Borrowing it
Nothing to install: this file belongs to nguyenph88/Media-Editor-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nguyenph88/Media-Editor-MCP/main/.claude/skills/pp-split-scenes/SKILL.mdgit clone --depth 1 https://github.com/nguyenph88/Media-Editor-MCPWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nguyenph88/media-editor-mcp/pp-split-scenes)<a href="https://agentmods.dev/skills/nguyenph88/media-editor-mcp/pp-split-scenes"><img src="https://agentmods.dev/badge/skills/nguyenph88/media-editor-mcp/pp-split-scenes/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nguyenph88/media-editor-mcp/pp-split-scenes"><img src="https://agentmods.dev/badge/skills/nguyenph88/media-editor-mcp/pp-split-scenes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00087 | $0.00665 |
| Opus 5 | $0.00044 | $0.00332 |
| Sonnet 5 | $0.00017 | $0.00133 |
| Haiku 4.5 | $0.00009 | $0.00067 |
Grade A, and why
pp-split-scenes scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Split a video into per-scene clips
Detect scene/shot boundaries in a video and export each scene as its own file on disk. Pure ffmpeg + PySceneDetect — does NOT need Premiere or the MCP plugin. Good for un-stitching an old montage back into its component shots.
Wraps the standalone script packages/media-analysis/split_scenes.py.
Inputs:
<video file>(required) — absolute path to the source video.[out folder]— default<input>_scenesnext to the source.[threshold]— detector sensitivity; LOWER = more cuts (default 27; try ~15-18 for soft dissolves).[min-len seconds]— minimum scene length, avoids tiny fragments (default 1.0).
How to run
All commands run from packages/media-analysis/ using its venv python:
./.venv/Scripts/python.exe split_scenes.py "<path>" [flags]
Flags: --out DIR, --threshold N, --min-len SEC, --detector content|adaptive (adaptive = fewer false splits on shaky/fast footage), --copy (fast lossless keyframe-snapped cuts vs default frame-accurate re-encode), --list (detect only, no files).
Workflow
- Preview first — run with
--list. It prints each scene's start/end/duration as JSON (no files written). Show the user the count + durations.- Suspiciously uniform short scenes that aren't real cuts → raise
--threshold. - Real cuts missed → lower
--threshold. - Too many tiny fragments → raise
--min-len.
- Suspiciously uniform short scenes that aren't real cuts → raise
- Confirm the boundaries look right, tuning flags as needed (this is the cheap step — detection, not export).
- Split — re-run without
--list. Each scene →<stem>_scene_NNN.mp4, plus ascenes.jsonmanifest in the out folder.
Notes & gotchas
- Re-encode (default) = frame-accurate H.264/AAC, larger total size.
--copy= fast/lossless but cuts snap to nearest keyframe (a few frames off). - The script already trims a half-frame off each scene's end so the next shot's first frame doesn't bleed onto the previous clip's tail. Don't re-add that.
- Single continuous shot (no cuts) → one output file (the whole video), never an error.
- Source media for test runs should be <20MB (user preference); real jobs any size.
- Re-running overwrites files of the same name in the out folder.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 41 lines · 87 tokens per session scan A e2dbb24927ba
pp-split-scenes is a skill published in the GitHub repository nguyenph88/Media-Editor-MCP (0 stars, last pushed 3mo ago), licensed MIT. It adds 87 tokens to every session and 665 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.