Youtube Data

Pulls YouTube transcripts, metadata, channel uploads, search results, and playlist contents through TranscriptAPI instead of wrangling Google's quota-limited Data API. You get 100 free credits (each transcript or search costs 1 credit), no OAuth dance, and some genuinely useful freebies like resolving handles to channel IDs and grabbing the latest 15 videos with exact view counts at zero cost. The main gotcha is remembering to set a proper User-Agent header or Cloudflare will 403 you. Good fit if you're building content analysis tools, research workflows, or anything that needs structured YouTube data without the ceremony of official API access.

skills.sh installs: 759
GitHub stars: 1.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add zeropointrepo/youtube-skills --skill youtube-data --agent claude-code

Installs into .claude/skills of the current project.

Files

YouTube Data

YouTube data access via TranscriptAPI.com — lightweight alternative to Google's YouTube Data API.

Setup

If $TRANSCRIPT_API_KEY is not set, read references/auth-setup.md and follow the instructions there to get and store the key.

Required Headers

Every request needs two headers:

Authorization: Bearer $TRANSCRIPT_API_KEY
User-Agent: your agent's name and version if known (e.g. HermesAgent/0.11.0, ClaudeCode/1.0). Version is optional — agent name alone is fine. Do not omit this header or send a bare default — Cloudflare will return a 403 (error code 1010) and block the request.

API Reference

Full OpenAPI spec: transcriptapi.com/openapi.json — consult this for the latest parameters and schemas.

Video Data (transcript + metadata) — 1 credit

curl -s "https://transcriptapi.com/api/v2/youtube/transcript\
?video_url=VIDEO_URL&format=json&include_timestamp=true&send_metadata=true" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
  -H "User-Agent: YourAgent/1.0"

Response:

SKILL.md on GitHub