home / skills / openclaw / skills / youtube-video-finder

youtube-video-finder skill

/skills/upintheairsheep/youtube-video-finder

This skill helps you locate and recover deleted YouTube videos by querying archives and returning available links and metadata for a given video ID.

npx playbooks add skill openclaw/skills --skill youtube-video-finder

Review the files below or copy the command above to add this skill to your agents.

Files (2)
SKILL.md
2.4 KB
---
name: Recover deleted YouTube videos
description: Searches multiple online archives to find and recover deleted YouTube videos, metadata, and comments using a video ID.
author: upintheairsheep
version: 1.0.0
url: https://findyoutubevideo.thetechrobo.ca/api/v5/{videoid}
method: GET
params:
  - name: videoid
    type: string
    description: The exact 11-character YouTube video ID to search for. DO NOT pass a full URL.
    required: true
  - name: includeRaw
    type: boolean
    description: Set to true to include the rawraw field for advanced debugging. Otherwise, omit or set to false to improve speed.
    required: false
  - name: stream
    type: boolean
    description: Set to true to stream JSONL. Keep false for standard agent data parsing.
    required: false
---

# YouTube Video Finder Instructions

Use this skill whenever a user asks to find, recover, or check the archive status of a deleted, missing, or private YouTube video. 

## Execution Steps:
1. **Extract the Video ID:** Isolate the 11-character ID from the URL or text provided by the user (e.g., for `youtube.com/watch?v=dQw4w9WgXcQ`, the ID is `dQw4w9WgXcQ`). Pass *only* this ID into the `videoid` parameter.
2. **Parameters:** Omit the `includeRaw` and `stream` parameters unless the user specifically asks for raw metadata or debugging data. 

## Interpreting the Response:
* **Initial Check:** Look at the `status` field. If it returns `bad.id`, stop and inform the user that the 11-character ID is invalid.
* **The Verdict:** Check the `verdict` object. Read the `human_friendly` string to immediately understand the overall result. Pay attention to the boolean flags `video`, `metaonly`, and `comments` to know exactly what was recovered.
* **Finding the Links:** Iterate through the `keys` array (which contains service objects like GhostArchive or Wayback Machine). 
    * If a service object has `archived: true`, look inside its `available` list.
    * Extract the `url` from the Link Objects to give to the user.
    * Take note of `maybe_paywalled` (boolean) or `note` (string) for context on how to access the link.

## Output Formatting:
Present your findings in a clear, friendly, and structured manner. 
* If the video is fully found, provide the direct links immediately. 
* If only metadata or comments were archived, clarify that the actual video file could not be recovered. 
* Mention which service(s) successfully held the archive.

Overview

This skill locates and recovers deleted, private, or missing YouTube videos by searching multiple online archives using a single video ID. It returns recovered video files when available, plus archived metadata and comments, and identifies which archival services hold each item. The skill is focused on actionable recovery: direct links, access notes, and clear verdicts about what was found.

How this skill works

Provide only the 11-character YouTube video ID and the skill queries various archives (e.g., Wayback, GhostArchive, and other snapshot services). The response includes a status check, a human-friendly verdict, boolean flags for video/meta/comments, and a list of services with available archived links and access notes. If the ID is invalid the skill reports that immediately; otherwise it extracts and returns URLs and context for each archived item found.

When to use it

  • You want to find a deleted or private YouTube video using its ID.
  • You need archived metadata or comment history for a removed video.
  • You want direct archive links from multiple services to preserve content.
  • You are preparing evidence or backups and need provenance from archives.

Best practices

  • Always pass only the 11-character video ID, not the full URL or extra text.
  • Do not request raw or streaming debug data unless you need low-level metadata (omit includeRaw and stream by default).
  • Check the verdict human_friendly string and boolean flags (video, metaonly, comments) first for a quick summary.
  • When links are returned, note maybe_paywalled or note fields for access restrictions or paywall info.
  • Cross-check multiple archived links to confirm file integrity before relying on a single source.

Example use cases

  • Recovering a previously uploaded video removed by the uploader or platform moderation.
  • Retrieving comment threads and timestamps for research or moderation appeals.
  • Gathering archived metadata (title, description, upload date) for citation or legal records.
  • Checking whether a suspicious or potentially infringing video still exists in public archives.
  • Creating a local backup of content that has been taken down from YouTube.

FAQ

What do I provide to start a search?

Provide only the 11-character YouTube video ID (for example, dQw4w9WgXcQ).

What if the response says bad.id?

That means the ID is invalid. Re-check the 11-character string and try again.

Can this skill recover every deleted video?

No. Recovery depends on whether an archive service captured the video file. If only metadata or comments were archived, the actual video file may be unavailable.