Agent SkillsChatCut-Inc/agent-plugin › transcription

transcription

GitHub

用于处理音视频转录、字幕生成及修复的技能,涵盖资产状态检查、进度监控、文本查找、错误重试及语义编辑引导。

codex/skills/transcription/SKILL.md ChatCut-Inc/agent-plugin

Trigger Scenarios

需要视频或音频文件的转录文本 生成或翻译字幕 修复错误的转录内容 进行基于语音的剪辑

Install

npx skills add ChatCut-Inc/agent-plugin --skill transcription -g -y
More Options

Non-standard path

npx skills add https://github.com/ChatCut-Inc/agent-plugin/tree/main/codex/skills/transcription -g -y

Use without installing

npx skills use ChatCut-Inc/agent-plugin@transcription

指定 Agent (Claude Code)

npx skills add ChatCut-Inc/agent-plugin --skill transcription -a claude-code -g -y

安装 repo 全部 skill

npx skills add ChatCut-Inc/agent-plugin --all -g -y

预览 repo 内 skill

npx skills add ChatCut-Inc/agent-plugin --list

SKILL.md

Frontmatter
{
    "name": "transcription",
    "description": "Use for ChatCut transcription, transcript readiness, captions, subtitles, transcript repair, filler removal, and speech-led editing setup."
}

Transcription

  1. Use browse_assets to identify the video/audio asset and its transcription state.
  2. For newly imported local media, complete the asset-import workflow first.
  3. Check track_progress with target transcription. It returns current status; follow the returned check-back guidance and do not busy-loop.
  4. Use find_transcript for timestamped text lookup.
  5. 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.

no_audio / no-speech is a successful terminal analysis result: the media is usable, but there is no transcript to read or caption. Do not report it as a transcription failure or retry it unless the user says the media contains speech that should have been detected.

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.

Version History

  • 926f56b Current 2026-08-12 11:07

    移除对显式失败状态的立即重试逻辑,改为直接处理;新增无音频/无声被视为成功终态的处理规则。

  • e1867a8 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

Same Skill Collection

chatcut/skills/asset-import/SKILL.md
chatcut/skills/chatcut-plugin-basics-claude/SKILL.md
chatcut/skills/chatcut-plugin-basics/SKILL.md
chatcut/skills/create-motion-graphics/SKILL.md
chatcut/skills/export/SKILL.md
chatcut/skills/image-gen/SKILL.md
chatcut/skills/known-errors/SKILL.md
chatcut/skills/music/SKILL.md
chatcut/skills/shader-gen/SKILL.md
chatcut/skills/transcription/SKILL.md
chatcut/skills/verification/SKILL.md
chatcut/skills/video-gen/SKILL.md
chatcut/skills/voice/SKILL.md
chatcut/skills/widget-forms/SKILL.md
claude/skills/asset-import/SKILL.md
claude/skills/create-motion-graphics/SKILL.md
claude/skills/export/SKILL.md
claude/skills/image-gen/SKILL.md
claude/skills/known-errors/SKILL.md
claude/skills/motion-graphic-gen/SKILL.md
claude/skills/music/SKILL.md
claude/skills/shader-gen/SKILL.md
claude/skills/transcription/SKILL.md
claude/skills/verification/SKILL.md
claude/skills/video-gen/SKILL.md
claude/skills/voice/SKILL.md
claude/skills/widget-forms/SKILL.md
codex/skills/asset-import/SKILL.md
codex/skills/create-motion-graphics/SKILL.md
codex/skills/export/SKILL.md
codex/skills/image-gen/SKILL.md
codex/skills/known-errors/SKILL.md
codex/skills/music/SKILL.md
codex/skills/shader-gen/SKILL.md
codex/skills/verification/SKILL.md
codex/skills/video-gen/SKILL.md
codex/skills/voice/SKILL.md
codex/skills/widget-forms/SKILL.md
chatcut/skills/product-help/SKILL.md
chatcut/skills/talking-head-guide/SKILL.md
claude/skills/chatcut-plugin-basics-claude/SKILL.md
claude/skills/multicam-sync/SKILL.md
claude/skills/product-help/SKILL.md
claude/skills/talking-head-guide/SKILL.md
codex/skills/chatcut-plugin-basics/SKILL.md
codex/skills/multicam-sync/SKILL.md
codex/skills/product-help/SKILL.md
codex/skills/talking-head-guide/SKILL.md

Metadata

Files
0
Version
926f56b
Hash
ccf5c449
Indexed
2026-07-22 10:58

ホーム - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-12 22:35
浙ICP备14020137号-1 $お客様$