No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by nuyoah-ai-works · Agent Tool · ★ 730
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is nuyoah-xiezhen-prompt safe to install? View the security audit →
南鸢写真提示词 南鸢写真与人像摄影 Skill。支持完整中文 Prompt、系列母版、同系列变体、网页端抽卡关键词、参考图拆解，以及“换一位人物、按同一摄影企划重新拍摄新分镜”的摄影方案复拍模式。 安装 更新已有安装： 更新后新建任务或重新加载 Agent，让新版指令进入上下文。 它解决什么 普通请求默认只交付 Prompt。只有用户明确要求生图时，摄影方案复拍模式才会在 Codex Image 中生成指定数量的图片并逐张检查。完整 Prompt、参考职责、质量状态和追溯记录直接在对话中交付；Eagle 只是检测可用后执行的可选归档，未安装或不可用不会中断任务。 摄影方案复拍会把人物身份与本张表情分开控制：身份图只提供稳定五官锚点，目标场景中的具体事件负责眉眼、呼吸、嘴角、视线和身体反应；同时按参考图重建主体清晰区、主导大形、次级细节和低细节留白，避免把“场景丰富”误写成“背景每一层都清楚”。 用户要求重做时，每一轮都会回到原始人物图与对应写真参考，从摄影方案和本轮反馈重新编译完整 Prompt。上一轮生成图只用于判断哪里失败，不作为新一轮输入；新图也直接对照原作验收，不以“比上一轮好”代替风格保真。 原作若依赖欠曝、失焦、堵黑和偶发抓拍，复拍会额外检查模型是否自行补入连续暖色轮廓光、稳定脸部焦点、皮革塑形、正面回填或英雄式构图，并把这些商业抛光改写为原作支持的曝光与焦点关系；精致 editorial 原作不会被统一做脏。 这不是换脸工具，也不承诺像素级复刻。它重建的是可观察的摄影方案：光源、机位、曝光、背景信息层级、人物事件和成像质感。结果仍受生成模型、参考图质量与人物授权影响。 署名与归档 默认不在图片中加入 或任何其他署名、水印。 只有用户明确要求并给出署名文字时，才把该文字写入 Prompt。 Eagle、个人知识库和其它本地 Skill 都不是使用本 Skill 的前提；Eagle 归档成功时会额外返回 Eagle ID，失败时仍保留完整的对话交付。 普通提示词 摄影方案复拍 文件结构 ：触发、授权、输出和跨环境边界。 ：提示词模板与摄影方案复拍工作流。 ：触发、皮肤反射和复拍回归案例。 ：公开发行与行为合同测试。 ：公开版本变化。 能力边界 只要 Prompt 时不会擅自生图。 明确要求生图但环境没有图片生成工具时，会交付完整 Prompt 并说明未执行生成，不伪造结果。 Eagle、个人知识库和其他本地 Skill 都不是运行前提。 使用参考图和人物图前，请自行确认版权、肖像权、商标与平台规则。 完整规则见 [SKILL.md](SKILL.m
| Stars | 730 |
| Forks | 81 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 51.6607338183999/100 |
| Last Updated | 2026-08-26 |
| Created | 2026-07-29 |
| Platforms | python |
| Est. Tokens | ~4k |
These tools work well together with nuyoah-xiezhen-prompt for enhanced workflows:
Looking for a nuyoah-xiezhen-prompt alternative? If you're comparing nuyoah-xiezhen-prompt with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
General-purpose Playwright automation for coding agents
🎭 AI 写小说：从零生成 10-50 章完整中文小说，三层问答 · 创作记忆 · 悬念钩子 · 自动校验，长篇网文连载皆宜｜开源免费，适配主流 coding agent｜AI novel writing skill
This repository contains a collection of Agent Skills developed by GudaStudio, enabling seamless collaboration
A collection of standardized Agent Skills to teach GitHub Copilot, Claude, Gemini and Cursor about modern Andr
A collection of Agent skills and Claude Code plugins for HashiCorp products.
Claude Code Skill Factory — A powerful open-source toolkit for building and deploying production-ready Claude
Explore other popular agent tool tools:
nuyoah-xiezhen-prompt is 南鸢写真提示词 Agent Skill. It is categorized as a Agent Tool with 730 GitHub stars.
nuyoah-xiezhen-prompt is primarily written in Python.
You can find installation instructions and usage details in the nuyoah-xiezhen-prompt GitHub repository at github.com/nuyoah-ai-works/nuyoah-xiezhen-prompt. The project has 730 stars and 81 forks, indicating an active community.
nuyoah-xiezhen-prompt is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to nuyoah-xiezhen-prompt on Agent Skills Hub include playwright-skill, chinese-novelist-skill, skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: