agentleFS
Sign inStart free
PatriotAgenticLLCPatriotAgenticLLC/better_claude_skillz/skills/supadata/SKILL.md

supadata

Skill3 starsChanged 5 months agoMITView on GitHub

Fetch video transcripts and transcriptions from external URLs — YouTube transcripts, TikTok transcripts, Instagram, X, Facebook. Pull a transcript, get a transcription, extract captions from any video URL. Also: YouTube search (find videos, keyword research, competitor discovery), web scraping (scrape a page to markdown, crawl a website), social media metadata (views, likes, engagement stats), channel and playlist data.

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use curl or Python requests/httpx directly.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Supadata API

Content extraction API for YouTube, social media, and web pages. 21 endpoints, credit-based pricing.

Authentication

  • API key env var: SUPADATA_API_KEY
  • Header: x-api-key: <key>
  • Base URL: https://api.supadata.ai/v1

Set your SUPADATA_API_KEY (via env or your secrets manager, e.g. Doppler) before calling the API. If your secrets are injected by a manager, run inside that manager's shell (for example, doppler run -- ...).

Calling the API

Use curl or Python requests/httpx directly. All endpoints accept the x-api-key header.

# Example: get a transcript
curl -s -H "x-api-key: $SUPADATA_API_KEY" \
  "https://api.supadata.ai/v1/transcript?url=https://youtube.com/watch?v=VIDEO_ID&text=true"

Endpoint Reference

EndpointMethodWhat It DoesCredits
/v1/transcript?url=&text=trueGETTranscript as plain text (YouTube, TikTok, IG, X, FB)1
/v1/transcript?url=GETTranscript with timestamps/chunks1
/v1/transcript/{jobId}GETPoll async transcript job0
/v1/youtube/transcript/translate?url=&lang=GETTranslate YouTube transcript30/min
/v1/youtube/transcript/batchPOSTBatch transcript extraction1 + 1/video
/v1/youtube/video?id=GETVideo metadata (title, views, duration, channel)1
/v1/youtube/video/batchPOSTBatch video metadata1 + 1/video
/v1/youtube/batch/{jobId}GETPoll batch job0
/v1/youtube/channel?id=GETChannel stats (subscribers, videos, total views)1
/v1/youtube/channel/videos?id=GETList video IDs from a channel1
/v1/youtube/playlist?id=GETPlaylist metadata1
/v1/youtube/playlist/videos?id=GETList video IDs from a playlist1
/v1/youtube/search?query=GETSearch YouTube (title, views, duration, channel)1/page
/v1/metadata?url=GETSocial post metadata (views, likes, author)1
/v1/extractPOSTAI-powered structured extraction from videoFREE (beta)
/v1/extract/{jobId}GETPoll extraction job0
/v1/web/scrape?url=GETScrape webpage to clean markdown1
/v1/web/map?url=GETDiscover all URLs linked from a page1
/v1/web/crawlPOSTAsync full-site crawl1 + 1/page
/v1/web/crawl/{jobId}GETPoll crawl job0
/v1/meGETAccount info (plan, credits used/remaining)1

YouTube Search Parameters

ParamValues
uploadDateall, hour, today, week, month, year
typeall, video, channel, playlist, movie
durationshort (<4m), medium (4-20m), long (>20m)
sortByrelevance, rating, date, views

Async Jobs

Videos longer than 20 minutes and batch/crawl operations return {"jobId": "..."}. Poll the corresponding status endpoint until status == "completed".

Supported Platforms

  • Transcripts: YouTube, TikTok, Instagram, X (Twitter), Facebook
  • Metadata: YouTube, TikTok, Instagram, X, Facebook
  • Not supported: Live streams in progress, private/unlisted videos, YouTube Music

Error Reference

CodeMeaning
401Invalid API key
402Out of credits or plan limit
429Rate limit hit — slow down
transcript-unavailableNo transcript exists (still costs 1 credit)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free