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 wyuzhi · Agent Tool · ★ 93
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is qisi-video-remix safe to install? View the security audit →
qisi-video-remix 给 Agent 一个参考视频，得到新故事、完整剧本、分镜表和可复制的分段视频提示词。 作者：qisi · MIT License · 完整输出示例 一个面向 AI Agent 的视频策划 skill。给它参考视频，它会借鉴原片的叙事方法，创作新故事，并直接展示 剧本 → 人物与场景 → 分镜 → 生成分段 → 可复制提示词。 默认做创意改编。无需选择模式，无需阅读 JSON，也无需接入特定 APP 后端。 最终输出 结果直接在对话中呈现；有文件写入能力时，同时保存为 。每段提示词展开所需人物外貌、造型、场景、动作和对白，可以独立复制使用。 看看交付效果 完整示例：便利店里的一场误会 包含 30 秒剧本、6 个镜头、2 个 15 秒生成段和各段完整提示词。示例的参考材料为虚构文字梗概，用来展示交付结构，不代表完成过真实视频分析或生成测试。 安装 Codex 用户可以直接克隆到技能目录。以下命令适用于尚未安装的情况： 下载并解压本仓库，将整个 文件夹放入 Agent 支持的技能目录。确保 直接位于该文件夹下；GitHub 下载的文件夹若带有 后缀，先改为 。 Codex 使用默认本地技能目录时，安装位置为： 若设置了 ，使用其下的 目录。其他支持 的 Agent 按各自的技能安装方式加载完整文件夹，尚未逐一验证各平台兼容性； 是可选的 Codex 展示信息。 使用 附上视频，然后发送： 也可以提供
| Stars | 93 |
| Forks | 13 |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 55.4993121998383/100 |
| Last Updated | 2026-09-11 |
| Created | 2026-09-11 |
| Est. Tokens | ~3k |
Looking for a qisi-video-remix alternative? If you're comparing qisi-video-remix with other agent tool tools, these 1 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults
Explore other popular agent tool tools:
qisi-video-remix is 视频创意改编 Agent Skill：参考视频 → 剧本 → 分镜 → 分段生成提示词。By qisi.. It is categorized as a Agent Tool with 93 GitHub stars.
You can find installation instructions and usage details in the qisi-video-remix GitHub repository at github.com/wyuzhi/qisi-video-remix. The project has 93 stars and 13 forks, indicating an active community.
qisi-video-remix is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to qisi-video-remix on Agent Skills Hub include tutor-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: