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 op7418 · Claude Skill · ★ 451
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is guizang-yingzao-skill safe to install? View the security audit →
Yingzao · 营造 把你拍下的建筑、街巷、店铺、器物与地方食物，转成真正经过艺术指导的编辑海报——不是给照片套滤镜，也不是把标题贴在空白处。 Yingzao 会先读照片的构图与身份，再选择一张兼容的主导参考，设计中文展示字与图文空间关系，最后把原图、参考与稀疏排版垫图一起交给图像模型完成整体重绘。主体处理、主动色场、地域材质和文字遮挡发生在同一个视觉世界里。 30 秒开始 安装后，在支持 Skills 与图像生成的 Agent 中直接说： 也可以把下面这段话发给你的 Agent，让它自行完成安装： 它会做什么 识别照片是正立面、仰视、对角、框景、局部构件还是环境叙事，并只修复一个真正影响画面的构图问题。 保护屋坡、飞檐、匾额、轮廓、不对称等身份锚点，不把真实建筑“优化”成另一栋楼。 在看参考图之前先提出主体、背景、图文互动与排版动作四域命题，避免参考越多、结果越平庸。 从内置 Recipe 与真实参考图中选择兼容方向，不把几十条风格词机械串进提示词。 设计展示字的宽窄、重心、笔画对比、收笔、字腔、节奏与表面媒介；小字可使用另一常规字族建立层级。 把主体语义抠取、移位、分区上材质，并让真实轮廓与标题、色形发生遮挡、共边或负形咬合。 多图“合一”时提取各图主体，在共享透视、光向、接触阴影和边缘语言中重建一个场景；只有明确要求组照时才保留照片矩形。 海报完成后，可按你的选择继续制作一张 3×3 视频分镜图和可直接交给视频模型的提示词。 使用示例 如果地点、殿名或历史信息不确定，可以先让 Agent 检索；Yingzao 只把已核实、照片可见或你确认过的信息写进海报。 工作方式 text 照片预检与事实边界 ↓ 参考无关的四域创意命题 ↓ Recipe 检索与一张主导参考 ↓ 设计语义编译 + 中文字形简报 + 带区域标记的稀疏排版垫图 ↓ 编译
| Stars | 451 |
| Forks | 37 |
| Language | Python |
| Category | Claude Skill |
| Quality Score | 60.6216348328792/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-03 |
| Created | 2026-09-02 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~14k |
Looking for a guizang-yingzao-skill alternative? If you're comparing guizang-yingzao-skill with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
One-ink editorial print image skill — warm paper, halftone photography, active negative space, and restrained
Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W
Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software
Use your ChatGPT subscription to generate images from the command line — no OPENAI_API_KEY, no gateway, no dae
开源中文配图技能 + IP 角色库:用「挑认知锚点→现编隐喻→反PPT自检」为中文深度文生成固定角色出演的正文配图
World-class creative director in a skill. Methodology-driven ideation (SIT, TRIZ, Lateral Thinking, bisociatio
Explore other popular claude skill tools:
guizang-yingzao-skill is 🏯 Claude Code / Codex skill — transform Chinese architecture, cultural places & travel photos into art-directed editorial posters with GPT Image. 中国古建筑与在地文化照片 → 艺术指导海报. It is categorized as a Claude Skill with 451 GitHub stars.
guizang-yingzao-skill is primarily written in Python. It covers topics such as agent-skill, ai-agent, anthropic.
You can find installation instructions and usage details in the guizang-yingzao-skill GitHub repository at github.com/op7418/guizang-yingzao-skill. The project has 451 stars and 37 forks, indicating an active community.
The top alternatives to guizang-yingzao-skill on Agent Skills Hub include mono-color-skill, compose-skill, pilot-shell. 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: