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 LetMeHappyCode · Agent Tool · ★ 222
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is auto-video-agent safe to install? View the security audit →
auto-video-agent 把一段 SRT 字幕文案，自动流水线化生成成套「分镜插画提示词 → AI 生图 → 拼接成片」的视频，基于 Agent / Skill / Workflow 编排。 兼用进度 项目内的 Agent/Skill/Workflow 目前按 Claude Code 的约定格式编写。以下是在不同 Coding Harness 下的兼用情况： 理论上其他支持类似 Agent/Skill/Workflow 编排能力的 Harness 也可以直接复用或少量适配后使用，欢迎反馈实际兼用结果。 效果预览 https://github.com/user-attachments/assets/f6d6576f-8c11-4dfe-b1ec-59370cc17bea https://github.com/user-attachments/assets/88b1fbad-e34c-461d-b6bd-26dd3a6c8073 这是什么 给定一份 SRT 字幕文件，本项目会： 自动分镜：将整份字幕按语义切分成若干「镜头」（2-6 秒/镜），每个镜头带起止时间和台词文本 生成插画提示词：为每个镜头生成结构化的插画生成提示词（风格、主角、画面描述等），并自动做十项自检 调用文生图 API：接入火山方舟 Seedream 文生图/图生图接口，把提示词批量转成分镜插画 拼接成片：按分镜时间轴把所有插画拼接成一段无声视频 可视化管理：提供一个本地 Web 管理界面，浏览分镜库、预览/生成图片、编辑分镜数据 整条链路（含生图、拼接成片）都可以由 AI 自主调度完成：只需在 Claude Code 里给出 SRT 路径和画风要求，Claude 会自主派发 Agent（）+ 运行 Workflow（）完成分镜切分与提示词生成，再自主通过 Bash 调用 、 完成生图和拼接，不需要人工逐步执行脚本。手动执行脚本仅作为备选方式（用于单独重跑某一步或不想经由 AI 调度的场景）。AI 生成的正文内容全部由子智能体自己落盘，主会话只传递状态和路径，避免上下文被大量正文占满。 工作流程 mermaid flowchart LR A[SRT 字幕文件] -- B["srt-shot-segmenter分镜切分"] -- C[shots.json] C -- D["generate-illustration-promptsworkflow 并发生成提示词"] -- G[shot-NNNN.prompt.json] G -- H["AI 自主调用generateimages.py"] -- I[shot-NNNN.png] I -- J["AI 自主调用composevideo.py"] -- K[outpu
| Stars | 222 |
| Forks | 7 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 59.444403311968/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-21 |
| Created | 2026-09-07 |
| Platforms | python |
| Est. Tokens | ~14k |
These tools work well together with auto-video-agent for enhanced workflows:
Looking for a auto-video-agent alternative? If you're comparing auto-video-agent 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.
A collection of standardized Agent Skills to teach GitHub Copilot, Claude, Gemini and Cursor about modern Andr
Coding Agents skills for Synalinks OSS
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
Lightweight registry to discover, install, and manage all public Claude plugins and agent skills for your favo
A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults
Explore other popular agent tool tools:
auto-video-agent is 自动流水线化生成成套「分镜插画提示词 → AI 生图 → 拼接成片」的视频，基于 Agent / Skill / Workflow 编排。. It is categorized as a Agent Tool with 222 GitHub stars.
auto-video-agent is primarily written in Python.
You can find installation instructions and usage details in the auto-video-agent GitHub repository at github.com/LetMeHappyCode/auto-video-agent. The project has 222 stars and 7 forks, indicating an active community.
The top alternatives to auto-video-agent on Agent Skills Hub include awesome-android-agent-skills, synalinks-skills, agent-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: