Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/nuva-lab-validate-media
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
validate-media- Description
- None
- License
- Apache-2.0
- Instructions
- 63 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- missing YAML frontmatter
- name: missing
- description: missing
Files (2)
- SKILL.md
- validate.py
SKILL.md (first lines)
# Validate Media Skill
Pre-flight media validation and diagnostics using ffprobe.
## Purpose
Check video/audio files for common issues before rendering:
- Duration mismatches between video and audio tracks
- Missing audio tracks
- Codec compatibility
- Volume levels
- Potential freeze points
## Usage
```bash
python skills/validate-media/validate.py <video_file> [--verbose]
```
## Output
JSON report with issues and recommendations:
```json
{
"file": "video.mp4",
"video_duration": 35.14,
"audio_duration": 37.07,
"has_audio": true,
"video_codec": "h264",
"audio_codec": "aac",
"resolution": [1920, 1080],
"fps": 30,
"issues": [
"Video track shorter than audio by 1.93s"
],
"recommendations": [
"Use loop=true in Remotion to handle shorter video"
]
}
```
## Integration
Call before `make-video` to catch issues early:
```python
from skills.validate_media.validate import validate_media
result = validate_media("video.mp4")
if result["issues"]:
print("Warning:", result["issues"])
```
## Common Issues Detected
| Issue | Cause | Fix |
|-------|-------|-----|
| Video shorter than audio | Mismatched source files | Loop video or trim audio |
| No audio track | Video-only file | Add audio track or use silent |
| Low audio volume | Quiet recording | Normalize audio |
| Unsupported codec | HEVC/ProRes | Convert to H.264 |From Nuva-Lab/vibecut, Apache-2.0.
More from Nuva-Lab/vibecut
- 0.467score
align-captions
Nuva-Lab
Generate karaoke-style word-level timestamps by aligning script text to audio using Qwen3-ForcedAligner + jieba for Chinese word segmentation.
SkillDFreshness: D★ 6Claude Code +9 - 0.461score
separate-audio
Nuva-Lab
Text-guided audio source separation using SAM-Audio via mlx-audio
SkillDFreshness: D★ 6Claude Code +9 - 0.461score
extract-clip
Nuva-Lab
Extract a video segment using FFmpeg with precise start/end times
SkillDFreshness: D★ 6Claude Code +9 - 0.461score
find-golden-segments
Nuva-Lab
Find naturally clean, coherent video segments worth keeping (selection over repair)
SkillDFreshness: D★ 6Claude Code +9 - 0.461score
analyze-video
Nuva-Lab
Analyze raw video content using Gemini to identify speakers, topics, key moments, and potential clip opportunities
SkillDFreshness: D★ 6Claude Code +9 - 0.461score
transcribe-clip
Nuva-Lab
Transcribe a video clip using Gemini to get timestamped segments for captions
SkillDFreshness: D★ 6Claude Code +9 - 0.461score
audio-process
Nuva-Lab
Audio processing utilities - noise reduction, normalization, enhancement
SkillDFreshness: D★ 6Claude Code +9 - 0.461score
transcribe-audio
Nuva-Lab
ASR with ~30ms timestamp precision using Qwen3-ASR + ForcedAligner
SkillDFreshness: D★ 6Claude Code +9 - 0.458score
write-script
Nuva-Lab
Generate voiceover scripts in Joyce's style for video clips
SkillDFreshness: D★ 6Claude Code +9 - 0.458score
voice-clone
Nuva-Lab
Clone a voice using qwen3-tts and generate speech from text
SkillDFreshness: D★ 6Claude Code +9 - 0.246score
inspect-video
Nuva-Lab
No description from the publisher yet.
SkillDFreshness: D★ 6Claude Code +9 - 0.246score
make-video
Nuva-Lab
No description from the publisher yet.
SkillDFreshness: D★ 6Claude Code +9
Signals
- Stars
- 6
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Jan 30, 2026 (9 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/Nuva-Lab/vibecut
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Nuva-Lab
- 0.467score
align-captions
Nuva-Lab
Generate karaoke-style word-level timestamps by aligning script text to audio using Qwen3-ForcedAligner + jieba for Chinese word segmentation.
SkillDFreshness: D★ 6Claude Code +9 - 0.461score
audio-process
Nuva-Lab
Audio processing utilities - noise reduction, normalization, enhancement
SkillDFreshness: D★ 6Claude Code +9 - 0.461score
extract-clip
Nuva-Lab
Extract a video segment using FFmpeg with precise start/end times
SkillDFreshness: D★ 6Claude Code +9 - 0.461score
find-golden-segments
Nuva-Lab
Find naturally clean, coherent video segments worth keeping (selection over repair)
SkillDFreshness: D★ 6Claude Code +9 - 0.461score
transcribe-audio
Nuva-Lab
ASR with ~30ms timestamp precision using Qwen3-ASR + ForcedAligner
SkillDFreshness: D★ 6Claude Code +9 - 0.461score
transcribe-clip
Nuva-Lab
Transcribe a video clip using Gemini to get timestamped segments for captions
SkillDFreshness: D★ 6Claude Code +9
Cite this page
validate-media skill. Agent Mart. https://agentmart.dev/skills/nuva-lab-validate-media (last updated 2026-10-24)