# Anycrawl Youtube Video Extractor

> Extract public YouTube watch-page data from a single URL through the AnyCrawl Scrape API. Use when a user provides a YouTube watch link and wants as much structured data as possible from that one video, including normalized JSON plus the raw AnyCrawl markdown, HTML, links, transcript-bearing content, and screenshot artifacts.

- **Type:** Skill
- **Install:** `agentstack add skill-citedy-skills-anycrawl-youtube-video-extractor`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [citedy](https://agentstack.voostack.com/s/citedy)
- **Installs:** 0
- **Category:** [Web & Browser](https://agentstack.voostack.com/c/web-and-browser)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [citedy](https://github.com/citedy)
- **Source:** https://github.com/citedy/skills/tree/main/skills/anycrawl-youtube-video-extractor

## Install

```sh
agentstack add skill-citedy-skills-anycrawl-youtube-video-extractor
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# AnyCrawl YouTube Video Extractor

Use this skill when the user gives a public YouTube watch URL and wants deep video metadata through AnyCrawl.

## Workflow

1. Accept a single public YouTube watch URL.
2. Validate that it is one of the supported shapes:
   - `https://www.youtube.com/watch?v=VIDEO_ID`
   - `https://youtu.be/VIDEO_ID`
3. Run the bundled extractor:

```bash
node .claude/skills/anycrawl-youtube-video-extractor/scripts/run.js ""
```

4. Read the JSON file path printed by the script.
5. Summarize the important fields for the user:
   - title
   - channel metadata
   - publish and upload dates
   - duration
   - views and likes
   - description
   - transcript availability
   - endscreen recommendations
   - age restriction flag
   - screenshot URL

## Output Handling

The script writes a full JSON artifact to `/tmp` by default and prints a compact summary to stdout.

The artifact includes:

- `normalized`: structured YouTube-focused extraction
- `anycrawl`: raw AnyCrawl response, including `markdown`, `html`, `links`, and `screenshot@fullPage` when available
- `request`: the exact payload used for the successful attempt

If you need the official template notes, read [references/template-notes.md](.claude/skills/anycrawl-youtube-video-extractor/references/template-notes.md).

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [citedy](https://github.com/citedy)
- **Source:** [citedy/skills](https://github.com/citedy/skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-citedy-skills-anycrawl-youtube-video-extractor
- Seller: https://agentstack.voostack.com/s/citedy
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.