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/shorts-production/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/shorts-production)<a href="https://agentmods.dev/skills/biblcontentofficial-art/premiere-pro-edit-bibl/shorts-production"><img src="https://agentmods.dev/badge/skills/biblcontentofficial-art/premiere-pro-edit-bibl/shorts-production/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/shorts-production"><img src="https://agentmods.dev/badge/skills/biblcontentofficial-art/premiere-pro-edit-bibl/shorts-production.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 | $0.00120 | $0.01749 |
| Opus 5 | $0.00060 | $0.00874 |
| Sonnet 5 | $0.00024 | $0.00350 |
| Haiku 4.5 | $0.00012 | $0.00175 |
Grade A, and why
shorts-production 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
쇼츠 제작 (온디맨드)
혼자 봐도 말이 되는 1분 쇼츠 5~10개(9:16)를 만든다. 컷편집 파이프라인과 분리 — 사용자가 요청할 때만 실행.
제작 모드 (소스에 따라 선택)
- 모드 A · 컷 기반(권장) — 그 영상에 auto_cut 산출물(
_cut.xml+_cut_audio.wav+_words.json)이 있으면:python3 engine/shorts_cut.py <원본영상> "MM:SS-MM:SS" ...(구간은 컷 타임라인 기준 =_cut.srt시각) → keep만 모은 무음·숨소리 빠진 타이트한 9:16 XML + 6~7자 SRT. - 모드 B · 완성 롱폼 — 이미 편집 완료된 mp4만 있으면
shorts_xml.py(아래 절차).
캡컷 납품 (요청 시)
캡컷은 XML을 못 연다 → 컷 구간을 ffmpeg concat으로 9:16(1080×1920 레터박스) MP4 렌더(loudnorm -14 LUFS + 48kHz 명시, -dn -map_metadata -1) + 그 MP4를 직접 재전사한 SRT(타이밍 오차 0). 캡컷에서 '텍스트 > 로컬 자막 가져오기'.
입력
- 완성된 롱폼 영상(사용자가 따로 업로드) + 그 전사본/자막. 원본 raw가 아니라 편집 끝난 버전 기준.
- 개수: 영상 맥락에 맞게 5~10개 (콘텐츠가 풍부하면 많이, 적으면 적게).
비블 쇼츠 템플릿 (예시 측정값, 9:16)
| 요소 | 세로 위치 | 스타일 |
|---|---|---|
| 배경 | 전체 | 검정 |
| 제목 | 상단 11~24% | 흰색 굵게(Pretendard), 2줄, 가운데 — 수정 가능한 텍스트 |
| 영상 | 26~90% | 16:9를 좌우 ~50% 크롭(중앙)해 폭 꽉 채움(세로 줌인) |
| 자막 | ~61% | 흰색 굵게 6~7자 한 줄, 얇은 검정 외곽 |
| 워터마크 | ~94% | "비블 bibl" 회색, 가운데 — 수정 가능한 텍스트 |
제목·워터마크·자막은 반드시 편집 가능한 텍스트로 (영상에 굽지 말 것). 영상 레이아웃은 9:16 XML로, 텍스트는 비블 프리미어 템플릿/텍스트 레이어로 얹는다.
프리미어 배치 실측값(short_01 확정, 1080×1920): 제목 그래픽 벡터모션 Y=-460(상단) / 워터마크 "비블 bibl" Y=1341·비율 62(맨 아래 작게, 비율 줄이면 Y도 같이 키움) / 캡션 하단 ~88%. 번인 자막 있는 소스는 V1 모션 '아래쪽 자르기 ~12%'로 제거(소스마다 값 확인).
입력
- 원본 영상,
output/<base>_transcript.md(읽기 좋은 전사),output/_workspace/10_research.md(하이라이트·hook 점수) - 전사/리서치 없으면 먼저
transcript_export.py/ 리서처 실행.
절차
1. 5~10개 선정 (서로 다른 맥락)
완성 롱폼의 핵심 구간 중 다른 각도로 5~10개(콘텐츠 풍부하면 많이): 인트로훅 / 핵심논리 / 반전 / 구체사례 / 결론. 같은 주제 반복 금지.
2. 1분 윈도우로 확장 (맥락 완결)
각 하이라이트를 45~75초로 확장:
- 시작점 — 훅 문장이 클립 첫 3초에 오게. 그 앞에 꼭 필요한 한 문장만 설정으로. 자막(
_cut.srt) 시작 시각에 스냅해 문장 중간에서 시작하지 않기. - 끝점 — 결론/임팩트 문장에서. 문장 중간에서 끊지 않기.
- 너무 길면(>75초) 곁가지를 빼서 압축, 너무 짧으면(<40초) 맥락을 더 포함.
3. 타임코드 = 완성 롱폼 시각
shorts_xml.py는 사용자가 올린 완성 롱폼을 자른다. in-out은 그 롱폼 기준.
4. 9:16 XML 생성 (mp4 아님 — 편집 가능)
python3 engine/shorts_xml.py "완성롱폼.mp4" "12:25-13:20" "23:10-24:05" ...
→ output/shorts/short_NN.xml : 9:16 시퀀스 + 16:9 좌우크롭 세로꽉참. 프리미어로 불러와 수정.
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 · 76 lines · 120 tokens per session scan A 6e8123db08b4
shorts-production is a skill published in the GitHub repository biblcontentofficial-art/Premiere-Pro-edit-bibl (21 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 1,749 once invoked, about $0.0006 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.