# Gameplay Clip Extractor

> Finds highlight moments in long gameplay recordings (BGMI, FIFA, Valorant, COD) using audio peak detection, optional scoreboard OCR, and pacing heuristics. Outputs timestamps + suggested clip ranges. Trigger when user has raw gameplay footage and wants to extract highlights, kill clips, goals, or shareable moments.

- Skill: `rahulcommercial/gameplay-clip-extractor` (Agent Skill)
- Install (CLI): `npx skillmds@latest add rahulcommercial/gameplay-clip-extractor`
- Raw SKILL.md: https://api.skillmd.com/api/skills/rahulcommercial/gameplay-clip-extractor/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: rahulcommercial (https://skillmd.com/u/rahulcommercial)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/rahulcommercial/gameplay-clip-extractor

---


# Gameplay Clip Extractor

Reduce a 1-hour gameplay capture to a list of 10-second clips worth posting.

## When to use

- User has raw `.mp4`/`.mov` gameplay footage (their own, no piracy).
- User wants timestamps for highlights without scrubbing manually.
- User wants the actual clipped files written to disk.

## Detection signals (combine, don't pick one)

### 1. Audio peak detection (cheapest, works everywhere)
Gunfire, goal whistles, killstreak voice lines, crowd reactions — all show up as audio amplitude spikes.

```bash
ffmpeg -i raw.mp4 -af "silencedetect=noise=-30dB:d=0.5" -f null - 2>&1 \
  | grep silence_end
```
Use the *inverse* — long non-silent stretches with sudden RMS jumps are candidates.

Python (cleaner):
```python
import librosa, numpy as np
y, sr = librosa.load("raw.mp4", sr=22050, mono=True)
rms = librosa.feature.rms(y=y, frame_length=2048, hop_length=512)[0]
peaks = np.where(rms > rms.mean() + 2 * rms.std())[0]
peak_times = librosa.frames_to_time(peaks, sr=sr, hop_length=512)
```

### 2. Scoreboard / kill-feed OCR (game-specific, higher accuracy)
- BGMI / COD: top-right kill feed → run Tesseract on that ROI every 1s.
- FIFA: scoreboard score-change → diff frames at fixed coords.
- Cache last value; emit event only on change.

### 3. Pacing heuristic
Cluster nearby peaks (within 3s) into single moments. A real highlight is usually 1 spike, not a noise burst.

## Output

```json
[
  {"start": 142.3, "end": 152.8, "label": "kill burst (3 audio peaks)", "score": 0.82},
  {"start": 384.1, "end": 394.6, "label": "score change 1→2", "score": 0.95}
]
```

Then clip with FFmpeg:
```bash
ffmpeg -ss 142.3 -i raw.mp4 -t 10.5 -c copy clips/clip_001.mp4
```

## Heuristics for "is this postable?"

- ≥ 2 audio peaks in a 10s window
- Clip ends on a *resolved* moment (kill confirmed, goal scored), not mid-action
- No long static frames (loading, respawn screen)

## What NOT to do

- Don't auto-publish. Always present clips for human review.
- Don't OCR the entire frame — that's slow and noisy. Define ROIs per game.
- Don't process clips you don't own the rights to.