Install
openclaw skills install creator-screeningScreen and evaluate social media creators/influencers using configurable quality frameworks. Analyzes Instagram, TikTok, YouTube creators using Memories.ai V...
openclaw skills install creator-screeningAutomated creator/influencer screening powered by Memories.ai V2 Video Understanding API.
| Parameter | Default | Description |
|---|---|---|
videos_per_creator | 5 | Number of top videos to analyze per creator |
video_seconds | 30 | First N seconds of each video to analyze |
platforms | Supported: instagram, tiktok, youtube | |
analysis_mode | mai | mai (visual+audio AI analysis) or transcript (audio-only fallback) |
framework | default | Screening framework to apply. See references/frameworks/ |
output_format | discord | discord, pdf (Google Doc→PDF), or json |
batch_size | 10 | Max creators per batch run |
Screen these creators: @anshmehra.in, @nishkarshsharmaa
Parameters: videos_per_creator=3, framework=cac-crusher
Accept creator URLs in any format:
https://www.instagram.com/username/https://www.instagram.com/reel/SHORTCODE/https://www.youtube.com/@channel or /shorts/IDMemories.ai V2: POST /instagram/video/metadata
python3 scripts/scrape_profiles.py --urls "reel_url1,reel_url2" --channel rapid
Returns per video ($0.01/video):
Memories.ai V2 MAI: POST /instagram/video/mai/transcript
This is the core analysis step. MAI provides:
python3 scripts/analyze_videos.py --mode mai --videos_per_creator 5 --urls "url1,url2"
Each video returns visual + audio AI analysis. Use this to evaluate:
Fallback: If MAI is unavailable, use --mode transcript for audio-only analysis:
python3 scripts/analyze_videos.py --mode transcript --videos_per_creator 5 --urls "url1,url2"
Score against the selected screening framework:
python3 scripts/score_creator.py --framework cac-crusher --profile profile.json --transcripts transcripts.json
Frameworks live in references/frameworks/:
cac-crusher.md — CAC Crusher Creator Screening Framework (Talking Head + Skit categories)default.md — Generic quality screening (5 dimensions, weighted scoring)template.md — Template for creating custom frameworksOutput per-creator screening cards with:
Set the following environment variables before use:
export MEMORIES_API_KEY="your-memories-ai-v2-api-key" # Required — Memories.ai V2 API key
export APIFY_API_KEY="your-apify-key" # Optional — fallback scraper for profiles
Get your API key at https://api-tools.memories.ai
All endpoints use: Authorization: <API_KEY> header (no Bearer prefix).
Base URL: https://mavi-backend.memories.ai/serve/api/v2
| Endpoint | Method | Use | Cost |
|---|---|---|---|
/{platform}/video/metadata | POST | Profile + video stats | $0.01/video |
/{platform}/video/mai/transcript | POST | Visual + audio AI analysis | ~$0.11/video |
/{platform}/video/transcript | POST | Audio transcription only | ~$0.01/video |
Platforms: instagram, tiktok, youtube, twitter
Request body: {"video_url": "...", "channel": "rapid"}
MAI response: {"data": {"task_id": "..."}} (async, results via webhook)
URL format: Instagram must use /reel/SHORTCODE/ (not /p/ or /reels/)
/p/ → /reel/, /reels/ → /reel/