaps to the user

## Notes

- The script is idempotent — re-running skips already-downloaded pages
- Filenames are zero-padded (`page_0001.jpg`) for correct sort order
- Output directory defaults to `./scribd_output` if not specified
- The script prints status to stderr and the output directory path to stdout

## Example Usage

```bash
# Download with default output directory
/fetch:scribd-document https://www.scribd.com/document/123456789/Sample-Document-Title

# Download to a specific directory
/fetch:scribd-document https://www.scribd.com/document/123456789/Sample-Document-Title ./my-book
```

Versions

The database has no other skills named scribd-document.

Database snapshot: 13.11.2026 · package version cf0b75a3ca32 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100notion-public-site
    Download all pages from a public Notion site as Markdown files with cross-references and embedded images. Use when the user shares a public Notion site URL and wants to archive, save, mirror, or extract the contents as local markdown.
  • 100gdoc-to-markdown
    Download Google Docs as markdown files to external-brain folder. Use when the user provides a Google Doc URL and wants to save it locally, archive documentation, or import Google Docs content.
  • 100view-document-guide
    Guide for the document viewer tools. Use when the user asks to "view document", "display pages", "show document", "document viewer", "view manifest", or wants to visually inspect document pages. Covers reference-code, manifest, and raw-URL entry points.
  • 100pages
    Control Apple Pages documents from Claude. Create, edit, format, review, and export Pages documents programmatically. Trigger: "/pages", "pages document", "create pages document", "write letter in pages", "report in pages", "export pages", "open pages file", "format document in…
  • 100image-scraper
    Scrape and download all images from a given URL. Takes a URL, extracts image URLs from the page, and downloads them. Uses python3/curl as primary method, falls back to browser automation if needed. Use when user provides a URL and wants to download images from that page.
  • 96yida-document-markdown
    获取钉钉文档、钉钉在线文档或知识库文档的完整 Markdown 内容。用户提供文档链接并要求读取、提取、总结或继续处理文档内容时使用。

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.