ZenStory AI
EN 中文
Open app

ZenStory AI Projects

Video workflow

Video Recap Skills

Turn footage into a Chinese-narration recap: understand the scenes, write, voice, edit and subtitle.

541 GitHub stars7 skills

Source on GitHubEnglish README

Install Video Recap Skills
npx skills add zenstory-ai/video-recap-skills -y -g

What it is

Video Recap Skills turns local footage into a Chinese-narration recap in a supported agent host such as Claude Code or Codex. Seven skills cover five production stages, an orchestrator and optional reference analysis. Local ffmpeg handles media; a MiMo API key enables remote speech recognition, visual understanding and voiceover, with Fish Audio as an optional TTS provider. No local GPU is required. The finished video can also be exported as an editable JianYing/CapCut draft for further editing.

What you need

  • LicenseMIT, open source.
  • HostAny one of these agents:Claude CodeCodex CLIGoogle AntigravityOpenCodeZCodeOpenClawReasonixKimi CodeDeepSeek Harness

Start in 3 steps

  1. Installnpx skills add zenstory-ai/video-recap-skills -y -g
  2. Entry commandRun /video-recap in your agent host.
  3. Follow a guideFind your first task under “How it works” below and open its guide.

Writing craft

49 craft articles, each built on a method file in this project's skills. Start with the complete workflow, or open a task.

By creative task

How it works

  1. How do I turn a local video into a Chinese recap? Build a scene/dialogue evidence index, choose the audience promise, divide the work between pictures, original audio and narration, then voice and assemble the grounded script. The complete workflow guide explains full/cut choices, stage handoffs and expected files before optional draft export.
  2. Can I add narration when the source has none? Yes. No narration does not mean no dialogue; preserve speech evidence when people speak. Dialogue-free footage can skip ASR while still using remote VLM analysis. The original evidence-to-script examples distinguish a changed on-screen promise from a proven result, then show what can be said when only the initial attempts are available. When later footage is missing, request that evidence or propose a clearly narrower account; do not invent an ending.
  3. Which moments should keep their original sound? Let a complete original line, a revealing action sound or a meaningful wait lead. The five-beat radio example compares shortening context with omitting it, then shows captions alongside each sound: retain faithful speech captions, separate optional sound labels, and do not turn “after the move” into “the move caused the fault.” The edit preserves the wait and invents neither poverty nor a completed mix.
  4. Can I write the recap before choosing the cut? Decide the story and sound roles first. In the orchestrated cut flow, select source clips, then write narration against the actual edited output timeline. Do not copy original timestamps into that output-time narration.
  5. What if the voiceover is too long? Reduce or move the thought instead of speaking over the next protected line. Bounded speed adjustment is not unlimited; an unsafe fit can block placement rather than clipping the spoken ending.
  6. Does an audio-owner label automatically preserve the mix? No. The renderer does not parse the creative board. Actual narration timing, speech evidence and mix settings implement the plan; source audio can remain ducked beyond the written block until a safe recovery point. Listen to the rendered transitions.
  7. Can I finish the sound and captions manually? Export the existing timeline, then choose what the scene needs. The JianYing / CapCut guide compares two original rehearsal edits: move commentary after the result, or remove it for an original-audio-led cut. Move matching captions and inspect the old and new volume keyframes; moving only a voiceover does not move every dependent element.

What makes it different

  • ffmpeg handles local media processing, while configured remote providers receive the media or text required for ASR, visual understanding and speech generation; this is not an offline-only pipeline.
  • An optional CapCut/JianYing draft export supports manual finishing.
  • Automated checks locate candidate problems; real playback remains the final review boundary.

Who it is for

  • Recap and commentary channel creators
  • Editors who finish in CapCut
  • Teams turning long footage into short narrated cuts

Terms it uses

解说视频 剪映草稿 先剪后配

Sources

Based on the source as of 2026-10-15; links point at that version.

Part of ZenStory AI

ProjectFormatWhat it does
Oh Story Agent skill pack Write web fiction in Claude Code, Codex and other agents: chart scans, breakdowns, drafting, de-AI editing and covers.
Drama Skills Production skill suite Turn an idea or a novel into episode scripts, then visual specs, storyboards and generation prompts; produce and review when you need to.
Novel to Game Adaptation skill pack Adapt a novel into a playable game build grounded in the source, and check it running on the platform you choose.
Video Recap Skills Video workflow Turn footage into a Chinese-narration recap: understand the scenes, write, voice, edit and subtitle.
Oh Story DSH DSH plugin Use the writing, short-drama, game and recap packs inside DeepSeek Harness's GUI workbenches.
ZenStory Workbench Web workbench Write a novel with AI in the browser: outline, characters, chapters and versions in one project.