Youtube research
Crawlora Agent Skills — structured public web data (search, e-commerce, social, finance, app stores, media, reviews) via the Crawlora REST API. Installable in any agent with the skills CLI or as a Claude Code plugin marketplace.
npx -y skills add Crawlora-org/crawlora-skills --skill youtube-researchAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Pulls structured YouTube data — video and channel details, transcripts/captions, comments, playlists, and search — via the Crawlora API as clean JSON, with no yt-dlp or HTML scraping. Use when the user provides a YouTube URL or asks for a transcript, comments, channel/video metadata, or video search results.
SKILL.md
3.3 KB, 822 tokens by cl100k_base, as published. Nobody here has run it
YouTube research
Resolve YouTube videos and channels, and pull transcripts, comments, playlists,
and search results as normalized JSON from the Crawlora API — no yt-dlp, no
browser, no scraping.
When to use this skill
- The user pastes a YouTube URL and wants its transcript, summary, or stats.
- "Get the comments on this video" / "what are people saying?"
- "List this channel's recent videos / shorts / playlists."
- "Search YouTube for …" or "what videos exist about …".
- Building a transcript-based summary, sentiment, or research pipeline.
Setup (one-time)
- Get a free Crawlora API key (2,000 credits/mo, no card) at https://crawlora.net.
export CRAWLORA_API_KEY=sk_your_key_here- All requests:
x-api-key: $CRAWLORA_API_KEYagainsthttps://api.crawlora.net/api/v1. Missing/invalid key →401.
How it works
- Resolve the id. A YouTube watch URL
https://www.youtube.com/watch?v=<ID>(orhttps://youtu.be/<ID>) gives the video id; channel URLs give a channel id. Extract the id before calling. - Transcript:
/youtube/transcript/{id}(use/youtube/transcript/{id}/languagesfirst if you need a specific language). - Metadata / comments:
/youtube/video/{id},/youtube/comments/{id}. - Channel:
/youtube/channel/{id}/videos,/channel/{id}/shorts,/channel/{id}/playlists,/youtube/profile/{id}. - Discovery:
/youtube/search?q=...to find videos by keyword.
Full endpoint list, methods, and params: reference/endpoints.md.
Calling the API
# Transcript for a video id (GET):
scripts/crawlora.sh /youtube/transcript/dQw4w9WgXcQ | jq '.'
# Video metadata + comments:
scripts/crawlora.sh /youtube/video/dQw4w9WgXcQ | jq '{title,views,channel}'
scripts/crawlora.sh /youtube/comments/dQw4w9WgXcQ | jq '.comments[].text'
# Search:
scripts/crawlora.sh /youtube/search q="web scraping tutorial" | jq '.'
Raw curl fallback:
curl -fsS -H "x-api-key: $CRAWLORA_API_KEY" \
"https://api.crawlora.net/api/v1/youtube/transcript/dQw4w9WgXcQ" | jq '.'
Endpoint reference
See reference/endpoints.md for every YouTube endpoint
this skill uses (method, path, params, description).
Examples
- Summarize a video: extract the id from the URL →
/youtube/transcript/{id}→ concatenate transcript segments → summarize. - Comment sentiment:
/youtube/comments/{id}→ bucket comments by sentiment and surface common themes. - Channel digest:
/youtube/channel/{id}/videos→ list recent uploads with view counts and publish dates.
Notes & limits
- Credits / pay-on-success: billed only on
2xx; free tier 2,000 credits/mo. Key at https://crawlora.net. - Public data only — public YouTube pages; respect YouTube's terms.
- Security: key lives in
CRAWLORA_API_KEYonly — never hardcode, query-param, or commit it. - Not every video has captions; check
/youtube/transcript/{id}/languageswhen a transcript request returns empty.
What ships with it: 2 files
7.9 KB alongside SKILL.md, 1 of them executable
reference/
- endpoints.md6.2 KB
scripts/
- crawlora.shruns1.8 KB