Agent skill

Nuyoah Xiezhen Prompt

by nuyoah-ai-works in nuyoah-ai-works/nuyoah-xiezhen-prompt

当需要生成、改写、扩展或反向拆解 AI 写真、人像摄影、editorial photography 中文提示词时使用;也用于用户提供一组写真参考图,希望换一位人物、按同一摄影企划重新拍摄新分镜,并在明确要求生图时完成 Codex Image 生成、检查与可选归档。普通提示词请求默认不主动生图。

MITAuto-check passedMedia & Creative

Install Nuyoah Xiezhen Prompt

skills CLI
$ npx skills add nuyoah-ai-works/nuyoah-xiezhen-prompt --skill nuyoah-xiezhen-prompt -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nuyoah-ai-works/nuyoah-xiezhen-prompt nuyoah-xiezhen-prompt --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
nuyoah-xiezhen-prompt
GitHub stars
754
Token cost
~729 tokens
SKILL.md length
108 words
Files
17 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

当需要生成、改写、扩展或反向拆解 AI 写真、人像摄影、editorial photography 中文提示词时使用;也用于用户提供一组写真参考图,希望换一位人物、按同一摄影企划重新拍摄新分镜,并在明确要求生图时完成 Codex Image 生成、检查与可选归档。普通提示词请求默认不主动生图。

  • Works in 4 steps: 人物图承担身份还是摄影参考,必须先分清。用户另外提供人物形象图但没有说明用途时,只… → 人物身份参考只回答“她是谁”,保持主要五官辨识度;目标写真接管妆容、发型、服装、场… → 写真方案参考只回答“这套写真怎样被拍出来”,不承担人物身份。Prompt… → …
  • Media & Creative work in your project
  • SKILL.md covers 目标, 入口判断, 参考图职责 and 共享原则, plus 2 more sections
  • Runs Python scripts from its folder

What it does

Nuyoah Xiezhen Prompt is an agent skill from nuyoah-ai-works/nuyoah-xiezhen-prompt. 当需要生成、改写、扩展或反向拆解 AI 写真、人像摄影、editorial photography 中文提示词时使用;也用于用户提供一组写真参考图,希望换一位人物、按同一摄影企划重新拍摄新分镜,并在明确要求生图时完成 Codex Image 生成、检查与可选归档。普通提示词请求默认不主动生图。

Its SKILL.md is about 730 tokens, which your agent loads only when the skill is triggered. The skill folder holds 20 other files, including reference files (for example `AGENTS.md`, `CHANGELOG.md` and `README.md`).

It sits in Media & Creative. The licence is MIT.

When your agent uses it

  • Media & Creative work in your project

Example prompts

  • “/nuyoah-xiezhen-prompt”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. 人物图承担身份还是摄影参考,必须先分清。用户另外提供人物形象图但没有说明用途时,只问一次:它是要保持同一位人物,还是只借人物气质?
  2. 人物身份参考只回答“她是谁”,保持主要五官辨识度;目标写真接管妆容、发型、服装、场景、道具、光线和情绪。
  3. 写真方案参考只回答“这套写真怎样被拍出来”,不承担人物身份。Prompt 必须正向写入:本张重新生成一位「【原创女性类型】」类型的成年原创女性,不要继承写真参考图中人物的脸。
  4. 没有人物身份图时,根据写真类型自动替换 【原创女性类型】,以人物好看、动作自然和画面成立为优先;不检查组内是否为同一张脸,也不增加生成脸与写真参考人物逐一比较的验收层。

What it can do on your machine

Read from SKILL.md and the folder at commit 7482a14. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Nuyoah Xiezhen Prompt loads about 729 tokens when it runs, and up to ~22k if it reads all its reference files. Until then it costs about 42 tokens; SKILL.md has 108 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~729
With references · SKILL.md plus every file in references/, read only if the agent opens them
~22k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nuyoah-ai-works/nuyoah-xiezhen-prompt at commit 7482a14, republished under its MIT licence (© nuyoah-ai-works). 108 words, ~729 tokens.

