ClawHub

Recover deleted YouTube videos

v1.0.0

Searches multiple online archives to find and recover deleted YouTube videos, metadata, and comments using a video ID.

⭐ 3· 706·0 current·0 all-time
by@upintheairsheep

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for upintheairsheep/youtube-video-finder.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Recover deleted YouTube videos" (upintheairsheep/youtube-video-finder) from ClawHub.
Skill page: https://clawhub.ai/upintheairsheep/youtube-video-finder
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Canonical install target

openclaw skills install upintheairsheep/youtube-video-finder

ClawHub CLI

Package manager switcher

npx clawhub@latest install youtube-video-finder
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (recover deleted YouTube videos) match the SKILL.md: it documents an HTTP GET against a single archive API that returns verdict, links, and metadata. There are no unrelated credentials, binaries, or install steps requested.
ℹ
Instruction Scope
The runtime instructions are narrowly scoped: extract an 11-character video ID, call the provided API, and format the results. However, the skill instructs the agent to send user-provided video IDs to the external host (findyoutubevideo.thetechrobo.ca). This is expected for the stated purpose but is a potential privacy/leakage vector — the SKILL.md does not require or validate user consent, and the optional includeRaw/stream parameters can increase data exposure.
✓
Install Mechanism
No install spec or code files are present (instruction-only). Nothing is written to disk and no third-party packages are pulled in, which minimizes install-time risk.
✓
Credentials
The skill requires no environment variables, credentials, or config paths. That is proportionate for a simple API-wrapper skill.
✓
Persistence & Privilege
The skill is not always-enabled and does not request persistent system privileges. It does allow normal autonomous invocation (platform default), which is not unusual for skills of this type.
Assessment
This skill appears coherent and minimal, but it calls an unknown third-party API (findyoutubevideo.thetechrobo.ca). Before installing or using it, consider: (1) Privacy: every video ID you query is sent to that external service — don't query private/unlisted or sensitive content unless you trust the operator. (2) Verify the service: look for an owner, privacy policy, and uptime/history for the domain; the skill metadata lacks a homepage. (3) Limit optional flags: avoid includeRaw/stream unless you need debugging or large data, since they may return more data and/or stream results. (4) Test safely: try non-sensitive or public video IDs first to confirm behavior. If you need a stronger trust guarantee, prefer solutions that query known archive providers (Wayback/GhostArchive) directly or run local tooling you control.

Like a lobster shell, security has layers — review code before you run it.

latestvk9733j7jbch6vkt24d1tvnczxx81nbkv
706downloads
3stars
1versions
Updated 1mo ago
v1.0.0
MIT-0
@upintheairsheep
latest
Download

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.

Comments

Loading comments...