Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Clarified that the WorthClip API is hosted on Convex (convex.site) and explained the significance of the domain used. - Added guidance about verifying the production API deployment via https://worthclip.com/developers.
What This Skill Does
WorthClip scores YouTube videos 1-10 against a personalized learning profile. It returns AI summaries, alignment analysis, and a curated feed of scored content. Supports channel tracking, persona configuration, and paginated feed browsing.
Instead of manually evaluating whether a video matches your learning goals, WorthClip automates scoring so you can triage a backlog of videos quickly.
When to use it
- Score a YouTube video before watching it
- Filter your feed to only show videos scored 8 or above
- Track specific YouTube channels and score their uploads
- Update your learning goals to recalibrate video scoring
- Check API usage to stay within billing limits
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Is this YouTube video worth watching for learning TypeScript?
- 1Extract the YouTube video ID from the URL
- 2Run score.sh with the video ID to submit it for scoring
- 3Poll until the scoring job completes
- 4Parse the returned score, verdict, and alignment summary
- 5Report the score and key alignment points to the user
Video scored 8/10 with verdict 'watch' — strong alignment with TypeScript learning goals, covers generics and type narrowing.
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.