Video Edit Planner

An agent skill that helps plan video edits through iterative dialogue — transcribe audio, extract key frames on demand, analyze visuals, and produce a structured edit plan.

Repository: https://git.nite07.com/nite/video-edit-planner-skill

Features

• Audio transcription — bundled funasr-script with Fun-ASR-Nano (default, high quality, Chinese-optimized) and SenseVoice (fast preview) models
• On-demand frame extraction — ffmpeg-based clip cutting (-c copy) + scene-change detection + uniform sampling, with hardware acceleration (CUDA/NVDEC preferred)
• Artifact indexing — JSON file tracks all transcriptions, clips, and frames with relative paths to avoid duplicate processing across sessions
• Vision analysis guidance — binary-search-style frame sampling strategy; works with any vision-capable model the agent's runtime provides
• Iterative edit plans — Markdown-table output (timecodes, segment descriptions, actions, transitions, notes) refined through follow-up questions
• Agent-agnostic — no platform-specific tool names; works with any agent framework (Hermes, Claude Code, Codex, etc.)

Quick Start

Prerequisites

Dependency	Install
ffmpeg + ffprobe	Linux: pacman -S ffmpeg / apt install ffmpeg; macOS: brew install ffmpeg; Windows: winget install Gyan.FFmpeg
uv	Linux: pacman -S uv; macOS: brew install uv; Windows: winget install astral-sh.uv; fallback: pip install uv
python3	Linux: pacman -S python; macOS: brew install python; Windows: winget install Python.Python.3

Install the skill

Option 1: npx skills add (recommended)

This skill is compatible with the open agent skills ecosystem. You can install it directly:

# Install globally (available across all projects)
npx skills add https://git.nite07.com/nite/video-edit-planner-skill.git -g -y

# Install to specific agents
npx skills add https://git.nite07.com/nite/video-edit-planner-skill.git -g -a claude-code -y

# List available skills without installing
npx skills add https://git.nite07.com/nite/video-edit-planner-skill.git --list

Supports 73+ agent frameworks including Claude Code, Codex, Cursor, OpenCode, and more.

Option 2: git clone (manual)

git clone https://git.nite07.com/nite/video-edit-planner-skill.git ~/.hermes/skills/media/video-edit-planner

For Hermes Agent specifically, clone into ~/.hermes/skills/media/. For other agents, follow their respective skills directory conventions.

Workflow

1. Check dependencies (ffmpeg, uv, python3)
2. Gather inputs (video path + audio track index)
3. Ask editing requirements
4. Transcribe audio (skip if cached in index)
5. Extract clips & frames on demand (agent decides when transcript is insufficient)
6. Analyze frames with vision model (binary-search-style sampling)
7. Produce Markdown-table edit plan + overall recommendation
8. Iterate — user asks follow-ups, plan is refined

Project Structure

video-edit-planner/
├── SKILL.md                          # Skill definition (workflow, guidance, pitfalls)
├── README.md                         # This file (English)
├── README.zh.md                      # 中文说明
├── scripts/
│   ├── transcription/                # Bundled funasr-script (self-contained uv project)
│   │   ├── pyproject.toml
│   │   ├── uv.lock
│   │   ├── funasr_common.py          # Shared: ffprobe, audio extraction, model runner
│   │   ├── funasr_nano.py            # Fun-ASR-Nano entry point (default, high quality)
│   │   ├── funasr_fast.py            # SenseVoice entry point (fast preview)
│   │   └── funasr_regular.py         # Paraformer entry point (comparison)
│   ├── frames/
│   │   └── extract_frames.py         # Clip extraction + frame sampling (ffmpeg wrapper)
│   └── index/
│       └── manage_index.py           # JSON index management (8 subcommands)
└── references/
    └── frame-extraction-guide.md     # Vision model token costs, resolution/batch guidance

Index File

All processing artifacts are tracked in a JSON file (<video_stem>.vedit.json) stored next to the video file:

• transcriptions — JSON path, track index, duration
• clips — start/end time, file path, extraction reason
• frames — timestamp, file path, scene score, extraction method

All paths are stored as relative paths (relative to the video directory), so moving the entire directory does not break references. The JSON file is human-readable and editable with any text editor.

License

MIT