Download SKILL.mdSave it as .claude/skills/nuyoah-xiezhen-prompt/SKILL.md (or your agent's skills folder). This skill also uses 16 other files; get the full folder from GitHub.
name
nuyoah-xiezhen-prompt
description
当需要生成、改写、扩展或反向拆解 AI 写真、人像摄影、editorial photography 中文提示词时使用;也用于用户提供一组写真参考图,希望换一位人物、按同一摄影企划重新拍摄新分镜,并在明确要求生图时完成 Codex Image 生成、检查与可选归档。普通提示词请求默认不主动生图。
license
MIT
metadata.author
南鸢 nuyoah
metadata.version
1.1.0
metadata.homepage
https://knowledge.nuyoahonline.com/skills/nuyoah-xiezhen-prompt
metadata.source
https://github.com/nuyoah-ai-works/nuyoah-xiezhen-prompt

nuyoah-xiezhen-prompt

目标

把写真意图编译成可直接使用的中文 Prompt;当用户明确要“换个人拍同一套写真”并要求生成时,把参考组还原成可执行的摄影方案,在 Codex Image 中生成指定数量的新照片并完成质量检查与可追溯交付。Eagle 只在当前环境可用时作为附加归档,不是完成任务的前提。

入口判断

先选择一种模式:

  • 用户提供一组写真参考并表达“照这套拍、换个人拍一套、像去同一家店拍、复刻这套写真企划”等意图时,进入摄影方案复拍。读取 摄影方案复拍工作流;只有用户明确要求生图才执行完整生成闭环。
  • 用户说“系列母版、一整套系列、系列规划、固定格式”时,输出系列母版。
  • 用户只说“变体、同系列、创作变体、仿拍扩展”,但没有表达完整摄影企划复拍意图时,输出同系列变体关键词链。
  • 用户说“完整、详细、精准控制、复刻 Prompt”时,输出详细提示词。
  • 用户说“抽卡、网页端、大量生成、短关键词、开盲盒”时,输出 6–8 行抽卡关键词。
  • 用户给图片并要求拆解时,输出图片关键词;组图先提取共同视觉 DNA,再列单张差异。用户明确“只拆解、不生图”时不得进入生成闭环。
  • 用户给出 主题:、人物类型、关键词: 三段骨架时,直接按 提示词逻辑与模板 的三段式规则编译,不依赖包外模板。
  • 用户说“文化视觉溯源、文化元素、往外扩展灵感”时,只根据当前可见证据区分事实、强关联和灵感联想;需要外部史实或来源时先真实检索,不依赖私有知识库方法。

普通提示词、变体、拆解与模板规则读取 提示词逻辑与模板。维护或回归验收本 Skill 时,同时读取 evals/skin_reflection_cases.json 与 evals/production_reshoot_cases.json。

参考图职责

  1. 人物图承担身份还是摄影参考,必须先分清。用户另外提供人物形象图但没有说明用途时,只问一次:它是要保持同一位人物,还是只借人物气质?
  2. 人物身份参考只回答“她是谁”,保持主要五官辨识度;目标写真接管妆容、发型、服装、场景、道具、光线和情绪。
  3. 写真方案参考只回答“这套写真怎样被拍出来”,不承担人物身份。Prompt 必须正向写入:本张重新生成一位「【原创女性类型】」类型的成年原创女性,不要继承写真参考图中人物的脸。
  4. 没有人物身份图时,根据写真类型自动替换 【原创女性类型】,以人物好看、动作自然和画面成立为优先;不检查组内是否为同一张脸,也不增加生成脸与写真参考人物逐一比较的验收层。

共享原则

  1. 先判断照片为什么成立,再写细节。光线必须写清来源、方向、在人身与环境中的落点和成像结果;更换机位时,光源、遮挡物与环境反射固定在世界空间中,先重建新视角下的受光关系,再编译 Prompt。
  2. 风格写成可观察的成像机制,不用“高级、氛围感、电影感”代替白平衡、曝光、反差、高光、锐度、噪点、压缩和景深。
  3. 穿搭只写服装,饰品放入道具;场景与道具分开。
  4. 默认人物为成年年轻女性,强调成年后的青春、灵动和生命力;不写未成年或儿童化表达。
  5. 有人物身份图时把身份与表情分开控制;身份图只提供稳定五官锚点,本张表情由目标拍摄中的具体人物事件决定,不默认继承身份图的中性眼神和嘴角状态。
  6. 场景复杂度服从参考图的画面信息层级;先区分主体清晰区、主导大形、次级细节和低细节留白,不因场景元素多就让背景每一层都清楚。
  7. 摄影方案复拍的每一轮都从原始人物图、原始写真参考和本轮重新编译的完整 Prompt 开始;上一轮生成图只用于诊断问题。除非用户明确要求编辑上一张图,不把任何生成图作为新一轮视觉输入,也不在旧 Prompt 上追加补丁式修图指令。
  8. 新一轮结果直接对照原始写真参考判断;“比上一轮更有风格”只表示相对改善,不能替代原作保真、结构检查和用户验收。
  9. 原作若依赖欠曝、失焦、堵黑和偶发抓拍,必须启动去商业抛光层:把连续暖色轮廓光、皮革折面塑形、稳定脸部焦点、正面回填和英雄式构图改写为原作支持的物理结果;精致 editorial 原作不套用这条降质规则。
  10. 皮肤质感必须区分纹理与反射;近景、直闪或高光妆面要按景别控制底妆反射和高光范围。
  11. 图片拆解只写可见事实;不确定内容标为“疑似”,不编造品牌、摄影师、器材或历史来源。
  12. 用户没有明确要求生成时,只交付 Prompt 或拆解结果,不产生图片、Eagle 资产或项目记录。
  13. 默认不添加任何署名或水印。只有用户明确要求时,才加入用户指定的署名文字;不得默认使用 nuyoah 或替用户决定署名内容。

