Youtube video scorer

v1.0.6

AI-powered YouTube video scoring. Scores videos 1-10 based on your learning goals and persona. Use when the user wants to evaluate YouTube videos, check their scored feed, manage tracked channels, or check API usage. Get AI summaries, alignment analysis, and a curated video feed. Keywords: YouTube, video, score, persona, feed, summary, AI, learning, channels. Requires a WorthClip API key from https://worthclip.com/developers.

2· 1.1k·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for ivanstancich/worthclip-youtube-video-scorer.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Youtube video scorer" (ivanstancich/worthclip-youtube-video-scorer) from ClawHub.
Skill page: https://clawhub.ai/ivanstancich/worthclip-youtube-video-scorer
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required env vars: WORTHCLIP_API_KEY
Required binaries: curl, jq
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Canonical install target

openclaw skills install ivanstancich/worthclip-youtube-video-scorer

ClawHub CLI

Package manager switcher

npx clawhub@latest install worthclip-youtube-video-scorer
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The name/description require only an API key and the ability to call WorthClip endpoints; the scripts use curl/jq to talk to the documented Convex backend (greedy-mallard-11.convex.site). No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md limits runtime actions to running the provided shell scripts which call WorthClip API endpoints. The scripts only read WORTHCLIP_API_KEY (declared) and do not access other files, system state, or external endpoints beyond the stated base URL.
Install Mechanism
There is no install spec; this is instruction/script-based and uses existing system tools (curl, jq). Nothing is downloaded or written to disk by an installer.
Credentials
Only one environment variable is required (WORTHCLIP_API_KEY), which is appropriate for a service-backed API skill. No additional secrets or unrelated variables are requested.
Persistence & Privilege
The skill is not always-enabled and model invocation is disabled (disable-model-invocation: true), reducing autonomous risk. The skill does not modify other skills or system configs.
Assessment
This skill is coherent and only needs your WorthClip API key and curl/jq to operate. Before installing: (1) Verify you trust WorthClip and that the base URL (https://greedy-mallard-11.convex.site) is the service deployment you expect (WorthClip documents that domain); (2) Keep your WORTHCLIP_API_KEY secret and only provide keys with appropriate scopes/limits; (3) Note that disable-model-invocation is set, so the model won't call the skill autonomously — you must invoke it; (4) If you ever suspect misuse, revoke/rotate the API key in your WorthClip dashboard.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

bullseye Clawdis
Binscurl, jq
EnvWORTHCLIP_API_KEY
Primary envWORTHCLIP_API_KEY
latestvk97b30tf2kp37sgff1j4f8syqs80xcre
1.1kdownloads
2stars
7versions
Updated 1mo ago
v1.0.6
MIT-0

WorthClip - YouTube Video Scoring

Score YouTube videos 1-10 based on your personalized learning goals. Get AI-powered summaries, alignment analysis, and a curated feed.

Setup

  1. Sign up at https://worthclip.com
  2. Go to Settings > API Keys
  3. Generate an API key
  4. Set it: export WORTHCLIP_API_KEY="wc_your_key_here"

Commands

Score a video

Scores a YouTube video against the user's persona and goals. Handles async scoring automatically with polling.

bash {baseDir}/scripts/score.sh "VIDEO_ID"

The script submits the video for scoring, polls for completion (up to 60 seconds), and returns the completed score JSON. If the video was already scored, it returns the existing score immediately.

Get your feed

Returns scored videos sorted by relevance, with optional filters.

bash {baseDir}/scripts/feed.sh [--min-score N] [--verdict VERDICT] [--limit N] [--cursor N]

Options:

  • --min-score N - Only return videos scored N or above (1-10)
  • --verdict VERDICT - Filter by verdict (e.g., "watch", "skip")
  • --limit N - Number of results per page
  • --cursor N - Pagination cursor from previous response

Check usage

Shows current billing period usage stats and limits.

bash {baseDir}/scripts/usage.sh

API Reference

Base URL: https://greedy-mallard-11.convex.site/api/v1

The API is hosted on Convex (convex.site), WorthClip's serverless backend. The domain greedy-mallard-11.convex.site is WorthClip's production Convex deployment. You can verify this by visiting https://worthclip.com/developers.

All requests (except /health) require Authorization: Bearer YOUR_API_KEY header.

EndpointMethodDescription
/healthGETHealth check (no auth required)
/scorePOSTScore a video (async, returns 202 with jobId)
/score/:jobIdGETPoll scoring job status
/videos/:ytId/summaryGETGet video summary (summarization)
/videos/:ytIdGETGet video detail with full score
/feedGETPaginated scored feed with filters
/channelsGETList tracked channels
/channels/lookupPOSTLookup channel by YouTube URL
/channels/trackPOSTTrack a new channel
/personaGETGet current persona and goals
/personaPUTUpdate persona description
/goalsPUTUpdate learning goals
/usageGETCurrent billing period usage stats

Rate Limits

  • General: 60 requests/minute (all endpoints)
  • Scoring: 20 requests/minute (POST /score and GET /score/:jobId)

Response headers:

  • X-RateLimit-Limit - Maximum requests per window
  • X-RateLimit-Remaining - Requests remaining in current window
  • Retry-After - Seconds to wait before retrying (only on 429 responses)

Error Format

All errors return a consistent JSON structure with an appropriate HTTP status code:

{
  "error": {
    "code": "ERROR_CODE",
    "message": "Human-readable description of the error"
  }
}

Common error codes:

  • UNAUTHORIZED (401) - Missing or invalid API key
  • RATE_LIMITED (429) - Too many requests
  • NOT_FOUND (404) - Resource not found
  • VALIDATION_ERROR (400) - Invalid request parameters
  • INTERNAL_ERROR (500) - Server error

Base URL

https://greedy-mallard-11.convex.site/api/v1

Comments

Loading comments...