with one click
media-scan
Scan configured paths for new/changed media files
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
Scan configured paths for new/changed media files
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
The Claw Fleet โ 5 AI engines (Media, Forge, Herald, Scout, Scribe) with 33 skills, cross-claw events, and fleet orchestration for creative operations.
Visual web dashboard for managing AI agent pipelines. Inbox with approval cards, live agent monitoring, social scheduling, and publish pipeline.
Complete AI-powered media processing pipeline for creative world-building. Scans, classifies, processes, scores, and uploads media with fantasy/mythology-aware tagging.
Auto-generate platform-optimized image variants and AI-written captions for Instagram, LinkedIn, X, YouTube, and TikTok from any source image.
AI-powered aesthetic quality scoring for images. 5-dimension evaluation: Canon Alignment, Design Compliance, Emotional Impact, Technical Fit, Uniqueness. Scores 0-100 with automatic tier assignment.
Classify untagged media against Arcanea canon using Gemini Vision
| name | media-scan |
| description | Scan configured paths for new/changed media files |
| trigger | scheduled |
| interval | 900 |
| sandbox | true |
| inputs | [{"name":"scan_paths","type":"list[str]","description":"Filesystem paths to scan for media files","source":"config.yaml#arcanea_claw.scan.paths"},{"name":"extensions","type":"list[str]","description":"Allowed file extensions","source":"config.yaml#arcanea_claw.scan.extensions"},{"name":"ignore_patterns","type":"list[str]","description":"Directory/file patterns to skip","source":"config.yaml#arcanea_claw.scan.ignore_patterns"}] |
| outputs | [{"name":"new_files_count","type":"int","description":"Number of newly discovered files inserted into asset_metadata"},{"name":"file_hashes","type":"list[str]","description":"MD5 hashes of all newly found files"}] |
| dependencies | {"python":["Pillow","supabase"]} |
| tables | ["asset_metadata (INSERT WHERE NOT EXISTS by file_hash)"] |
Walks configured scan paths on a 15-minute heartbeat, discovers new or changed
media files, computes MD5 hashes, extracts basic metadata (size, dimensions,
MIME type), and inserts new rows into asset_metadata with status='new'.
Files already tracked (by hash match) are skipped. Directories matching
ignore_patterns are pruned from the walk.
Step 1 of 8 โ runs first, feeds media-classify and media-dedup.