luoluoluo22/jianying-editor-skill

Skill for Agent automating JianYing (CapCut Chinese version) video editing.

What it solves

It automates the tedious process of video editing in Jianying (the Chinese version of CapCut). Instead of manually dragging clips and aligning audio, users can use natural language to instruct an AI to handle the entire pipeline from scriptwriting and voiceover to subtitle generation, music selection, and final export.

How it works

The project acts as a "skill" for AI editors (like Cursor, Trae, or Claude Code). It generates and modifies the draft_info.json files that Jianying uses to define its timeline. It can import media, synthesize AI voiceovers, align subtitles, and apply effects by searching the software's internal library. On Windows, it uses UI Automation to trigger the final MP4 export, while on macOS, it prepares the draft for the user to export manually.

Who it’s for

Content creators, vloggers, and tutorial makers who want to speed up their editing workflow by using AI to build their timelines automatically.

Highlights

  • End-to-End Automation: Handles script, voiceover, subtitles, music, and effects in one flow.
  • Web-to-Video: Converts HTML/JS/Canvas animations into video clips via Playwright recording.
  • Smart Zoom: Automatically adds zoom-ins and red circles to mouse clicks in screen recordings for better tutorials.
  • Semantic Matching: Analyzes audio and subtitles to automatically pick the most relevant footage from a library.
  • Cross-Platform Support: Works on Windows (full automation) and macOS (draft generation).

Related

  • Project
    Agentchengfeng/chengfeng-videocut-skills

    A Codex plugin suite that automates talking-head video editing by coordinating AI-driven cutting, subtitle management, and exporting via a dedicated cross-platform Runtime.

  • Project
    ModelTC/LightX2V

    LightX2V is an open‑source inference framework for fast image and video generation (T2V, I2V, T2I, I2I, T2AV, etc.). It supports many state‑of‑the‑art models (MiniMax‑H3, Wan, HunyuanVideo, Qwen‑Image, etc.) and provides speed‑up techniques such as 4‑step distilled LoRAs, FP8/NVFP4 quantization, tensor/sequence parallelism, and disaggregated deployment on a wide range of hardware. Benchmarks show up to 3.9× faster inference than competing frameworks on H100 GPUs. The project offers Docker images, pip install, Gradio/ComfyUI front‑ends, extensive docs, and an online demo.

  • Project
    fqscfqj/Y2A-Auto

    Y2A‑Auto is an open‑source, Docker‑ready pipeline that downloads YouTube videos, optionally runs Whisper/Voxtral ASR, translates and quality‑checks subtitles, generates titles/tags via OpenAI, encodes the video (CPU or GPU), and uploads it to AcFun and/or bilibili. It includes a Flask web UI, YouTube monitoring, CookieCloud sync, content‑moderation, and multi‑channel notification support, all configurable through a JSON file and protected by password/lockout features.

  • Project
    FireRedTeam/FireRed-OpenStoryline

    A conversational AI video creation tool that automates scriptwriting, media sourcing, and editing through natural language prompts.