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/video-edit-pipeline/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/video-edit-pipeline)<a href="https://agentmods.dev/skills/biblcontentofficial-art/premiere-pro-edit-bibl/video-edit-pipeline"><img src="https://agentmods.dev/badge/skills/biblcontentofficial-art/premiere-pro-edit-bibl/video-edit-pipeline/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/video-edit-pipeline"><img src="https://agentmods.dev/badge/skills/biblcontentofficial-art/premiere-pro-edit-bibl/video-edit-pipeline.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 | $0.00165 | $0.01776 |
| Opus 5 | $0.00082 | $0.00888 |
| Sonnet 5 | $0.00033 | $0.00355 |
| Haiku 4.5 | $0.00016 | $0.00178 |
Grade A, and why
video-edit-pipeline 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
비블 영상 편집 파이프라인 (오케스트레이터)
원본 영상 1개를 받아 5개 전문 에이전트를 파이프라인으로 지휘해 프리미어 핸드오프까지 끝낸다.
실행 모드: 서브 에이전트 파이프라인 + 감독자(편집 디렉터 검수). 작업이 순차 의존적이고(전사→분석→기획→재컷→자막) 무거운 연산은 auto_cut.py가 결정적으로 처리하므로, 파일 기반 핸드오프가 가장 안정적이다.
모든 에이전트 호출은 Agent 도구 + subagent_type + model: "opus". 산출물은 output/_workspace/에 파일로 주고받는다.
Phase 0: 컨텍스트 확인
output/_workspace/존재 여부 확인.- 없음 → 초기 실행 (전체 Phase)
- 있음 + 비블이 부분 수정 요청("자막만 다시", "더 보수적으로") → 부분 재실행 (해당 에이전트만)
- 있음 + 새 영상/전면 재작업 → 기존을
_workspace_prev/로 옮기고 새 실행
- 부분 재실행이면 아래 Phase 중 해당 단계만 수행하고 디렉터 검수로 마무리.
Phase 1: 방향 설정 (편집 디렉터)
Agent(edit-director, model:opus)→00_director_brief.md(영상 성격, 초기 프리셋, 주의점).
Phase 2: 러프컷 + 전사 (컷편집가)
Agent(cut-editor, model:opus)→engine/auto_cut.py "영상" --preset {brief의 프리셋}실행(백그라운드, 완료 대기).- 산출:
_cut.xml/_cut_audio.wav/_cut.srt/_cut_report.txt/_words.json+30_cut_result.md. - 여기서 전사(
_words.json)가 먼저 나와야 리서처·기획자가 일한다.
Phase 3: 내용 분석 + 내용 컷 제안 (콘텐츠 리서처, 확정/검토 2단)
Agent(content-researcher, model:opus)→10_research.md(핵심메시지·하이라이트·챕터)output/<base>_content_cuts.json(확정 컷: 오프닝/호명/홍보/아웃트로/자체컷마커/명백한 곁가지)11_content_cuts_review.md(검토: 긴 개별 Q&A·서사/철학 경계 → 디렉터가 1차 판정).
- 라이브 소스면 이 단계가 필수다. 4회 정량 측정으로 검증된 규칙: 긴 개별 Q&A는 통삭제, 단 영상 서사 정체성·철학·마인드셋은 절대 보존(잘못 자르면 완성본 망침). 기계 컷만으로 라이브를 납품하지 않는다.
Phase 4: 편집 기획 (영상 기획자)
Agent(video-planner, model:opus)→20_plan.md(인트로훅·흐름·프리셋추천·강조/B롤마커 + 라이브면 본론 시작점·Q&A 배치).
쇼츠는 이 파이프라인에서 자동 생성하지 않는다. 사용자가 완성된 롱폼을 따로 올리고 "숏폼 만들어줘"라고 할 때만
shorts-production스킬로 별도 진행한다(온디맨드).
Phase 5: 최종 컷 (컷편집가)
_content_cuts.json이 생겼거나 기획의 프리셋/설정이 Phase 2와 다르면Agent(cut-editor, model:opus)로 재실행(전사 캐시로 수 분). 엔진이 내용 컷을 자동 반영한다.- 둘 다 없으면 건너뜀.
Phase 6: 자막 교정 (자막 에디터)
Agent(subtitle-editor, model:opus)→_cut.srt교정본 +40_subtitle_notes.md(고유명사·줄균형·가독성).
Phase 7: 검수 & 핸드오프 (편집 디렉터)
Agent(edit-director, model:opus)→ 전체 산출물 검수 →99_director_handoff.md(잘린 요약, 비블이 손볼 지점, 불러올 파일).- 비블에게 핸드오프 노트를 요약 보고.
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 · 73 lines · 165 tokens per session scan A 3579ada96acc
video-edit-pipeline is a skill published in the GitHub repository biblcontentofficial-art/Premiere-Pro-edit-bibl (21 stars, last pushed 1mo ago), licensed MIT. It adds 165 tokens to every session and 1,776 once invoked, about $0.0008 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.