transcription
GitHub用于处理音视频转写、字幕生成及文本修复的技能。涵盖资产识别、进度监控、转录失败重试、填充词清理及语义编辑引导，确保转录就绪后启用字幕工具。
触发场景
安装
npx skills add ChatCut-Inc/agent-plugin --skill transcription -g -y
SKILL.md
Frontmatter
{
"name": "transcription",
"description": "Use for ChatCut transcription, transcript readiness, captions, subtitles, transcript repair, filler removal, and speech-led editing setup."
}
Transcription
- Use
browse_assetsto identify the video/audio asset and its transcription state. - For newly imported local media, complete the
asset-importworkflow first. - Check
track_progresswith targettranscription. It returns current status; follow the returned check-back guidance and do not busy-loop. - Use
find_transcriptfor timestamped text lookup. - Use the current caption tools to enable, inspect, translate, or style captions only after transcription is ready.
Do not call a transcription stuck from one pending status. Treat an explicit failed terminal state immediately; otherwise allow at least max(5 minutes, min(60 minutes, 2 x asset duration)), or at least 10 minutes across multiple checks when duration is unknown.
When a run is genuinely failed or stuck, call manage_transcript with action:"retry_transcription" and the asset id, then check transcription progress again. Repair source words with the transcript-fix action instead of rewriting visible captions when the source transcript itself is wrong.
For semantic speech edits, load talking-head-guide and use the Script workflow. Use mechanical cleanup only for fixed fillers and pauses; do not replace transcript-aware editing with destructive physical timeline cuts.
版本历史
-
e1867a8
当前 2026-08-02 23:37
简化了流程步骤描述，明确了非终端状态下的等待策略（基于资产时长计算），新增了针对真实卡住或失败时的重试与修复操作指引，并强调了语义编辑与机械清理的区别。
-
f39cdae
2026-07-30 21:54
将获取资产ID和状态的方法从 read_project 改为 browse_assets；更新了本地资产不可达时的处理逻辑，明确通过 asset-import skill 重新上传而非 download_media；优化了卡住转录的重试判定逻辑示例。
- 5e9afe0 2026-07-22 10:58