输出

  • 普通模式直接交付用户触发的 Prompt 或拆解结果,不输出内部分析模块。
  • 摄影方案复拍必须在对话中交付简短摄影方案摘要、实际图片、每张完整 Prompt、参考职责、质量状态与追溯记录。Eagle 可用且归档成功时再附 Eagle ID;不可用或归档失败不影响上述核心交付。
  • 默认中文,仅保留模型更易理解的摄影英文词。

环境兼容

在有本地项目规则的工作区中,先读取当地 AGENTS.md 和适用的生图方法;项目规则可以补充归档与记录要求,但不得把署名或 Eagle 变成跨环境默认前提。环境提供图片生成工具且用户明确要求生图时,才执行真实生成;没有图片生成工具时,明确停在 Prompt 与摄影方案交付层,不得声称已经出图。检测到 nuyoah-codex-image-to-eagle 且 Eagle 可用时才执行归档;未安装、未连接、同步失败或用户不使用 Eagle 时,继续在对话中完成全部核心交付。

© nuyoah-ai-works, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 16 other files (references) in the repository root of nuyoah-ai-works/nuyoah-xiezhen-prompt.

  • SKILL.md
  • .gitignore
  • AGENTS.md
  • CHANGELOG.md
  • LICENSE
  • README.md
  • SOURCE.md
  • agents/interface.yaml
  • agents/openai.yaml
  • evals/production_reshoot_cases.json
  • evals/semantic_config.json
  • evals/skin_reflection_cases.json
  • evals/trigger_cases.json
  • manifest.json
  • references/production-reshoot.md
  • references/prompt-logic.md
  • tests/run_contract_tests.py

Open the folder on GitHubat commit 7482a14

Compare with similar skills

Nuyoah Xiezhen Prompt next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Nuyoah Xiezhen Prompt compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nuyoah Xiezhen Prompt this skillnuyoah-ai-works/nuyoah-xiezhen-prompt754—~729Automated safety check: PassMIT
Guizang Social Cardsop7418/guizang-social-card-skill7.4k1 repos~7.8kAutomated safety check: PassAGPL-3.0
Weekly Changelog Videoheygen-com/hyperframes60k—~3.3kAutomated safety check: PassApache-2.0
Anthropic Brand Stylinganthropics/skills180k30 repos~559Automated safety check: PassApache-2.0
MoneyPrinterTurbo Video Generatorharry0703/MoneyPrinterTurbo130k—~2.1kAutomated safety check: WarnMIT
HyperFrames Media Useheygen-com/hyperframes60k—~2.4kAutomated safety check: PassApache-2.0

Similar skills

  • Guizang Social Cards

    op7418/guizang-social-card-skill

    Produces social card sets for Xiaohongshu and WeChat: carousels, Live Photo motion cards and puzzle layouts, and WeChat cover pairs, rendered from single-file HTML.

    7.4k GitHub starsUsed in 1 repo~7.8k tokens
    Media & CreativeAuto-check passed
  • Weekly Changelog Video

    heygen-com/hyperframes

    Turns a weekly changelog markdown file into a branded HyperFrames video with voiceover, animated mock-UI scenes and captions, using fonts, background and scripts bundled in the skill.

