ClaudeMap

Guizang Yingzao Skill

Guizang's art-direction skill: turn architecture, street, and food photos into editorial-grade posters.

Skills & Commandsdesignphotographyskillimage
Visit projectop7418/guizang-yingzao-skill

From Guizang (op7418), a well-known Chinese AI-art voice: the yingzao skill turns photos of buildings, streetscapes, shops, and food into art-directed editorial posters — not a filter passthrough. It reads the composition's identity first and fixes only the one composition problem that truly matters, protects identity anchors (flying eaves, plaques, silhouettes) so real buildings don't get "optimized" into different ones, and supports Chinese display typography plus multi-image compositions, with a path to 3x3 storyboard frames and video-model prompts.

What it does

  • Reads the photo's composition type (facade, low-angle, diagonal, framed, structural detail, environmental) and fixes only the one composition problem that truly matters
  • Protects identity anchors — roof slopes, flying eaves, plaques, silhouettes, asymmetry — so real buildings are not "optimized" into different ones
  • Designs Chinese display typography (width, weight axis, stroke contrast, terminals, counters, rhythm) and unifies multiple photos into one shared perspective, light direction, and contact-shadow language
  • Deterministic preflight gates run before the image-model call; one low-cost read-back diagnosis after — no automatic regeneration, edits resume only on your feedback

When to use it

Turning travel and architecture photos into editorial posters: heritage buildings, historic streets, cultural shops, handmade objects, local food. A finished poster can extend into a 3x3 video storyboard with prompts ready for video models.

Getting started

npx skills add https://github.com/op7418/guizang-yingzao-skill --skill yingzao

# First run: dependency check (Python 3.10+, Pillow, NumPy, OpenCV, fontTools)
python3 yingzao/scripts/check_dependencies.py

Things to know

Needs an agent that supports Skills, reads local images, and can call an image generation/editing tool. Out of scope per the README: e-commerce hero shots, generic retouching (exposure or sky swaps), fictional buildings with no real reference, and tasks needing only deterministic collage with no image model.

Repository

op7418/guizang-yingzao-skill

Charted

Related on the map

  • SureForge

    Skill

    An instruction-only skill that makes agents research before they ask, plan before they build, and verify before they call anything done.

    • workflow
    • verification
    • quality
    • skill
    View

  • guizang-product-video-skill

    Skill

    Guizang's agent skill turns your repo's recent updates into a finished promo video — real components, code-rendered animation, an original code-written soundtrack — no video editor involved.

    • agent-skill
    • video
    • promo
    • marketing
    View

  • geo-sleuth

    Skill

    An agent skill that geolocates a photo with nothing readable in it — OSM geometry, elevation skylines and satellite tiles turn “where was this taken?” into a measured answer with an error radius.

    • agent-skill
    • geolocation
    • osint
    • openstreetmap
    View