Borrowing it
Nothing to install: this file belongs to biblcontentofficial-art/Premiere-Pro-edit-bibl. 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/biblcontentofficial-art/Premiere-Pro-edit-bibl/main/.claude/skills/cut-editing/SKILL.mdgit clone --depth 1 https://github.com/biblcontentofficial-art/Premiere-Pro-edit-biblWrote 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/biblcontentofficial-art/premiere-pro-edit-bibl/cut-editing)<a href="https://agentmods.dev/skills/biblcontentofficial-art/premiere-pro-edit-bibl/cut-editing"><img src="https://agentmods.dev/badge/skills/biblcontentofficial-art/premiere-pro-edit-bibl/cut-editing/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/biblcontentofficial-art/premiere-pro-edit-bibl/cut-editing"><img src="https://agentmods.dev/badge/skills/biblcontentofficial-art/premiere-pro-edit-bibl/cut-editing.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 | $0.00143 | $0.01436 |
| Opus 5 | $0.00072 | $0.00718 |
| Sonnet 5 | $0.00029 | $0.00287 |
| Haiku 4.5 | $0.00014 | $0.00144 |
Grade A, and why
cut-editing 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 12d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
컷편집 실행
engine/auto_cut.py 통합 엔진을 운용해 러프컷을 만든다. 엔진이 무거운 작업(무음감지·전사·말더듬/중복·NG 제거·숨소리 축소·음성보정·자막)을 결정적으로 처리하므로, 올바른 설정으로 실행하고 결과를 검증하는 게 핵심.
전문 편집자 기준 기본 동작: 무음 제거(끝음 보존) · 추임새 보존 · 말더듬/중복 제거 · NG(재촬영) 컷 제거(재촬영 신호어+재시도가 확인될 때만, 오탐 방지) · 숨소리 축소 · 음성보정(de-esser + 노이즈플로어 자동측정 후 조건부 노이즈제거 + 압축 + -14 LUFS).
0단계: 프리셋 자동 추천 (먼저)
어떤 프리셋을 쓸지 모르면 먼저 영상을 분석한다:
python3 engine/analyze_video.py "원본영상.mp4"
길이·라우드니스·무음 비율을 측정해 보수/표준/공격을 추천하고 config 값까지 제안한다. 추천을 그대로 따르거나, 기획자(20_plan.md)가 정한 프리셋이 있으면 그것을 우선한다.
실행
# 프로젝트 루트에서 실행 (프리셋은 위 추천 또는 기획자 지정)
python3 engine/auto_cut.py "원본영상.mp4" --preset 표준
- 73분 영상 기준 첫 실행 ~5분(전사 포함). 전사 캐시(
_words.json) 있으면 ~2분. - 무거우니 백그라운드로 실행하고 완료를 기다린다.
프리셋 선택 기준 (2026-06 정책: 추임새는 기본 보존, 숨소리만 축소)
| 프리셋 | 언제 | 효과 |
|---|---|---|
| 보수 | 자연스러움 최우선, 잔잔한 인터뷰 | 무음도 최소한만. 추임새 살림 |
| 표준 | 대부분의 토크/라이브 (기본) | 무음+숨소리+더듬 정리, 추임새(아·어·음·뭐) 살림 ( |
| 공격 | 최대한 타이트, 군더더기 많은 영상 | 추임새·망설임까지 전부 제거(그래서·이제·근데까지) |
세부 조정은 프로젝트 루트 config.json(config.json.example 참고)으로. 모델·임계값·필러목록 override.
산출물 (output/)
<base>_cut.xml— 프리미어 '불러오기' 하면 편집 가능한 시퀀스<base>_cut_audio.wav— 정리된 -14 LUFS 오디오 (XML이 자동 연결)<base>_cut.srt— 컷 정렬 자막 초안<base>_cut_report.txt— 잘린 내용 전체(타임코드별)<base>_words.json— 단어 단위 전사(리서처·자막이 재사용)
제1원칙: 자연스러움 > 최대 제거
추임새(아·어·음·뭐)는 말의 호흡이라 기본 보존한다(비블 확정 — 다 자르면 AI가 읽는 것처럼 됨). 대신 숨소리(노이즈성 들숨/날숨)만 무음처럼 줄인다. 잘라낸 뒤 전체 맥락에서 부자연스러우면 그 컷은 실패. 제거율·개수만 보지 말고, 이어 봤을 때 뚝뚝 끊기지/숨 가쁘지/리듬 깨지지 않는지 본다.
검증 (실행 후 필수)
- 자연스러움 (최우선) —
_cut_report.txt의 '자연스러움 주의(컷 촘촘)' 목록 확인. 컷이 몰린 구간은 부자연 위험 → 디렉터에 보고하거나 한 단계 보수 프리셋 재실행. - 제거율 — "총 제거 %" 확인. 표준 3~10% 정상(추임새 살리므로 낮음), 12% 초과면 과제거 의심. 공격은 13~19% 정상.
- 과제거 점검 —
_cut_report.txt에서 의미 있는 단어(접속사·핵심어)가 잘렸는지. 잘렸으면 보수적 프리셋 재실행. - 프레임 무결성 — XML의 갭/겹침이 0인지(엔진이 '검증' 항목에 자동 표시).
왜 이렇게 하는가
- 엔진 실행은 결정적이라 매번 같은 결과 → 신뢰 가능. 하지만 영상마다 발화 습관이 달라 제거율이 튄다 → 결과 검증은 매번 한다.
- 과제거는 되돌리기 번거로우므로(원본 가장자리 드래그 필요), 의심되면 처음부터 보수적으로.
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.
- 12d ago First seen · 61 lines · 143 tokens per session scan A 0da8cf5e2c13
cut-editing is a skill published in the GitHub repository biblcontentofficial-art/Premiere-Pro-edit-bibl (21 stars, last pushed 1mo ago), licensed MIT. It adds 143 tokens to every session and 1,436 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
pr-to-video
Turn a GitHub pull request (a PR URL, owner/repo#N, or 'this PR' in a checked-out repo) into a code-change explainer video — changelog, feature reveal, fix, or refactor walkthrough built from the diff, commits, and files: the input is a code change, not a website. Not a product promo (/product-launch-video) or a no-PR…
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…
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
remake-reel
Analyze a reference video (a reel, montage, or ad the user likes) into an edit blueprint — shot boundaries, music beats, BPM, energy curve, the drop — and rebuild the same structure with the user's own footage. Use when someone says "make it like this video", "remake this reel with my clips", or asks what makes an…
stage-edit
Intelligent editing of real user-supplied footage—understand it with transcript/OCR/scene/silence/quality/vision evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.