Install any skill in seconds. Free to start, no credit card required.
Get Started Free →worldwonderer/video-recap
从输入视频端到端生成中文解说成片。用户提供 .mp4 / .mov / .mkv / .webm,并要求添加旁白、 配音、总结、短剧/电视剧/电影/纪录片/科普解说时使用。负责编排 video-* 技能链:视频理解 → Agent 制定故事与视听方案 → 剪辑 → 配音 → 合成。触发词:视频解说、视频旁白、生成解说、 视频 recap、video recap、voiceover、narration、auto-dub、recap。
Passed 12 of 18 test cases with the skill, and 2 of 18 without it.
and 16 more in the full report
12 fixed3 passed either way7 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
After reviewing version 1 of our video recap, the client requested a faster narrative pace and changes to specific line phrasing, but wants to keep the original visual scene selections and story structure unchanged. Which plan files should be updated?
| Checked | Without skill | With skill |
|---|---|---|
| Updates style_card.json with pacing and expression feedback. | Missed | Passed |
| Keeps recap_story_plan.json frozen without modification. | Passed | Passed |
The instructions your model reads when the skill loads.
本技能是五个独立技能的轻量编排器。各技能只通过 work_dir 中的 JSON / MP4 产物通信,不共享代码:
video-understanding ─▶ Agent 按 video-script 制定方案并写稿 ─▶ [video-cut] ─▶ video-voiceover ─▶ video-assemble
流程支持断点续跑:写好 narration.json 后重复同一条命令即可继续。第二阶段会校验
recap_run_manifest.json,拒绝复用来自其他源视频或其他运行参数的旧工作目录;视频理解产物也只在来源一致时复用。
这不是单纯的 JSON / 渲染流水线。Agent 是本次内容的创作负责人。先判断本轮的创作控制模式;它与 --edit-mode full|cut|dub 是两个维度:
REVISION 开始前先明确“本轮修改项”和“冻结项”。表达、节奏、字幕反馈写回 style_card.json,镜头、入出点和声音分工写回 visual_audio_board.json;只有观众承诺、POV、主线或故事 beat 改变时才更新 recap_story_plan.json。删除成片内容时同步删除计划中的旧描述,不能让工作产物继续指导已不存在的镜头。
确定模式后,在进入昂贵的下游处理前完成五次判断:
执行前阅读本技能的 references/creative-editing-playbook.md,并把简洁的创作决定写入:
recap_story_plan.json:导演意图、适用时的备选假设、选定主线和基于变化的 beat 图。visual_audio_board.json:每拍的画面任务、表演/反应选择、原声锚点、audio_owner 与 narration_job。style_card.json(有表达要求或表达反馈时):当前声音、口语节奏、字幕阅读姿态与明确禁忌。这些文件只记录可审计的当前决定,不记录冗长思维过程;它们不会增加服务或渲染依赖。现有工具可以忽略它们,Agent 与建议型解说评审会用它们保持创作一致。建立这条内容基线不需要平台数据。
test cases passed, vs 2 / 18 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.