Agentchengfeng/chengfeng-videocut-skills

用 Claude Code Skills 做的视频剪辑 Agent

What it solves

This project provides the installation entry points and specific skill sets for the chengfeng-videocut ecosystem, enabling AI agents to perform video editing tasks. It bridges the gap between an AI agent's reasoning and the actual execution of video editing operations through a set of defined plugins and tools.

How it works

It functions as a Codex Plugin that provides agents with methods and confirmation tools. These skills are categorized into several entry points, including talking-head video cutting, subtitles, visuals, exporting, and a specialized "workbench operation" skill. The workbench skill allows agents to locate phrases, overwrite or remove visuals, delete segments, split/crop/move clips, and adapt the canvas.

To function, the plugin requires a a compatible Runtime (the software engine that executes the operations) and the Codex CLI. The installation process uses a Node.js-based installer to register the plugin with the host environment.

Who it’s for

This project is for developers and users of the chengfeng-videocut system who want to integrate AI-driven video editing capabilities into their AI agents via the Codex plugin system.

Highlights

  • Agent-Centric Video Editing: Provides a dedicated set of skills for AI agents to manipulate video timelines and assets.
  • Workbench Integration: Includes advanced operations like segment splitting, cropping, and canvas adaptation.
  • Strict Versioning: Uses fixed commit SHAs and snapshots to ensure installation stability and prevent "version drift."
  • Modular Architecture: Separates the plugin (the agent's interface), the runtime (the execution engine), and the independent skills (specialized animation or adaptation tools).

Related

  • Project
    DannyMac180/skills

    A GitHub repo offering plug‑in style “skills” that extend Claude Code or any skill‑aware AI agent with ready‑made ModSmith mods, multi‑agent workflow orchestration, task relaying, prompt‑ambition boosting, and artifact explanation with spaced‑repetition learning.

  • Project
    veedstudio/open-edit

    OpenEdit is an open‑source CLI skill that lets AI coding agents (Claude Code, Codex, Gemini) edit videos by describing the desired changes. It handles transcription, layout, rendering in a headless browser and outputs an MP4, supporting subtitles, cuts, motion graphics and AI‑generated media.

  • Project
    awslabs/agent-plugins

    A collection of plugins for AI coding agents that provide specialized skills, MCP servers, and workflows to help developers architect, deploy, and operate on AWS.

  • Project
    databricks/databricks-agent-skills

    A collection of skills and plugins that provide AI coding agents with specialized knowledge and guidance for building and managing resources on the Databricks platform.

  • Project
    trailofbits/skills

    A marketplace of specialized plugins for AI coding assistants that adds expert-level security auditing, vulnerability research, and advanced development workflows to agents like Claude Code.