paper-collage-ad-codex — security grade SAFE, quality 62/100

Security audit verdict: SAFE · quality 62/100

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 Jane-xiaoer · Codex Skill · ★ 385

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is paper-collage-ad-codex safe to install? View the security audit →

About paper-collage-ad-codex

Paper Collage Ad for Codex 一个适合在 OpenAI Codex 中运行的完整剪纸 / 编辑拼贴广告制作 skill。从创意、脚本、分镜和关键帧开始,继续完成动画、旁白、音乐、音效、合成与 MP4 质检。 Codex edition: Skill name: Primary runtime: OpenAI Codex desktop / CLI 安装到 Codex 全局安装,供当前用户的所有 Codex 项目使用: 项目内安装,只供当前项目使用: 重新启动 Codex 或开启新任务后,可以直接说: Codex 会读取根目录的 ,并按需调用 、 和 。 从安装到最终 MP4 的完整中文操作步骤见:WORKFLOW.zh-CN.md。 能完成什么 从产品资料提炼一个贯穿全片的视觉隐喻。 输出等待确认的脚本、对白和时间码分镜。 使用真实品牌资产生成风格锁定的剪纸关键帧。 在关键帧与最终动画之间,用 ChatCut 的 Gemini Omni 快速预演动作或局部修改已有短片。 使用 Seedance、HyperFrames、分层 PNG 或 FFmpeg 完成动画。 使用普通 TTS,或在本地通过 IndexTTS-2 MLX 克隆已获授权的声音。 添加音乐、纸张拟音和动作音效,最后输出经过流级验证的 H.264/AAC MP4。 基础依赖 macOS: 只使用静态关键帧、分层动画和最终合成时,不需要任何 API Key。Gemini Omni 通过可选的 ChatCut 插件调用,需要登录并拥有视频生成额度;Seedance、即梦、MiniMax 和 ElevenLabs 也分别需要使用者自己的服务权限。 Gemini Omni 中间环节 这一版加入 Gemini Omni(ChatCut 工具参数 ,后台模型 )。它不是最终精修模型,主要用于: 用已确认关键帧做 3–10 秒动作预演,先判断节奏和笑点是否成立。 用 对现有短片做一次局部修改,未提及的内容尽量保持不变。 Omni 固定输出 720p/24fps,只支持 16:9 或 9:16,也不适合生成精确中文文字。最终需要

Quick Facts

Stars385
Forks51
LanguageJavaScript
CategoryCodex Skill
LicenseMIT
Quality Score62.2809391813871/100
Open Issues1
Last Updated2026-08-01
Created2026-07-10
Platformscodex, node
Est. Tokens~5k

Compatible Skills

These tools work well together with paper-collage-ad-codex for enhanced workflows:

paper-collage-ad-codex alternative? Top 6 similar tools

Looking for a paper-collage-ad-codex alternative? If you're comparing paper-collage-ad-codex with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • nano-banana-pro-prompts-recommend-skill by YouMind-OpenLab · ⭐ 1.9k

    AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart sear

  • skillkit by rohitg00 · ⭐ 1.5k

    Supercharge AI coding agents with portable skills. Install, translate & share skills across Claude Code, Curso

  • Skills-Manager by jiweiyeah · ⭐ 991

    Free, open-source desktop manager for AI Agent Skills. Write a skill once, sync it to 32 AI coding tools (Clau

  • ai-maestro by 23blocks-OS · ⭐ 789

    AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agen

  • upskill by huggingface · ⭐ 747

    Generate and evaluate agent skills for code agents like Claude Code, Open Code, OpenAI Codex

  • skills by wlzh · ⭐ 607

    开源了Codex Skills等集合,大部分是自己实际需要搞得,需要的自取。欢迎star

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is paper-collage-ad-codex?

paper-collage-ad-codex is Codex skill for complete paper-cut collage ad production, local IndexTTS-2 voice cloning, animation, audio and MP4 QC. It is categorized as a Codex Skill with 385 GitHub stars.

What programming language is paper-collage-ad-codex written in?

paper-collage-ad-codex is primarily written in JavaScript.

How do I install or use paper-collage-ad-codex?

You can find installation instructions and usage details in the paper-collage-ad-codex GitHub repository at github.com/Jane-xiaoer/paper-collage-ad-codex. The project has 385 stars and 51 forks, indicating an active community.

What license does paper-collage-ad-codex use?

paper-collage-ad-codex is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to paper-collage-ad-codex?

The top alternatives to paper-collage-ad-codex on Agent Skills Hub include nano-banana-pro-prompts-recommend-skill, skillkit, Skills-Manager. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Codex Skill tools