デザイン・メディアに強いスキル

Site audit, content writing, and competitor analysis for organic search rankings.

Create and critique visual artifacts with quantified rules for hierarchy, spacing, type scale, color, and layout.

Search, read, and manage YouTube videos, playlists, channels, subscriptions, and comments via managed OAuth.

Generate AI portraits with 140+ nationalities, 8 styles, and 24 moods via a free or donation-based API.

Generate up to 4-minute videos from a single prompt — scripted, voiced, scored, and edited automatically.

Designs the delivery system across services — pipelines, deploys, environments, reliability, on-call — and keeps local notes.

Compress any source while preserving every claim, hedge, number, and attribution.

Produces design deliverables — palettes, specs, guidelines, audits — with the specific values engineers and printers build from.

Cross-border e-commerce research agent with 79 built-in tools for Amazon product, keyword, competitor, patent, and trend analysis, plus 1688 sourcing and image…

Plans and progresses workout programs with quantified rules for strength, muscle, cardio, and comeback from missed training.

Generate, edit, and process commercially safe images via 20+ Bria.ai API endpoints.

Operate and extend the read-only OpenClaw dashboard backend, frontend tabs, and security model.

Diagnose and fix Visual Studio Code at the editor layer: settings scopes, debug, formatters, extensions, keybindings, remotes.

WP-CLI toolkit to audit, clean, and tune WordPress sites: database, autoload, slow queries, frontend.

Delegate multi-format work to an AI sub-agent that delivers PDFs, dashboards, videos, and spreadsheets from one call.

Pillow image toolkit for resize, crop, watermark, format conversion, and web optimization.

Publish websites and files to live URLs at {slug}.here.now, with password or invite-only access control.

Prisma schema design, type-safe queries, and fixes for migrations, connection pools, and N+1 in Node and TypeScript.

Reads an article, marks the spots that need a visual, and generates matching illustrations via Type × Style × Palette.

Long-form story creation and multilingual translation agent with a confirmable action workflow.

Get Markdown that renders correctly in GitHub, MDX, Pandoc, docs sites, Slack, Notion, and other parsers.

Generate and edit images from text or references using routed AI models, with character consistency and product photography support.

Generate polished PDF and DOCX documents from prompts — resumes, contracts, reports, proposals, and more.

Generate cohesive game assets — art, 3D models, UI, music, and GDDs — from a single prompt.