Captions

Pulls timestamped captions from any YouTube video through TranscriptAPI. You'd reach for this when someone pastes a video link and you need to quote it, translate it, or just read what was said without watching. Works for accessibility cases, language learning, or quickly scanning long videos. The JSON format gives you exact timestamps for each line, which is handy for syncing or analysis. Text format is cleaner for straightforward reading. Free tier gives you 100 credits to start. One honest limitation: if the video doesn't have captions enabled at all, you're out of luck, but most videos have at least auto-generated ones these days.

skills.sh installs: 767
GitHub stars: 1.2K
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Captions

Extract closed captions from YouTube videos via TranscriptAPI.com.

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.

GET /api/v2/youtube/transcript

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"

SKILL.md on GitHub