video-recap-skills — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by worldwonderer · Claude Skill · ★ 470

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

🔒 Is video-recap-skills safe to install? View the security audit →

About video-recap-skills

video-recap-skills 中文 · English 把任何视频做成中文解说 recap——在 Claude Code 里一句话搞定。 本地只要 和一个小米 MiMo 的 API Key,不要 GPU、不用下载模型。 演示 https://github.com/user-attachments/assets/92698ec6-0d23-4f9f-8825-c3684ef57aff 成片之外,还能一键导出剪映草稿接着手动精修——原片片段、解说、BGM、字幕各成一轨: 这是什么 一个 Claude Code 插件:五个小而独立的 skill 加一个编排器,各管一段,只靠 里的 JSON/MP4 传结果。确定的活儿(剪辑、配音、混音)交给脚本,解说词交给 Agent 写。 为什么用它 一个 key 跑全程。 ASR、VLM、TTS 全走小米 MiMo,本地只装 。 先调研再分析。 先把剧情人物查清楚写进 。 原声不丢,动态混音。 解说压低原声后混

ai-agentasrclaude-codeclaude-code-pluginclaude-skillsffmpegllmmimottsvideo-clipping

Quick Facts

Stars470
Forks86
LanguagePython
CategoryClaude Skill
LicenseMIT
Quality Score62.9633693243167/100
Last Updated2026-08-24
Created2026-05-02
Platformsclaude-code, cli, python
Est. Tokens~14k

Compatible Skills

These tools work well together with video-recap-skills for enhanced workflows:

  • mcp-video — semantic(0.35)+complementary+rare_topics+same_lang+similar_pop+shared_platform (67%)
  • OpenMontage — semantic(0.43)+complementary+rare_topics+same_lang+shared_platform (64%)
  • skills — semantic(0.37)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)
  • VideoGraphAI — semantic(0.36)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)

video-recap-skills alternative? Top 6 similar tools

Looking for a video-recap-skills alternative? If you're comparing video-recap-skills 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.

  • video-recap-skills by zenstory-ai · ⭐ 529

    Claude Code / Codex skills that turn a video into a Chinese narration recap (视频解说): scene detection, ASR, VLM,

  • adversarial-spec by zscole · ⭐ 557

    A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until a

  • narrator-ai-cli by NarratorAI-Studio · ⭐ 115

    AI 解说大师 — CLI 客户端;用于终端调用视频解说生成 API

  • skills by wondelai · ⭐ 2.1k

    Wondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 50 skills + 12 gu

  • OpenGUI by Core-Mate · ⭐ 1.8k

    OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps th

  • bailing by wwbin2017 · ⭐ 1.8k

    百聆 是一个类似GPT-4o的语音对话机器人,通过ASR+LLM+TTS实现,集成DeepSeek R1等优秀大模型,接入openClaw,真正的个人语音助手,时延低至800ms,Mac等低配置也可运行,支持打断

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is video-recap-skills?

video-recap-skills is Clip any video into a narration recap with claude code skill|用 claude code skill 把任何视频剪辑成中文解说视频,支持剪映导出. It is categorized as a Claude Skill with 470 GitHub stars.

What programming language is video-recap-skills written in?

video-recap-skills is primarily written in Python. It covers topics such as ai-agent, asr, claude-code.

How do I install or use video-recap-skills?

You can find installation instructions and usage details in the video-recap-skills GitHub repository at github.com/worldwonderer/video-recap-skills. The project has 470 stars and 86 forks, indicating an active community.

What license does video-recap-skills use?

video-recap-skills is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to video-recap-skills?

The top alternatives to video-recap-skills on Agent Skills Hub include video-recap-skills, adversarial-spec, narrator-ai-cli. 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 Claude Skill tools