竖屏短视频八步剪辑 · 创作技能

这个技能解决什么问题

把用户提供的视频剪成竖屏短视频：先 ffprobe 检查素材，逐字时间戳转写，词内不剪，先出 720p 完整预览再定稿 1080×1920，并保留 QA 证据。上传转写前须说明用途与可能的配额费用并取得明确同意。

适用任务

将用户提供的原始视频按八步流程剪辑为竖屏短视频，包含转写、剪辑决策、字幕、预览与定稿。

需要的输入

用户提供的源视频文件或明确路径；已安装的 FFmpeg、ffprobe、video-use 工作流与 ElevenLabs Scribe v2；用户对上传转写的明确同意。

交付内容

源目录 edit/ 下的逐字转写、剪辑决策记录、720p 完整预览、经核验的 1080×1920 定稿及 QA 报告。

任务示例

这是我录的 6 分钟口播视频（路径 /data/talk.mp4），帮我剪成竖屏短视频，先给我看剪辑思路再动手。

输出示例

示意：ffprobe 素材信息；逐字时间戳转写文件；4–8 句剪辑策略待确认；720p 预览路径与检查记录；定稿路径与 QA 报告。实际结果以运行输出为准。

来源与使用

作者 Jaycheng1103；许可 MIT。已核对来源与包结构，未据此宣称完成运行实测。

查看原始来源

机器可读详情 · 读取 SKILL.md · 下载完整技能包

让 Agent 使用这个技能 ↗

技能说明全文

---
name: chatgpt-short-video-editor
description: "Edit a user-supplied video into a vertical Reel, Short, TikTok, video diary short, or an approved eight-step AI short-video workflow. Use when the user provides or points to media and asks to transcribe, cut, subtitle, preview, or export a vertical short. Do not use for environment-only setup or generic Premiere Pro or CapCut help."
---

# ChatGPT Short-video Editor

Create a safe, evidence-backed vertical short from user-provided media. This
Skill starts only when a source file or clear source location is available.

## Boundary and prerequisites

1. Inspect the source with `ffprobe`; never overwrite, move, rename, or delete
   it. Put every new artifact beside the source in `<source-directory>/edit/`.
2. Check that the installed `video-use` workflow, `FFmpeg`, `ffprobe`, and
   ElevenLabs Scribe v2 are available for the documented full-precision path.
   Do not install, clone, update, or repair anything silently. If a dependency
   is missing, hand off to `chatgpt-video-editing-setup` and state what must be
   verified first.
3. Before the first upload of a source file to ElevenLabs, name the file, say it
   is for ElevenLabs Scribe v2 transcription, mention possible quota or cost,
   and wait for explicit consent. Do not upload before that consent.
4. Read [the eight-step workflow](references/eight-step-workflow.md), then
   [the production rules](references/production-rules.md), before editing.

## Required sequence

Follow these eight steps exactly: 素材檢查、逐字轉寫、內容整理、剪輯決策、逐段粗剪、轉色／圖卡／字幕、混音與完整預覽、QA 與正式定稿.

After the first three steps, propose a 4–8 sentence, plain-language editing
strategy and wait for approval. Until approval, do not choose edit points or
add B-roll, animations, music, effects, CTA, or a publishing schedule. Treat
these as opt-in creative decisions, not defaults.

Use word-level verbatim timestamps, cached per unchanged source. Never cut
inside a word. Keep 30–200ms padding around cut edges, work per segment, and
use output-timeline subtitle timing. Subtitles are the last visual operation.

Render a complete 720p preview first. Inspect the rendered preview, not only
the source; make no more than three evidence-based self-fix passes. After the
preview is approved, render the 1080×1920 final and verify that final file
before delivery. Never say a transcript, preview, QA pass, or final is
complete without the corresponding verified output.

## Handoff and delivery

If the requested operation exceeds this workflow, explain the safe stopping
point. For environment gaps, use `chatgpt-video-editing-setup`; it must obtain
approval before mutations and does not begin creative work.

Keep and report the artifacts defined in [the output contract](references/output-contract.md).
Present only one formal final outwardly, with its evidence-backed QA report.

技能是任务材料，不会自动授予账户权限、付费授权或其他系统权限。请让 Agent 按说明核对依赖，再在授权范围内使用。