    60k GitHub stars~3.3k tokensUpdated today
    Media & CreativeAuto-check passed
  • Anthropic Brand Styling

    anthropics/skills

    Official

    Applies Anthropic's brand colors and fonts to artifacts such as PowerPoint slides, using fixed hex values for text and accents, Poppins headings and Lora body text.

    180k GitHub starsUsed in 30 repos~559 tokens
    Media & CreativeAuto-check passed
  • MoneyPrinterTurbo Video Generator

    harry0703/MoneyPrinterTurbo

    Installs and runs MoneyPrinterTurbo to turn a topic or script into a finished short video with voice-over, subtitles, stock footage and music.

    130k GitHub stars~2.1k tokensUpdated yesterday
    Media & CreativeAuto-check: warnings
  • HyperFrames Media Use

    heygen-com/hyperframes

    Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.

    60k GitHub stars~2.4k tokensUpdated today
    Media & CreativeAuto-check passed
  • Holo Card Studio

    EverettFish/holo-card-studio

    Create collectible holographic foil cards and two-image lenticular flip cards with AI-generated full-color ukiyo-e and colored sumi-e anime artwork, layered Blender scenes, renders, GLB export, and…

    1.9k GitHub stars~1.4k tokensUpdated 19 days ago
    Media & CreativeAuto-check passed

Questions about Nuyoah Xiezhen Prompt

What does Nuyoah Xiezhen Prompt do?

当需要生成、改写、扩展或反向拆解 AI 写真、人像摄影、editorial photography 中文提示词时使用;也用于用户提供一组写真参考图,希望换一位人物、按同一摄影企划重新拍摄新分镜,并在明确要求生图时完成 Codex Image 生成、检查与可选归档。普通提示词请求默认不主动生图。. Nuyoah Xiezhen Prompt is an agent skill from nuyoah-ai-works/nuyoah-xiezhen-prompt.

When should I use Nuyoah Xiezhen Prompt?

Nuyoah Xiezhen Prompt fits situations like: media & Creative work in your project.

How do I install Nuyoah Xiezhen Prompt in Claude Code?

Run `npx skills add nuyoah-ai-works/nuyoah-xiezhen-prompt --skill nuyoah-xiezhen-prompt -a claude-code`. Or copy the skill folder (the nuyoah-ai-works/nuyoah-xiezhen-prompt repository) into .claude/skills/nuyoah-xiezhen-prompt in your project. Claude Code loads it when a task matches its description.

How do I install Nuyoah Xiezhen Prompt in Codex?

Run `npx skills add nuyoah-ai-works/nuyoah-xiezhen-prompt --skill nuyoah-xiezhen-prompt -a codex`. Or copy the skill folder (the nuyoah-ai-works/nuyoah-xiezhen-prompt repository) into .agents/skills/nuyoah-xiezhen-prompt in your project. Codex loads it when a task matches its description.

Can I use Nuyoah Xiezhen Prompt in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nuyoah-ai-works/nuyoah-xiezhen-prompt --skill nuyoah-xiezhen-prompt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nuyoah-xiezhen-prompt, .gemini/skills/nuyoah-xiezhen-prompt, .github/skills/nuyoah-xiezhen-prompt and .opencode/skills/nuyoah-xiezhen-prompt in your project.

What does Nuyoah Xiezhen Prompt need to run?

Going by SKILL.md and its folder, Nuyoah Xiezhen Prompt needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Nuyoah Xiezhen Prompt access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Nuyoah Xiezhen Prompt safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Nuyoah Xiezhen Prompt use?

Nuyoah Xiezhen Prompt is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Nuyoah Xiezhen Prompt use?

About 729 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 21k tokens, read only when the agent opens those files.

What are the alternatives to Nuyoah Xiezhen Prompt?

Skills that share tags, products or a category with Nuyoah Xiezhen Prompt: Guizang Social Cards (op7418/guizang-social-card-skill, 7.4k stars), Weekly Changelog Video (heygen-com/hyperframes, 60k stars), Anthropic Brand Styling (anthropics/skills, 180k stars) and MoneyPrinterTurbo Video Generator (harry0703/MoneyPrinterTurbo, 130k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nuyoah Xiezhen Prompt?

nuyoah-ai-works (a GitHub user) maintains it in nuyoah-ai-works/nuyoah-xiezhen-prompt, which has 754 GitHub stars. The repository was last updated on August 26, 2026.

Source: nuyoah-ai-works/nuyoah-xiezhen-prompt on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.