SocialKit YouTube Research

Researches a YouTube topic with the official YouTube Data API v3 - top videos, view and engagement statistics, titles, tags and gaps - and writes research.md for a video project. Use when the user wants topic ideas, competitor or trend research, or evidence for a YouTube video.

YouTube research

Requires YT_API_KEY. If it is missing, point the user to setup.

Steps

1. Agree on 1-3 search queries with the user, plus region and language if relevant.
2. For each query run: node scripts/research.mjs --query "<terms>" --max 15 --order viewCount Add --published-after <ISO date> for recent trends. Output is JSON on stdout. Each query costs one call from the 100/day search bucket; do not loop over many queries without asking.
3. Analyse: recurring angles, title patterns, typical length, views per day since publishing, and what the top videos do not cover.
4. Write research.md in the project folder with: queries used, a table of the top videos (title, channel, views, published, URL), patterns, gaps, and 3-5 proposed angles. Cite video URLs for every claim.

Rules

• Research informs an original video. Do not copy titles, scripts or thumbnails.
• Only report numbers from the script output. Do not estimate missing statistics.

Failure handling

• YT_API_KEY_MISSING: stop and show the setup steps.
• YT_QUOTA_EXCEEDED or YT_QUOTA_ESTIMATE_EXHAUSTED: stop; quotas reset at midnight Pacific Time.
• Empty results: suggest broader terms; do not invent results.