MCP servers and skills: search, filter by where they run, and compare.
A searchable GPT Image 2 portrait-prompt atlas organized by outcome and scenario. Maintained by @dboy_yi2025 on X.
SkillMIT★ 9No key
`xxg-portrait-rebuild-light` is an image-edit skill for existing portrait photos. It reconstructs the key light, fill, shadows, and background atmosphere with a director-led lighting workflow while re
SkillMIT★ 218No key
🎭 Know yourself as a developer. One command → AI analyzes your coding history → beautiful personality portrait + persona skill. Works with Claude Code & Codex.
SkillMIT★ 27No key
Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. Use for prompt-only image generation, image edits, and multi-image compositing; supports 1K/2K/4K output.
OfficialSkillMIT★ 40k in collectionNo key
A Claude Code skill for web report decks — richer ECharts charts, one file per slide (edit one page, save tokens), and complex structure diagrams. 16:9 & vertical, PDF/image export.网页版 PPT 汇报的 Claude
SkillMIT★ 81No key
One-ink editorial print image skill — warm paper, halftone photography, active negative space, and restrained typography.
SkillMIT★ 3.4kNo key
Soulscrape is a free agent skill that writes a dated dossier on a person, company, or product, with every claim tied to its sources, kept private or published.
SkillMIT★ 1Few starsNo key
Turn a photo into a portrait 3:4 monthly Zine postcard with image-grounded literature and music curation. Ready-to-use Codex / WorkBuddy Skill.
SkillMIT★ 23No key
Collection of Claude Code skills for enhanced AI workflows
SkillMIT★ 393No key
AI media generation skills for Codex, Claude Code and other agents. Images, video and audio workflows using Magic Hour MCP or API.
SkillMIT★ 12No key
Agent skill that generates Apple-inspired bento grid presentation cards. For Claude Code, Codex, and any AI coding agent.
SkillMIT★ 236No key
Open-source agent skills for generating editorial-style information cards from natural-language input.
SkillMIT★ 516No key
Claude paints with code: a Claude Code skill for procedural illustration in 70 styles, from ink wash (水墨), watercolour and ukiyo-e to stained glass, Roman mosaic, Art Deco, shadow puppets, X-ray, VHS
SkillMIT★ 34No key
An open Agent Skill for reconstructing faithful, reusable image-generation prompts from reference images.
SkillMIT★ 30No key
A Claude skill for adapting iOS apps to iPhone Duo: resizable layout, the fold, vertical bars, and the Xcode 27.1 requirements
SkillMIT★ 3Few starsNo key
Publication-grade figures for scientific papers — reproducible matplotlib & TikZ, with a quality bar, composition paradigms, and journal-grade craft. A self-contained Claude skill.
SkillMIT★ 57No key
Open-source Codex Skill with 24 photo-to-art styles for illustrations, stickers, paper cutouts, prints, collage, pixel art, and comparisons.
SkillMIT★ 6No key
Image generation skill for Claude Code / Codex / OpenClaw — wraps api.letmego.top (GPT-Image-2)
SkillMIT★ 1Few starsNo key
AI manga page generation skill pack with persistent character image memory for consistent characters across pages.
SkillMIT★ 14No key
抠图、图片抠图、视频抠图、去背景、背景移除、人像抠图、透明背景, background removal, background remover, remove background, image matting, video matting, image segmentation, image cutout, cut out image, transparent background, portr
SkillMIT★ 16No key
16 AI conversation personality types based on your real Claude Code / Cursor / Codex prompts. 100% local, MIT, ~500 lines.
SkillMIT★ 3Few starsNo key
Codex Skill for turning a source photo into a minimal editorial illustration composition
SkillMIT★ 15No key
Codex skill for director-level Eastern beauty AI image prompts, covering gu feng, Eastern fantasy, modern Chinese aesthetics, SweetHomeGirl lifestyle portraits, prompt routing, style systems, and imag
SkillMIT★ 33No key
Who stands behind it
