메뉴
Use this skill when creating, running, or modifying the lightflow.video_auto_edit_plan workflow for automated video editing plans.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/LIghtJUNction/lightflow-auto-editing --skill lightflow-video-auto-edit-plan명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | LightFlow Video Auto Edit Plan |
| description | Use this skill when creating, running, or modifying the lightflow.video_auto_edit_plan workflow for automated video editing plans. |
| version | 0.4.0 |
Use lightflow.video_auto_edit_plan only after
lightflow.video_highlights has returned its approved VideoScore clips output.
Pass that output unchanged as clips. The
package-owned Rust runner produces a structured lightflow.video.edit-plan.v1
from those explicit, HMAC-verified ranges; lightflow.video_render_edit
consumes the result.
The workflow crate contains a Rust-native runner.v1 binary, so installation
does not depend on repository-relative scripts. It does not perform ASR,
semantic selection, silence removal, or scene detection.
lightflow.video_auto_edit_planclips: JSON array of explicit clip objects with VideoScore
provenance.brief: human editing goal, story outline, or script notes.style: editing style guidance. Defaults to clean social edit.constraints: JSON delivery constraints for aspect ratio,
duration, frame rate, width, and height.edit_plan: JSON edit decision plan.summary: readable planning summary.# Set this only in the runtime environment. Use the same key for
# lightflow.video_highlights and lightflow.video_auto_edit_plan.
export LIGHTFLOW_VIDEOSCORE_EVIDENCE_KEY='at-least-32-non-whitespace-bytes'
lfw run lightflow.video_auto_edit_plan \
--input clips='[{"id":"intro","path":"intro.mp4","start":0,"end":8,"highlight":{"workflow":"lightflow.video_highlights","source_path":"intro.mp4","start_seconds":0,"end_seconds":8,"score":3.7,"model":"TIGER-Lab/VideoScore-v1.1","reason":"Clear opening vehicle shot.","evidence":"<generated-by-lightflow.video_highlights>"}}]' \
--input brief='"Cut a concise launch recap with a strong opening hook."' \
--input style='"fast social product edit"' \
--input constraints='{"aspect_ratio":"9:16","max_duration_seconds":45}'
<generated-by-lightflow.video_highlights> is a schema placeholder, not a
usable value. Copy the actual lowercase-hex HMAC-SHA256 tag produced by
lightflow.video_highlights; do not forge it.
Start lfw serve, then call the workflow through the shared HTTP run contract:
curl -sS -X POST http://127.0.0.1:5174/workflows/lightflow.video_auto_edit_plan/run \
-H 'content-type: application/json' \
-d '{"inputs":{"clips":[{"id":"intro","path":"intro.mp4","start":0,"end":8,"highlight":{"workflow":"lightflow.video_highlights","source_path":"intro.mp4","start_seconds":0,"end_seconds":8,"score":3.7,"model":"TIGER-Lab/VideoScore-v1.1","reason":"Clear opening vehicle shot.","evidence":"<generated-by-lightflow.video_highlights>"}}],"brief":"Cut a concise launch recap with a strong opening hook.","style":"fast social product edit","constraints":{"aspect_ratio":"9:16","max_duration_seconds":45}}}'
When changing inputs, outputs, runtime behavior, or common commands, update this skill and the runner tests in the same change so agents can safely run and inspect the workflow.