LeoYeAI/agent-master-skills / skills/auto-video-editing
video-editing
VerifiedAutomated video editing skill for talk/vlog/standup videos. Use when: cutting video, splitting video into sentences, merging video clips, extracting audio, transcribing speech, auto-editing oral presentation videos, combining selected sentence clips into a final video, generating video cover/thumbnail with title. Requires ffmpeg and whisper.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 6.8 KB |
| SKILL.md | skill md | 16.4 KB |
| _meta.json | config | 290 B |
| scripts/add_chapter_bar.py | script | 11.5 KB |
| scripts/burn_subtitles.py | script | 9.7 KB |
| scripts/extract_audio.py | script | 1.4 KB |
| scripts/extract_audio.sh | script | 742 B |
| scripts/generate_cover.py | script | 9.9 KB |
| scripts/merge_clips.py | script | 5.3 KB |
| scripts/split_video.py | script | 3.6 KB |
| scripts/transcribe.py | script | 5.4 KB |
| scripts/utils.py | script | 18.0 KB |
scripts/split_video.py
View on GitHub#!/usr/bin/env python3
"""
Split a video into individual sentence-level clips based on transcript timestamps.
Usage: python3 split_video.py <video_path> <transcript_json_path>
Output: <video_dir>/<video_name>_clips/clip_001.mp4, clip_002.mp4, ...
"""
import argparse
import json
import os
import subprocess
import sys
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from utils import detect_gpu, get_ffmpeg_encode_args
def main():
parser = argparse.ArgumentParser(description="Split video into sentence clips")
parser.add_argument("video_path", help="Path to the source video file")
parser.add_argument("transcript_path", help="Path to the transcript JSON file")
parser.add_argument("--padding", type=float, default=0.0,
help="Padding in seconds added before/after each clip (default: 0.0)")
args = parser.parse_args()
video_path = args.video_path
transcript_path = args.transcript_path
if not os.path.isfile(video_path):
print(f"Error: Video not found: {video_path}", file=sys.stderr)
sys.exit(1)
if not os.path.isfile(transcript_path):
print(f"Error: Transcript not found: {transcript_path}", file=sys.stderr)
sys.exit(1)
with open(transcript_path, "r", encoding="utf-8") as f:
transcript = json.load(f)
segments = transcript.get("segments", [])
if not segments:
print("Error: No segments found in transcript", file=sys.stderr)
sys.exit(1)
video_dir = os.path.dirname(os.path.abspath(video_path))
video_name = os.path.splitext(os.path.basename(video_path))[0]
clips_dir = os.path.join(video_dir, f"{video_name}_clips")
os.makedirs(clips_dir, exist_ok=True)
print(f"Splitting video into {len(segments)} clips...")
print(f"Output directory: {clips_dir}")
# Get video duration for boundary clamping
probe_cmd = [
"ffprobe", "-v", "error",
"-show_entries", "format=duration",
"-of", "default=noprint_wrappers=1:nokey=1",
video_path
]
try:
duration_str = subprocess.check_output(probe_cmd, text=True).strip()
video_duration = float(duration_str)
except (subprocess.CalledProcessError, ValueError):
video_duration = None
# Detect GPU and choose encoder
gpu_info = detect_gpu()
encode_args = get_ffmpeg_encode_args(gpu_info)
print(f"Video encoder: {encode_args[1]}")
for seg in segments:
seg_id = seg["id"]
start = max(0, seg["start"] - args.padding)
end = seg["end"] + args.padding
if video_duration is not None:
end = min(end, video_duration)
clip_duration = end - start
clip_filename = f"clip_{seg_id:03d}.mp4"
clip_path = os.path.join(clips_dir, clip_filename)
# Always re-encode for precise audio/video cuts (stream copy causes keyframe-aligned cuts
# which can include audio from adjacent segments)
cmd = [
"ffmpeg", "-y",
"-i", video_path,
"-ss", str(start),
"-t", str(clip_duration),
] + encode_args + [
"-c:a", "aac", "-b:a", "192k",
"-avoid_negative_ts", "make_zero",
clip_path
]
try:
subprocess.run(cmd, check=True, capture_output=True, text=True)
print(f" clip_{seg_id:03d}.mp4 [{start:.2f}s - {end:.2f}s] {seg['text']}")
except subprocess.CalledProcessError as e:
print(f" ERROR on clip_{seg_id:03d}: {e.stderr[:200]}", file=sys.stderr)
print(f"\nSplitting complete. {len(segments)} clips saved to: {clips_dir}")
if __name__ == "__main__":
main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |