MoneyPrinterTurbo Video Generator
harry0703/MoneyPrinterTurbo
Installs and runs MoneyPrinterTurbo to turn a topic or script into a finished short video with voice-over, subtitles, stock footage and music.
从输入视频生成中文解说成片或原声剧情短片。用户提供 .mp4 / .mov / .mkv / .webm，并要求剪辑、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…
Install Video Recap
$ npx skills add zenstory-ai/video-recap-skills --skill video-recap -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install zenstory-ai/video-recap-skills video-recap --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/zenstory-ai/video-recap-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/video-recap .claude/skills/video-recap && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "video-recap" agent skill from https://github.com/zenstory-ai/video-recap-skills/tree/main/skills/video-recap into .claude/skills/video-recap/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-recap", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/zenstory-ai/video-recap-skills/tree/main/skills/video-recapType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add zenstory-ai/video-recap-skills --skill video-recap -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install zenstory-ai/video-recap-skills video-recap --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenstory-ai/video-recap-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/video-recap .agents/skills/video-recap && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "video-recap" agent skill from https://github.com/zenstory-ai/video-recap-skills/tree/main/skills/video-recap into .agents/skills/video-recap/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-recap", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zenstory-ai/video-recap-skills --skill video-recap -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install zenstory-ai/video-recap-skills video-recap --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenstory-ai/video-recap-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/video-recap .cursor/skills/video-recap && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "video-recap" agent skill from https://github.com/zenstory-ai/video-recap-skills/tree/main/skills/video-recap into .cursor/skills/video-recap/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-recap", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/zenstory-ai/video-recap-skills.git --path skills/video-recap--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add zenstory-ai/video-recap-skills --skill video-recap -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install zenstory-ai/video-recap-skills video-recap --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenstory-ai/video-recap-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/video-recap .gemini/skills/video-recap && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "video-recap" agent skill from https://github.com/zenstory-ai/video-recap-skills/tree/main/skills/video-recap into .gemini/skills/video-recap/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-recap", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install zenstory-ai/video-recap-skills video-recapInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add zenstory-ai/video-recap-skills --skill video-recap -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/zenstory-ai/video-recap-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/video-recap .github/skills/video-recap && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "video-recap" agent skill from https://github.com/zenstory-ai/video-recap-skills/tree/main/skills/video-recap into .github/skills/video-recap/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-recap", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zenstory-ai/video-recap-skills --skill video-recap -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install zenstory-ai/video-recap-skills video-recap --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenstory-ai/video-recap-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/video-recap .opencode/skills/video-recap && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "video-recap" agent skill from https://github.com/zenstory-ai/video-recap-skills/tree/main/skills/video-recap into .opencode/skills/video-recap/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-recap", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
video-recap- GitHub stars
- 561
- Token cost
- ~2.4k tokens
- SKILL.md length
- 522 words
- Files
- 34 (incl. scripts, references, assets)
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
从输入视频生成中文解说成片或原声剧情短片。用户提供 .mp4 / .mov / .mkv / .webm，并要求剪辑、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…
- Works in 8 steps: 定位与流程 → 创作职责 → 环境与脚本路径 → …
- Tasks that involve Text to speech and voice
- SKILL.md covers 1. 定位与流程, 2. 创作职责, 3. 环境与脚本路径 and 4. 标准解说流程（audio-mode narration）, plus 4 more sections
- Runs Python and JavaScript scripts from its folder; calls python3; needs MIMO_API_KEY
What it does
Video Recap is an agent skill from zenstory-ai/video-recap-skills. 从输入视频生成中文解说成片或原声剧情短片。用户提供 .mp4 / .mov / .mkv / .webm，并要求剪辑、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。
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 38 other files, including scripts, reference files and assets (for example `assets/dashboard/app.js`, `assets/dashboard/views.js` and `references/audio-routing.md`).
It sits in Media & Creative, covering Text to speech and voice. The repository describes itself as: Claude Code / Codex skills that turn a video into a Chinese narration recap (视频解说): scene detection, ASR, VLM, script, TTS, ffmpeg assembly, optional editable JianYing / CapCut… The licence is MIT.
When your agent uses it
- Tasks that involve Text to speech and voice
Example prompts
- “/video-recap”
Requirements
- Python 3
- Node.js
- A credential in MIMO_API_KEY
Workflow steps
8 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 5391686. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 6 files in scripts/ (Python and JavaScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
MIMO_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Video Recap loads about 2.4k tokens when it runs, and up to ~19k if it reads all its reference files. Until then it costs about 59 tokens; SKILL.md has 522 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from zenstory-ai/video-recap-skills at commit 5391686, republished under its MIT licence (© zenstory-ai). 522 words, ~2,412 tokens.
Download SKILL.mdSave it as
.claude/skills/video-recap/SKILL.md (or your agent's skills folder). This skill also uses 33 other files; get the full folder from GitHub.- name
- video-recap
- description
- 从输入视频生成中文解说成片或原声剧情短片。用户提供 .mp4 / .mov / .mkv / .webm，并要求剪辑、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。
1. 定位与流程
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把成片拆成制作参考不是生产路径。用户要求时：对成片跑 video-understanding（建议 ASR_SEGMENT_SECONDS=5），
再用 video-reference 做 measure、标注、check、export，把导出的 production_reference.json 复制进下一次运行的
work_dir，或登记成资源库的 production_reference 模板、采纳后经 --project 绑定。recap 不会自动运行它，也不拿新成片与参考做比对。
流程支持断点续跑：写好 narration.json 后重复同一条命令即可继续。第二阶段会比对
recap_run_manifest.json 记录的源视频路径、文件大小/修改时间与运行参数，拒绝复用来自其他源视频或其他参数的旧工作目录；视频理解产物也只在来源一致时复用。
暂停时打印的续跑命令就是原命令：保留原来的写法，视频与路径参数转成绝对路径，补上 --work-dir 和来自环境变量的设置，从任何目录都能直接运行；同一份参数写在 manifest 的 argv。
画面流程 --edit-mode full|cut|dub 与声音策略 --audio-mode 是两个独立开关；
narration 保留上述解说流程，source-mix 不做配音，adopted-packet-copy 冻结当前输入的已采用 AAC 音轨。
组合只有下面几条路径，其余组合在启动时直接报错：
| 输入 | --edit-mode | --audio-mode | Agent 暂停点 | 流程 | 详见 |
|---|---|---|---|---|---|
| 单视频 | full | narration | 1：narration.json | 理解 → 写稿 → 校验 → 配音 → 合成 | §4 |
| 单视频 | cut | narration | 2：clip_plan.json，再对着成片写 narration.json | 理解 → 剪辑 → 重建输出时间 brief → 写稿 → 配音 → 合成 | §4 |
| 多视频 | cut | narration | 2：同上，clip 必须带 source_id | 逐源理解 → 剪辑 → 写稿 → 配音 → 合成 | §4.3 |
| 单视频 | full | source-mix / adopted-packet-copy | 无 | 直接合成当前整段 | §4.7 |
| 单 / 多视频 | cut | source-mix / adopted-packet-copy | 1：clip_plan.json | 理解 → 剪辑 → 合成，不写稿 | §4.7 |
| 单视频 | dub | narration | 1：dub_script.json | 英文转写 → 译稿 → 克隆音色整轨替换 | §5 |
| 已剪好的母版 | full | narration + 三个采用 JSON | 无 | 只做严格合成 | 下文 |
所有 full/cut 路径共用同一段收尾：（有旁白时）评审 → TTS → 合成 → 成片 QC。使用原声模式时读
references/audio-routing.md。
已有预制画面和本地采用的完整声音三件套时，可走严格 assembly-only 路径：
python3 scripts/recap.py picture.mp4 --edit-mode full --work-dir NEW_WORK \
--output-dir DELIVERY \
--tts-meta tts_meta.json \
--narration-adoption narration_adoption.json \
--audio-mix-adoption audio_mix_adoption.json三个 JSON 参数必须同时出现。该入口只接受单视频、full、narration、音轨 0、新工作目录和未存在的
交付文件；不运行理解、写稿、解说评审、TTS、cut 或剪映导出。语义与媒体形状仍由
video-assemble 严格验证，recap 只核对子技能绑定记录引用的是同一批采用文件与母版路径，不把调用方
采用的声音或混音声明成自动创作或发布批准。详见 references/audio-routing.md。
这里的单视频是已经剪好的母版。重剪后可以复用未改动的 WAV 与 tts_meta.json，但必须按新母版
重新写混音采用文件里的落点与准备好的音床；衔接步骤见 references/audio-routing.md 的 “Keep adopted voice after a cut”。
2. 创作职责
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（CREATE / DIRECTED / REVISION，与 --edit-mode 无关），再在进入昂贵的下游处理前完成五次判断：
- 导演判断：观众承诺、POV、戏剧问题、情绪终点与揭示节奏。
- 故事编辑：beat 定义为“发生了什么变化”，不是场景摘要。
- 画面剪辑：选择真正值得保留的具体时刻、反应、入点与出点。
- 声音/旁白：先分配画面、原声、沉默和旁白的任务，再写解说词。
- 观众复核：分别检查无旁白、只听声音和第一次观看的体验。
三种控制模式的定义、REVISION 的修改/冻结规则、创作方法以及 recap_story_plan.json / visual_audio_board.json / style_card.json 的写法，全部按 video-script 执行；它会要求先读创作手册。这些文件只记录可审计的当前决定，不增加服务或渲染依赖。
3. 环境与脚本路径
# ffmpeg: brew install ffmpeg | apt install ffmpeg | choco install ffmpeg
export MIMO_API_KEY=***同一个 MiMo key 驱动：
- ASR：
mimo-v2.5-asr - VLM：
mimo-v2.5 - TTS：
mimo-v2.5-tts
TTS 供应商由 --tts-provider mimo-tts|fish-audio|index-tts（或 TTS_PROVIDER）透传给配音技能；Fish Audio 与自托管 index-tts 各自的环境变量、默认音色和能力限制见该技能。ASR/VLM 始终使用 MiMo。--doctor 只做离线配置检查。
tp-* Token Plan 密钥默认使用中国区集群，可用 MIMO_TOKEN_PLAN_CLUSTER 覆盖。
可选能力：
--mimo-video-overview：按场景块补充 MiMo 视频理解。
可覆盖配置见 references/config-playbook.md，final_qc.json 的字段见 references/data-schema.md。
下面的 scripts/... 均相对于本技能目录。若执行器从仓库根目录启动，请给脚本路径加上本技能的绝对目录。脚本启动后会自行定位兄弟技能和资源。
4. 标准解说流程（audio-mode narration）
4.1 背景调研
若能识别影片、剧集或主题，先按 video-understanding 技能的调研指南 research-guide.md 调研并写入
work_dir/background_research.json。视频理解会把人物名和剧情背景折入 VLM 上下文，避免只得到“黑衣男子”一类模糊描述。无法识别来源时可跳过。
多视频运行同样写在项目 work_dir 下：recap 在每个来源理解前把它复制到 sources/<source_id>/（来源目录里没有、或比项目文件旧时才复制，所以某一集需要单独的调研时，在项目文件之后写入该来源目录即可）。
4.2 分析并暂停创作
python3 scripts/recap.py <video> --work-dir <work_dir> --context "背景"命令完成视频理解、写出 agent_narration_brief.md，然后暂停。此时按以下顺序执行 video-script：
- 查看创作 brief 与原片故事板。
- 写
recap_story_plan.json和visual_audio_board.json。 - full 模式写
narration.json；cut 模式第一阶段只写clip_plan.json。 - cut 模式第二阶段查看剪后故事板，补充输出时间与声音分工，再写
narration.json。
不要从标题或旁白句子开始；先锁定故事体验和素材选择。
时间线有两条不可降级的硬约束：原声只能在可靠句末/静音边界被切入、切出或恢复；旁白必须使用
完整逐段音频，任何 clip 映射裁段、TTS 裁尾或剪映引用更长的加速前素材都阻断。Agent 收到
interrupts_source_sentence / unsafe_clip_sentence_boundary / no_safe_fit /
timeline_audio_mismatch 时，应移动边界、缩短整句或删除该块，而不是增加抢断 override；
unsafe_clip_sentence_boundary 附带的 nearest_safe 给出前后最近的安全边界时间。
4.3 多视频与素材库
多视频只支持 cut 模式。项目 brief 会列出稳定的 source_id，clip_plan.json 中每个片段都必须填写来源：
python3 scripts/recap.py ep1.mp4 ep2.mp4 --edit-mode cut --target-duration 10m --work-dir work_dir_multi_ep第二阶段与单视频一样生成剪后故事板 storyboard/edited_storyboard.*，取自各来源 sources/<source_id>/frames/，brief 顶部列出 S1/S2… 对应的 source_id；素材库恢复的来源没有抽帧，这些片段不出现在故事板里，用 inspect clip-map 核对。
可选文件系统素材库：
python3 scripts/recap.py ep1.mp4 --material-library-dir .video-materials --save-materials
python3 scripts/recap.py ep1.mp4 ep2.mp4 --edit-mode cut --material-library-dir .video-materials --use-materials素材检索只是对 JSON / MD / JSONL 做 grep，例如 grep -R "keyword" .video-materials。当前版本不复制原始媒体，也不提供数据库、向量或语义搜索。
同一根目录还可以登记可复用的资源（BGM、音效、音色、字体、图片）、带版本与采用记录的模板（字幕样式、包装图层、制作参考）和样片。
格式与 scripts/library.py check|list|show 只读工具见 references/resource-library.md。用 --project recap_project.json 把已采用的字幕样式、包装、制作参考、音色与 BGM 绑定到这次运行；
每次 full / cut 合成后 work_dir/resource_lock.json 记下实际用到的资源与授权状态。
Show full SKILL.md (192 more words)Show less
4.4 继续生成成片
写好所需产物后，重复同一条命令：
python3 scripts/recap.py <video> --work-dir <work_dir> # 可追加 --edit-mode cut / --no-burn-subtitles流程会校验当前阶段的硬输入（clip_plan.json / narration.json）；两份创作计划仍是 Agent 与建议型评审使用的工作记录，不是渲染门禁。cut 模式随后生成 edited_source.mp4，再合成旁白并输出 recap_<name>.mp4。
校验从不改写解说稿（只更新实测的 overlaps_speech）；full 模式下文本装不下时间窗会以 over_budget error 退回给 Agent。已有批准解说稿时加 --preserve-approved-text，TTS 也原样保留批准稿，装不下时间窗即失败，不缩稿、不降级为部分成功。
4.5 字幕与克隆旁白
若要把旁白字幕固定在原片字幕区域，先在仓库根目录运行：
python3 tools/measure_subtitle.py <video>再传入测得的 --subtitle-y-top/--subtitle-y-bot。坐标基于 ffmpeg 自动旋转后的显示画布，区间为半开 [top, bot)，并要求底对齐 ASS 样式；显式设置后，该区域默认使用 60% 透明度的旁白窗口遮罩。
解说模式如需克隆参考声音，使用 --voice-ref <audio>；它与 dub 模式不同。
4.6 最终观看与交付复核
脚本、接点检测、样帧和 QC 报告都不能替代观看。每轮准备交付前，必须检查本轮实际要交付的最终文件，而不是旧别名、无字幕母版或中间代理：
- 正常速度完整播放一次短片，不边看边改；先记录真实观看问题。
- 播放每个拼接点前后约 0.5–1 秒，检查闪帧、原片叠化被截断、动作跳变和半句原声。
- 完整只听声音一次，检查旁白是否碎成一句一停、场景间声音是否接得上、关键原声是否完整。
- 单独复看开头、核心情绪/表演点和结尾，确认进入时机、回报停留和收束都成立。
- REVISION 分别验证本轮修改项已经改变、冻结项没有意外变化；然后再做解码、时长、音画规格等机械检查。
scene score、亮度统计、contact sheet 与自动 QC 只负责定位候选问题；最终判断以真实播放为准。密集切点的来源判断与处理规则按剪辑技能执行。修复失败时回到剪点、声音或文案层，不用更多包装掩盖。
full/cut 交付如需让确定性的最终检查影响命令退出状态，显式传
--require-final-qc。只有 final_qc.json 的摘要为 ok: true 且整数
blocker_count: 0 才打印完成并返回成功；缺失、畸形或 blocker
会保留报告和已渲染诊断媒体，但命令非零退出且不打印完成。默认仍是仅报告、不阻断。
该参数不支持 --edit-mode dub；dub 未传该参数时的准备和渲染行为不变。
交付时读 final_qc.json 的 metadata.warnings，有内容就原样告诉用户，不能只报“完成”。subtitle_burn_degraded
表示 ffmpeg 缺 libass、默认烧录被降级：成片里没有字幕，字幕在成片旁的同名 .srt。用户要烧录字幕，就请他装带 libass 的
ffmpeg 后重跑；显式传 --burn-subtitles 时缺 libass 会在开跑前报错。旁白里写了 visual_overlays 而 ffmpeg 缺
drawtext 时，流程在配音前停下，按报错删掉叠加或换 ffmpeg 后续跑。
4.7 不需要解说的片子
# 对当前整段输入直接合成；不隐式跑理解/ASR/TTS
python3 scripts/recap.py locked_picture.mp4 --work-dir source_work --audio-mode source-mix
# 剪辑计划仍按 cut 流程产生，剪完不再暂停等待 narration.json
python3 scripts/recap.py ep1.mp4 ep2.mp4 --edit-mode cut --work-dir cut_work --audio-mode source-mix
# 只换包装时冻结当前整片 AAC；不允许同时加 BGM/TTS
python3 scripts/recap.py adopted.mp4 --work-dir packaging_work --audio-mode adopted-packet-copysource-mix 仍会混音和重编码；cut + adopted-packet-copy 冻结的是剪后中间片的声音，不是原片的 AAC 包。
当前严格字幕轨只支持 adopted 模式；其他字幕来源没有因此变成精确对齐。切换声音模式须新工作目录，不得把旧 TTS、QC 或自动生成的解说花字混入本轮原声生产。细节见 references/audio-routing.md。
5. 英译中原声复刻模式
--edit-mode dub 是实验功能：把英文视频翻译为中文，并用原说话者的克隆音色替换人声；它不是在压低原声上叠加解说。只在用户明确要求英译中配音时使用。
dub 会把源视频音轨分窗发给 MiMo ASR 转写，并把截取的约 10 秒原说话人声音作为参考，连同每句译文发给 MiMo voiceclone。因此必须带 --confirm-voice-rights：先向用户确认他有权使用这段视频与音频、且说话人同意被克隆声音，确认后才加这个参数；缺少时启动即报错，不抽音频、不发请求。该参数只用于 dub，其他模式传入会报错。
python3 scripts/recap.py <video> --edit-mode dub --confirm-voice-rights --work-dir <work_dir>准备阶段会转写英文、提取一段参考音频，并写出 dub_brief.md 与 dub_transcript.json。Agent 按 dub_brief.md 里的翻译要求（逐句忠实、时间窗、语速）写 dub_script.json：
[{"start": 0.0, "end": 2.0, "zh": "中文译文"}]重复同一命令后先做确定性 lint（dub_lint.json，空行、重叠、越界即中止），再输出 dub_<name>.mp4。每句单独克隆并贴回原时间线；只有即将覆盖下一句时才局部加速。当前版本只支持单说话者、整轨替换，不分离背景音乐。
6. 自检与只读 dashboard
python3 scripts/recap.py --doctor6.1 只读 dashboard
python3 scripts/dashboard_server.py --root <目录> [--port 0] [--open]前台运行并打印本机地址（只绑定 127.0.0.1，Agent 启动时放到后台）。它在 --root 下按 library.json、recap_project.json、
recap_run_manifest.json 发现资源库、项目与运行，按阶段显示剪辑节奏、旁白、成片与时间线、QC 和 resource_lock.json。
严格只读：只接受 GET / HEAD，不写任何文件；页面上的「复制给助手」只复制一句请求，改动回到对话里做。
7. 输出与参数
主要输出：
recap_<video>.mp4：最终成片。subtitles.srt/subtitles.ass：字幕。work_dir/：全部中间产物，契约见references/data-schema.md。work_dir/recap_story_plan.json/visual_audio_board.json：Agent 创作意图与剪辑决定。
完整参数列表以 python3 scripts/recap.py --help 为准。--style 是原样传给 Agent 的自由文本指导，不是 preset、枚举、开关或有限风格分类。
8. 能力边界
- 语义评审默认建议型、失败开放；只有调用方显式启用严格解说评审时，事实矛盾、残句或评审不可用才会在 TTS 前阻断。确定性校验阶段始终负责硬校验。
- 宣发标题、花字或外部文案回填见
video-script的 references/promotional-copy.md。
© zenstory-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 33 other files (scripts, references, assets) in skills/video-recap of zenstory-ai/video-recap-skills.
- SKILL.md
- assets/dashboard/app.js
- assets/dashboard/index.html
- assets/dashboard/styles.css
- assets/dashboard/tokens.css
- assets/dashboard/views.js
- references/audio-routing.md
- references/config-playbook.md
- references/data-schema.md
- references/resource-library.md
- scripts/dashboard/__init__.py
- scripts/dashboard/data.py
- scripts/dashboard/io.py
- scripts/dashboard/runs.py
- scripts/dashboard/templates.py
- scripts/dashboard_server.py
- … and 18 more
Open the folder on GitHubat commit 5391686
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in zenstory-ai/video-recap-skills, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Video Recap next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Video Recap this skillzenstory-ai/video-recap-skills | 561 | — | ~2.4k | Automated safety check: Pass | MIT | |
| MoneyPrinterTurbo Video Generatorharry0703/MoneyPrinterTurbo | 130k | — | ~2.1k | Automated safety check: Warn | MIT | |
| HyperFrames Media Useheygen-com/hyperframes | 60k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Openspec OnboardSAP/e-mobility-charging-stations-simulator | 227 | 25 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Blog AudioAgriciDaniel/claude-blog | 2.3k | 1 repos | ~2.2k | Automated safety check: Notes | MIT | |
| Musictadaspetra/loop | 296 | 2 repos | ~827 | Automated safety check: Pass | MIT |
Similar skills
HyperFrames Media Use
heygen-com/hyperframes
Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.
- Official
Openspec Onboard
SAP/e-mobility-charging-stations-simulator
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
Blog Audio
AgriciDaniel/claude-blog
Generate audio narration of blog posts using Google Gemini TTS.
Music
tadaspetra/loop
Generate music using ElevenLabs Music API. An agent skill from tadaspetra/loop.
Create News Video
hoquanghai/Auto-Create-Video
Tạo video tin tức ngắn 9:16 (~60s) từ URL bài báo hoặc file .txt tiếng Việt.
More from zenstory-ai/video-recap-skills
Video Assemble
zenstory-ai/video-recap-skills
合成视频解说最终成片：把旁白音频铺到源视频上，按旁白窗口压低原声，生成 SRT / ASS 字幕并可烧录， 最后做响度标准化。作为最终合成阶段使用。输入源视频、ttsmeta.json 与旁白位置； 输出 recap 成片和字幕。触发词：视频合成、混音、字幕、压字幕、assemble video、mux、ducking、subtitles、成片。
Video Cut
zenstory-ai/video-recap-skills
把长视频按 Agent 选择的原片区间剪成短片。作为两阶段创作流程中的剪辑环节，读取 clipplan.json 与源视频， 输出 editedsource.mp4；随后 Agent 按输出时间线写 narration.json。支持单视频与多视频（sources manifest）拼剪， 本工具不读取、不映射旁白。
Video Reference
zenstory-ai/video-recap-skills
按需把一部成片拆成可复用的制作参考：测镜头节奏与响度，标注段落与音轨分工，把原片事实与可迁移方法分开， 导出不含原片人名台词的 productionreference.json 供下次制作参考。不在默认生产路径上。
Video Script
zenstory-ai/video-recap-skills
对已完成分析的视频进行导演与剪辑策划，再写带时间戳的中文解说并校验；也处理已有短片的 宣发标题、花字修订和外部文案回填。普通策划输入 workdir 的 agentnarrationbrief.md 与 vlmanalysis.json；文案返修输入当前成片的工程与内容证据。策划输出 recapstoryplan.json、visualaudioboard.json、 可选…
Video Understanding
zenstory-ai/video-recap-skills
把视频分析为结构化理解索引：场景检测、ASR 转写、逐场景 VLM 观察、静音窗口、融合时间线和写作 brief. An agent skill from zenstory-ai/video-recap-skills.
Video Voiceover
zenstory-ai/video-recap-skills
把带时间戳的 narration.json 合成为中文解说音频。使用 MiMo TTS（mimo-v2.5-tts）或 Fish Audio（s2.1-pro-free）或显式配置的通用 IndexTTS HTTP 服务逐段生成语音， 按时间窗动态适配语速并处理响度；输入输出时间线上的旁白，产出 ttssegments 与 ttsmeta.json。
Related
Categories
Questions about Video Recap
What does Video Recap do?
从输入视频生成中文解说成片或原声剧情短片。用户提供 .mp4 / .mov / .mkv / .webm，并要求剪辑、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…. Video Recap is an agent skill from zenstory-ai/video-recap-skills.
When should I use Video Recap?
Video Recap fits situations like: tasks that involve Text to speech and voice.
How do I install Video Recap in Claude Code?
Run `npx skills add zenstory-ai/video-recap-skills --skill video-recap -a claude-code`. Or copy the skill folder (skills/video-recap in zenstory-ai/video-recap-skills) into .claude/skills/video-recap in your project. Claude Code loads it when a task matches its description.
How do I install Video Recap in Codex?
Run `npx skills add zenstory-ai/video-recap-skills --skill video-recap -a codex`. Or copy the skill folder (skills/video-recap in zenstory-ai/video-recap-skills) into .agents/skills/video-recap in your project. Codex loads it when a task matches its description.
Can I use Video Recap in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zenstory-ai/video-recap-skills --skill video-recap -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/video-recap, .gemini/skills/video-recap, .github/skills/video-recap and .opencode/skills/video-recap in your project.
What does Video Recap need to run?
Going by SKILL.md and its folder, Video Recap needs Python and JavaScript for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named MIMO_API_KEY. Our summary lists: Python 3; Node.js; A credential in MIMO_API_KEY.
Does Video Recap access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Video Recap safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Video Recap use?
Video Recap is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Video Recap use?
About 2.4k tokens (SKILL.md is roughly 9.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 17k tokens, read only when the agent opens those files.
What are the alternatives to Video Recap?
Skills that share tags, products or a category with Video Recap: MoneyPrinterTurbo Video Generator (harry0703/MoneyPrinterTurbo, 130k stars), HyperFrames Media Use (heygen-com/hyperframes, 60k stars), Openspec Onboard (SAP/e-mobility-charging-stations-simulator, 227 stars) and Blog Audio (AgriciDaniel/claude-blog, 2.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Video Recap?
zenstory-ai (a GitHub organization) maintains it in zenstory-ai/video-recap-skills, which has 561 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 4, 2026.
Source: zenstory-ai/video-recap-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.