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/edit-direction/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/edit-direction)<a href="https://agentmods.dev/skills/biblcontentofficial-art/premiere-pro-edit-bibl/edit-direction"><img src="https://agentmods.dev/badge/skills/biblcontentofficial-art/premiere-pro-edit-bibl/edit-direction/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/edit-direction"><img src="https://agentmods.dev/badge/skills/biblcontentofficial-art/premiere-pro-edit-bibl/edit-direction.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 | $0.00097 | $0.01227 |
| Opus 5.5 | $0.00039 | $0.00491 |
| Sonnet 5.5 | $0.00019 | $0.00245 |
| Haiku 4.5 | $0.00010 | $0.00123 |
Grade A, and why
edit-direction 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 1mo 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.
What it actually says
편집 디렉션 & 검수
파이프라인의 **시작(방향 설정)**과 **끝(검수·핸드오프)**을 담당한다.
시작: 방향 설정 → 00_director_brief.md
- 원본 영상 성격 파악(라이브/토크/강의/대담) — 길이·발화밀도로 추정.
- 편집 톤과 초기 프리셋 결정 (기획자가 리서치 후 조정 가능).
- 주의점 명시 (이 영상에서 특히 조심할 것 — 예: "전문용어 많음 → 자막 고유명사 주의").
## 편집 방향
- 영상 성격: 라이브 토크 (73분)
- 초기 프리셋: 표준
- 톤: 타이트하되 논리 연결 보존
- 주의: 시청자 닉네임 다수 → 자막 오인식 점검
끝: 검수 → 99_director_handoff.md
정량 검수 게이트 (인상 말고 숫자로)
각 항목을 통과/주의/반려로 판정. '반려'면 컷편집가에 재실행 지시.
| 항목 | 통과 | 주의 | 반려 |
|---|---|---|---|
| 제거율(표준) | 3~10% | 10~12% | >12% (과제거 의심 → 보수 재실행) |
| 제거율(공격) | 13~19% | 19~22% | >22% |
| choppy(자연스러움 주의) | ≤ 길이(분)/4 곳 | 그 2배까지 | 그 이상 (보수 프리셋 재실행) |
| 추임새 보존(표준/보수) | 추임새 제거 0건 | — | 추임새가 잘림(설정 오류 — REMOVE_FILLERS 확인) |
| 접속사 보존 | "그래서"/"근데" 살아있음 | — | 다수 잘림 (공격 과함) |
| 자막 타이밍 | 역전·겹침·빈칸 0 | — | 1개+ (자막 재마감) |
| 자막 분할 | 문장 섞임·수식어 끝 ≤0.5% | ~1% | 그 이상 (의미단위 재분할) |
| 끝음 | 문장 끝 살아있음 | 일부 잘림 | 다수 잘림 (NOISE_DB 낮추기) |
| (멀티캠) 오프셋 | 전 구간 일정 | — | 흔들림 (재싱크·부호 재검증) |
표본 점검: choppy 상위 3곳 + 더듬/중복 의심 3곳을 _cut_report.txt에서 실제 발화로 확인.
각 산출물을 실제로 읽고 점검:
30_cut_result.md— 제거율이 프리셋 기대범위(표준 310%/공격 1319%)인지. 초과 시 과제거 의심._cut_report.txt— 의미 있는 단어(접속사·핵심어)가 잘렸나? 표본 점검._cut.srt— 고유명사 교정됐나? 타이밍 무결성?10_research.md+20_plan.md— 인트로 훅·강조·B롤 마커가 비블에게 전달 가능한가?
핸드오프 노트(비블용):
## 편집 핸드오프
### 한 일
- 64:24 → 60:xx (x% 제거): 무음·숨소리·더듬 (추임새는 보존)
- 음량 -14 LUFS 정리 / 자막 고유명사 N건 교정
### 비블이 손볼 것
- 00:35:02 "네가 뭔데?" 의도적 반복인지 확인(잘림)
- 강조 자막: 00:08:15 "구체성이 핵심"
- B롤: 00:15:40 썸네일 예시
### 불러올 파일
- output/..._cut.xml (시퀀스) / _cut.srt (자막)
검수 원칙
- 데이터로 판단 — 인상이 아니라 리포트·자막 실제 내용으로.
- 과제거는 보수로 반려 — 의심되면 컷편집가에 한 단계 보수 프리셋 재실행 지시.
- 불확실은 비블 위임 — 애매한 컷은 핸드오프에 '확인 요망'으로 넘긴다.
왜 이렇게 하는가
- 자동화가 못 하는 마지막 판단(의미 손상 여부, 비블 톤 적합성)을 사람 대신 책임지는 자리. 그래서 인용·타임코드로 검증 가능하게 남긴다.
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.
- 1mo ago First seen · 69 lines · 97 tokens per session scan A b0dd3f0c6ef1
edit-direction is a skill published in the GitHub repository biblcontentofficial-art/Premiere-Pro-edit-bibl (24 stars, last pushed 3mo ago), licensed MIT. It adds 97 tokens to every session and 1,227 once invoked, about $0.0004 per session on Opus 5.5. 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
glass-shard-title
Glass shards fly in through fog and tile themselves into the headline. HyperFrames block, 1920×1080, 12.16s, 19 variables.
remotion-video
Use when you need to render an actual video file with Remotion — React compositions, the Composition/Sequence/TransitionSeries graph, transitions, burned-in word-by-word captions from a transcript, automatic silence removal, b-roll overlays, headless CI renders, and a final MP4 or MOV. NOT writing the script, hook…
stage-edit
Intelligent editing of real user-supplied footage—understand it with transcript/inspected-frame/scene/silence/quality evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.
video-perception
Use when the user mentions a video file (.mp4, .mov, .avi, .mkv, .webm), a YouTube URL, asks to watch/analyze/review a video, or references video content in conversation.
web-demo-video
A process for making product-demo videos from a real website or web app by displaying it in an embedded browser page, controlling it with real mouse events, capturing the frames, and combining them with ffmpeg.
value-based-proposal
A proposal and quotation workflow that prices consulting or client work by the result it is expected to create rather than by hours spent. It makes document files locally and treats amounts and conditions as examples to recalculate.