ワンクリックで
media-process
Convert classified media to WebP and generate size variants
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Convert classified media to WebP and generate size variants
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
The Claw Fleet — 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-process |
| description | Convert classified media to WebP and generate size variants |
| trigger | pipeline |
| depends_on | ["media-classify"] |
| sandbox | true |
| inputs | [{"name":"webp_quality","type":"int","description":"WebP compression quality (0-100)","source":"config.yaml#arcanea_claw.process.webp_quality"},{"name":"max_dimension","type":"int","description":"Maximum pixel dimension on longest side","source":"config.yaml#arcanea_claw.process.max_dimension"},{"name":"size_variants","type":"dict","description":"Named variant sizes (width, height)","source":"config.yaml#arcanea_claw.process.size_variants"},{"name":"staging_dir","type":"str","description":"Root directory for processed output","source":"config.yaml#arcanea_claw.process.staging_dir"}] |
| outputs | [{"name":"processed_count","type":"int","description":"Number of assets processed this cycle"}] |
| dependencies | {"python":["Pillow","supabase"]} |
| tables | ["asset_metadata (UPDATE metadata JSONB with variant paths, status='processed')"] |
Takes classified assets and produces production-ready WebP files:
Output is organized by guardian: /data/staging/{guardian}/{variant}/{filename}.webp
Step 4 of 8 — runs after media-dedup, feeds taste-score.