基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/mediar-ai/skillhubz --skill anti-render命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Validate rights-aware AI-hybrid video-production metadata with SHAR Production's local read-only MCP tool.
Publish files, folders, and artifacts to the web. Static hosting for HTML sites, images, PDFs, reports, dashboards, and any file type. Use when asked to publish, host, upload, serve, or share work at a live URL. Also use to propose a rendered page when a report, comparison, chart, design document, or status page would work better than terminal text, but do not create or update a remote site until the user asks or agrees. Account publishing gives a permanent, private-by-default URL visible to org members; --anonymous gives a temporary public URL with no account. Use the valet CLI when available and its MCP server when the CLI cannot run. For deploying an AI agent rather than static files, use the `valet` skill instead.
Use when the user wants to manage Valet agents, channels, connectors, organizations, or environment variables (secrets and plain config) via the valet CLI. Handles creation, deployment, linking, teardown, and all multi-step workflows. Also use when asked to "create an agent", "deploy an agent", "design an agent", "build me an agent that...", "create a connector", "set up a webhook", or anything involving the Valet platform or any request to create and deploy AI agents. Also use when asked to "learn from this session", "capture this workflow", "save this as an agent", "make this repeatable", or when writing SOUL.md files.
| name | anti-render |
| description | 智能识别任何领域的"理想承诺 vs 残酷现实"对比需求，生成理想化渲染、现实主义真实面貌或对比图的三种视觉风格转换 |
用户上传图片后，识别其当前状态和期望转换方向：
破烂/不理想状态：
普通/正常状态：
对比模式：
中间派：
Anti-Render 的核心理念是**"理想承诺 vs 残酷现实"的视觉对比叙事**。通过并置(juxtaposition)手法，揭示任何领域中"承诺与交付之间巨大落差"的普遍困境：
识别特征：建筑外观、城市景观、室内空间、建筑效果图 资源文件：anti-render.architecture.json 核心表达：建筑师理想化渲染图到残酷现实的视觉坠落
识别特征：人像写真、Cosplay摄影、活动拍摄、自拍 资源文件：anti-render.person.json 核心表达：后期精修的完美人像到原片真实的视觉落差
识别特征：产品、食物、旅游、游戏、健身、办公、活动、教育、自然、社交媒体、科技等 资源文件：使用通用核心原则 应用原则：灵活应用到具体场景，基于5个核心对比场景进行创作
严格保留原图结构、元素与构图：
对比图排列规则：
对比图内容规则：
领域专属资源引用规则：
主动询问机制：