| name | ai-video-editing |
| description | 用于 AI 口播初剪、自动剪辑、去气口、去重复、视频转字幕、按口播稿对稿。支持语义级重复判断、剪后重新转字幕并与口播稿复核，还会标出大段 NG / 试讲 / 临场发挥候选段供用户确认。支持中文和英文，默认按电脑语言自动切换，也可手动指定。中文触发词包括 AI剪辑、自动剪辑、初剪、口播初剪、去气口、视频转字幕、对稿；英文触发词包括 AI video editing、auto edit this video、video edit、rough cut、trim pauses、remove repeated takes。开始前先确认用户是否提供口播稿，以及剪辑强度选 一般 或 多点。 |
| source_skill_id | raven7979-ai-video-editing-skill-skill-md |
| category | Creative, media & design |
| source_mirror | ../../../../../skills/by-category/creative-media-design/creative-reference/ai-video-editing/SKILL.md |
| benchmark_status | artifact_gated |
ai-video-editing
Use this skill when the task matches the description above or the source path clearly applies. Start with this concise entrypoint; open ../../../../../skills/by-category/creative-media-design/creative-reference/ai-video-editing/SKILL.md only when implementation details, commands, assets, or references are needed.
Workflow
- Confirm the task matches this skill's scope.
- Read the local source mirror if more detail is required.
- Follow repository-level
AGENTS.md; use one AI session only.
- Keep claims tied to files, commands, citations, or benchmark artifacts.
Verification
- Source mirror:
../../../../../skills/by-category/creative-media-design/creative-reference/ai-video-editing/SKILL.md
- Source commit:
9bf0a9c3396c181dca45ee969de72bfa57602d4c
- Static benchmark results: see
docs/benchmark-results.md
- Runtime artifacts recorded by this entrypoint:
0
- Assigned scenarios:
skill-proof-raven7979-ai-video-editing-skill-skill-md, creative-media-and-design-coco-captions, creative-media-and-design-air-defense-android-benchmarks, creative-media-and-design-nyc-tlc-trip-records
Do not claim this skill passed a runtime benchmark until a validated artifact exists.
