Scavio Youtube

Search YouTube and retrieve video metadata. Use for finding videos, checking view counts, channel info, or AI training suitability.

Security Scan

The skill's requests and instructions match its stated purpose (searching YouTube and returning metadata via the Scavio API) and require only a single API key; nothing in the SKILL.md asks for unrelated credentials or system access.

Purpose & Capability

Name/description (YouTube search and metadata) align with the declared requirement (SCAVIO_API_KEY) and the documented endpoints at https://api.scavio.dev. The requested credential is the expected one for a third‑party API wrapper.

Instruction Scope

SKILL.md instructs only how to call Scavio endpoints, handle responses, and install an optional LangChain helper. It does not direct the agent to read unrelated files, environment variables, or local system state.

Install Mechanism

This is an instruction-only skill with no install spec or code files. It merely suggests a pip package (scavio-langchain) as an optional integration — no arbitrary downloads or extract/execute steps are present in the manifest.

Credentials

Only a single env var (SCAVIO_API_KEY) is required and is declared as the primary credential. That is proportionate for a cloud API client; no unrelated secrets are requested.

Persistence & Privilege

The skill is not always-enabled and does not request system-wide changes or higher privileges. Autonomous invocation is allowed (platform default) but not combined with other concerning capabilities.

Assessment

This skill appears coherent: it simply forwards queries to Scavio's YouTube API and needs your SCAVIO_API_KEY. Before installing, confirm you trust scavio.dev and the API key provider (check their privacy/terms and quota limits). Be aware that any queries and returned metadata will be sent to/received from api.scavio.dev, so avoid sending sensitive local data in search requests. If you plan to pip install scavio-langchain, remember that Python packages run code on install/runtime — review that package on PyPI/github if you need extra assurance. Finally, protect your SCAVIO_API_KEY the same way you would any API key (do not paste it into public places).

YouTube Search and Metadata via Scavio

Search YouTube and retrieve video metadata. All endpoints return structured JSON.

When to trigger

Use this skill when the user asks to:

• Find YouTube videos on a topic
• Check view counts, upload date, or video metadata
• Verify if a video is suitable for AI training or has captions available

Setup

Get a free API key at https://scavio.dev (1,000 free credits/month, no card required):

export SCAVIO_API_KEY=sk_live_your_key

Workflow

1. Finding a video: call /search with the topic. Use sort_by: view_count for the most-watched result.
2. Checking metadata: call /metadata for view counts, likes, tags, or channel info.
3. Trainability: call /trainability to check license and caption availability before ingesting.

Endpoints

Endpoint	Description
POST https://api.scavio.dev/api/v1/youtube/search	Search YouTube videos
POST https://api.scavio.dev/api/v1/youtube/metadata	Get structured video metadata
POST https://api.scavio.dev/api/v1/youtube/trainability	Check AI training suitability

Authorization: Bearer $SCAVIO_API_KEY

Search Parameters

Parameter	Type	Default	Description
search	string	required	Search query — note: this field is search, not query
upload_date	string	--	last_hour, today, this_week, this_month, this_year
type	string	--	video, channel, or playlist
duration	string	--	short (< 4 min), medium (4-20 min), long (> 20 min)
sort_by	string	relevance	relevance, date, view_count, rating
subtitles	boolean	false	Videos with captions only
creative_commons	boolean	false	Creative Commons videos only

Examples

import os, requests

BASE = "https://api.scavio.dev"
HEADERS = {"Authorization": f"Bearer {os.environ['SCAVIO_API_KEY']}"}

# Search — use "search" field, not "query"
results = requests.post(f"{BASE}/api/v1/youtube/search", headers=HEADERS,
    json={"search": "langchain tutorial", "type": "video", "sort_by": "view_count"}).json()

video_id = results["data"][0]["videoId"]

# Metadata
metadata = requests.post(f"{BASE}/api/v1/youtube/metadata", headers=HEADERS,
    json={"video_id": video_id}).json()

Search Response

{
  "data": [
    {
      "videoId": "sVcwVQRHIc8",
      "title": "Learn RAG From Scratch - Python AI Tutorial",
      "channel": "freeCodeCamp.org",
      "publishedAt": "2024-04-17",
      "duration": "2:33:11",
      "viewCount": 1258310,
      "thumbnail": "https://i.ytimg.com/vi/sVcwVQRHIc8/hq720.jpg"
    }
  ],
  "credits_used": 1
}

Metadata response: title, view_count, like_count, comment_count, categories, tags, channel_id, upload_date, thumbnails.

Trainability response: has_transcript, transcript_languages, license, is_trainable.

Guardrails

• The search parameter is search, not query — this is different from other Scavio endpoints.
• Never fabricate video IDs, view counts, or metadata.

Failure handling

• If search returns no results, suggest different keywords or relaxing filters.
• If SCAVIO_API_KEY is not set, prompt the user to export it before continuing.

LangChain

pip install scavio-langchain

from scavio_langchain import ScavioSearchTool
tool = ScavioSearchTool(engine="youtube")