
Youtube Summary
- 1 installs
- 1 repo stars
- Updated July 29, 2026
- starchild-ai-agent/community-skills
Fetch a YouTube video's transcript via the Supadata API and generate a structured, sectioned summary in the user's language.
About
Fetches a YouTube video transcript through the Supadata API and produces a structured summary with themed sections. A developer or user invokes it after sharing a YouTube link to get key points and takeaways.
- Uses Supadata API (not yt-dlp) to avoid YouTube IP blocks
- Structured summary with core theme, key points, breakdown, and conclusions
Youtube Summary by the numbers
- 1 all-time installs (skills.sh)
- Ranked #1,983 of 2,715 Automation & Workflows skills by installs in the Skillselion catalog
- Data as of Jul 30, 2026 (Skillselion catalog sync)
npx skills add https://github.com/starchild-ai-agent/community-skills --skill youtube-summaryAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1 |
|---|---|
| repo stars | ★ 1 |
| Last updated | July 29, 2026 |
| Repository | starchild-ai-agent/community-skills ↗ |
What it does
Fetch a YouTube video's transcript via the Supadata API and generate a structured, sectioned summary in the user's language.
Files
YouTube Summary Skill
Summarize any YouTube video by fetching its transcript via Supadata API and generating a structured, readable summary.
Prerequisites
This skill requires a Supadata API key. The free tier is sufficient for personal use.
1. Sign up at supadata.ai 2. Get your API key from the dashboard 3. Set it as an environment variable:
SUPADATA_API_KEY=sd_your_key_hereOr provide it directly when prompted.
---
Workflow
Step 1: Get the YouTube URL
Accept any of these formats:
https://youtu.be/VIDEO_IDhttps://www.youtube.com/watch?v=VIDEO_ID
Step 2: Fetch transcript via Supadata API
curl -s "https://api.supadata.ai/v1/youtube/transcript?url=VIDEO_URL" \
-H "x-api-key: $SUPADATA_API_KEY"Response format:
{
"content": [
{"text": "...", "offset": 0, "duration": 5000, "lang": "en"},
...
],
"lang": "en",
"availableLangs": ["en"]
}Extract the text fields and concatenate to get the full transcript.
Step 3: Generate summary
Use the transcript text to produce a structured summary with these sections (adapt based on video content):
- 🎯 核心主题 — What is the video about?
- 📌 主要观点 — Key arguments or findings (3–7 bullet points)
- 📖 详细内容 — Expanded breakdown by section/topic
- 💡 结论 — Main takeaways or conclusions
Adjust language of summary to match the user's language preference.
---
Error Handling
| Error | Cause | Resolution |
|---|---|---|
401 Unauthorized | Invalid or missing API key | Ask user to check their Supadata API key |
404 Not Found | Video has no transcript / is private | Inform user the video has no available transcript |
429 Rate Limited | Too many requests | Wait and retry, or upgrade Supadata plan |
Empty content array | No captions available | Inform user and suggest they check if the video has captions |
---
Example Usage
User: "帮我总结一下这个视频 https://youtu.be/BU9sIfGVhIQ"
Agent workflow: 1. Call Supadata API with the URL 2. Parse and concatenate transcript text 3. Generate structured summary in Chinese (matching user language) 4. Present summary with emoji section headers
---
Notes
- Supadata free tier has a monthly quota — sufficient for casual use
- Videos without auto-generated or manual captions cannot be transcribed
- For non-English videos, Supadata returns the transcript in the original language; summarize accordingly
- Do NOT use
youtube-transcript-apiPython library oryt-dlp— cloud server IPs are blocked by YouTube. Always use Supadata API.