xianxia-visual-director skill
A Codex skill that writes xianxia image prompts: celestial cities, checkable scale, five depth layers and several aspect ratios.
- 595 ★ on the repository
- Last commit
Minimal access
Why this level
- The skill only writes prompt text and takes no external actions.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/xianxia-visual-directorDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill only writes prompt text and takes no external actions.
This is third-party code. Review the repository files before installing.
What it does
The `xianxia-visual-director` skill turns a short idea, an existing prompt or a reference into a structured image-generator request. Output is a scene plan, a positive prompt, constraints and variants. A single rule set underlies it: at least four scale cues, five depth layers, forty to sixty percent of content-bearing air, railing-free architecture. The skill separates a single landmark from an inhabited city of gods and supports 16:9, 21:9, 4:3, 3:2, 4:5 and 9:16.
Who it is for. Illustrators and concept artists building eastern fantasy scenes who want controllable prompts instead of lucky draws.
Good fit when
- A celestial capital or a lone palace above a cloud sea is wanted from a single line.
- An existing prompt gives a flat layout and muddy greys and needs repair.
- One scene has to move to vertical 9:16 without changing its style.
- A series of images is built around shared scale rules.
Not a fit when
- You want a realistic or modern subject without eastern architecture.
- You need a finished picture without a generator: the skill writes prompts.
- The task is to copy a specific artist's style.
Example request
Design a celestial gate scene above a cloud sea in 21:9 and return a finished prompt with negative constraints.Limitations
The documentation is in Chinese. The repository has no license file, and the README states that public visibility grants no right to copy or redistribute. Use it personally and ask the author for anything beyond that. Last commit August 2026. The skill targets Codex and Agent Skills systems. Output depends on the image generator: the same prompt gives different pictures in different services.
How to disable. Delete the `xianxia-visual-director` folder from the agent's skills directory, for example `~/.codex/skills`.
FAQ
Does the skill generate images itself?
By default it prepares a single prompt. Direct generation works when a generator is connected.
Which aspect ratios are supported?
16:9 by default, plus 21:9, 4:3, 3:2, 4:5 and 9:16. A vertical ratio does not turn into a nine-image series.
Can the style be changed?
Yes, style routes range from luminous colourful fantasy to monumental sky structures while the shared rules stay.
What license does it have?
The repository has no license file, so no copying or republishing rights are granted.
Is Chinese required?
The skill handles requests in Russian and English, but the repository reference materials are in Chinese.
Discussion
No questions or reviews yet.
Related
SkillsA Codex skill that turns photos, receipts and pets into a humorous social post with a 3:4 poster brief and an image prompt.
A Codex skill that turns a photograph into a vertical composition with an abstract memory panel and an English title
A Codex skill that turns a Chinese article into a series of hand-drawn 16:9 illustrations on white background with the Xiaohei character
A skill that turns your photo or description into a hand-drawn character and uses it for diagrams, knowledge cards and slides
A Codex skill that draws 16:9 scenes with the Xiaohei character among real objects for Chinese articles
A skill that turns photos of buildings, streets and local culture into art-directed editorial posters via an image model
README in short
The README is in Chinese and lists capabilities, shared rules, scene and style routes, aspect ratios and installation.