Skip to content
cccskills
FreePublished on GitHub

auto-short-video

Turn a topic or script into a finished short explainer video with images, narration, subtitles, and optional music. Coordinate the production steps, use supplied assets or generated visuals, and retain intermediate files for later replacement.

OriginalShow the original description

一句话主题 → 成品短视频:自动串联 文案→配图/AI视频→配音→字幕→BGM→合成,把 Easel 制作层零件编排成一条'一键出片'流水线。**单条视频、口播/资讯向,画面默认逐句配图 + Ken Burns 缓动,需要动态时才逐段图生视频**。

当用户说 一键生成视频、自动做短视频、主题生成视频、帮我做条视频、口播视频一条龙、自动出片、短视频一键生成 时使用。**有剧情/角色/对白/反转/多集的短剧改用 short-drama(每镜强制图生视频、不用静态图冒充);只写脚本用 video-script;只生成单个片段用 ai-video-gen。**

See how to install

Good for

  • Creating a short explainer from a topic
  • Turning a narration script into video
  • Combining supplied images and music
  • Replacing assets and assembling the video again

Files included (3)

  • SKILL.md5.8 KB
  • EASEL-META.md1.2 KB
  • scripts/assemble.py37.6 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

一键短视频(端到端编排)

输入一个主题,自动产出一条短视频。本 SKILL 是编排层:把已有制作零件串成流水线—— 文案(video-script) → 逐句配图(ai-image-gen)或片段(ai-video-gen) → 配音(tts-voiceover) → 字幕(auto-subtitle) → BGM(ai-music) → 合成(scripts/assemble.py)。 沉淀自 Pixelle-Video / MoneyPrinterTurbo 的自动短视频引擎思路。

输入

  • 主题 / 文案(必填)
  • 可选:目标时长、风格、是否要配音/字幕/BGM、配图用 AI 生图还是用户素材
  • 画幅确认硬门:用户或上游任务未明确横版/竖版(或 16:9/9:16/具体分辨率)时,制作/付费调用前必须追问并等确认;不得从平台、Profile 或默认值静默推断,已明确则不重复问

输出

成品短视频写入 outputs/主题名/final.mp4;分镜图、配音、字幕和 storyboard 写入 outputs/主题名/assets/。

执行步骤(按需裁剪,缺 API key 的环节自动降级或询问)

  1. 写脚本分镜:用 video-script 把主题写成口播文案,拆成 N 句(每句一个分镜),每句配一个画面描述。

  2. 生成画面(每个分镜一张图/一段片):

    • 有图像 API key → ai-image-gen 逐句 text2img(按已确认画幅)
    • 要动态 → ai-video-gen text2video/image2video
    • 用户自带素材 → 用 image-editing pad 到已确认画幅
    • 都没有 → 按已确认画幅选图卡(竖版用 card-xiaohongshu/poster-hero,横版用 card-quote)再 pad,避免画幅错配。
  3. 配音:tts-voiceover 把文案合成口播(同时出 SRT)。配了 VOICE_PROVIDER 默认走闭源好嗓子(有情感、像真人),没 key 才退 edge(机械)——想要口播不"生硬"务必配闭源 key。不需要配音才跳过。

  4. 字幕:用 TTS 附带的 SRT,或对配音跑 auto-subtitle;也可让 assemble 用各分镜 caption 自动生成。

  5. BGM:ai-music 生成,或用用户提供的音乐。可选。

  6. 合成成片:把上面的素材写成 storyboard JSON,调合成器:

    python skills/builtin/auto-short-video/scripts/assemble.py assemble \
      --storyboard outputs/主题名/assets/storyboard.json \
      -o outputs/主题名/final.mp4
    

    storyboard 结构(图/片二选一,narration/bgm/subtitle 可选,缺 duration 时按配音均分):

    {
      "size": "<已确认尺寸,如1080x1920或1920x1080>",
      "image_motion": "ken-burns",
      "shots": [
        {"image": "outputs/主题名/assets/shot1.png", "duration": 3, "caption": "第一句", "motion": "static"},
        {"video": "outputs/主题名/assets/clip2.mp4", "caption": "第二句"}
      ],
      "narration": "outputs/主题名/assets/voice.mp3",
      "bgm": "outputs/主题名/assets/bgm.mp3",
      "subtitle": "outputs/主题名/assets/voice.srt"
    }
    

    image_motion 设整条图片默认运动,单镜 motion 可覆写:照片用 ken-burns,含文字的 slide/图表/界面必须用 static(等比缩放 + 补边,不裁切、不平移)。 合成器自动做:按 image_motion 生成静帧或 Ken Burns、补边到画幅、拼接、配音+BGM 混音(BGM 自动压低)、烧录字幕。

    长流程可在首次合成时加 --resume,中断后用同样的参数再次运行:

    python skills/builtin/auto-short-video/scripts/assemble.py assemble --resume \
      --storyboard outputs/成都旅行指南/assets/storyboard.json \
      -o outputs/成都旅行指南/final.mp4
    

    已完成镜头在输入参数、素材内容和产物摘要均匹配时复用;修改素材、时长、画幅、运动方式或渲染器会失效。 检查点存于成片旁的 .final.mp4.checkpoints/,不重复生成图片/视频、不调用付费 API。 拼接、混音和字幕每次重新执行;失败时保留上一份成片。未加 --resume 时仍使用原有临时目录流程。 清单损坏会报错,不自动清空;仅在确认相关进程全部退出后才能人工清理检查点目录。

  7. 交付:产出 final.mp4,附一句制作说明(用了哪些环节、哪些降级了)。

编排原则

  • 零件可缺:缺图像/视频/TTS API key 的环节自动降级(图卡兜底 / 跳过配音),不阻断整体,并如实告知用户降级了什么。
  • 先出 Plan:涉及多个付费 API(生图/生视频/生乐)时,先向用户说明将调用哪些、大致耗时/花费,确认后再跑。
  • 中间产物留档:分镜图、配音、字幕和 storyboard 都写进 outputs/主题名/assets/,方便单独替换后重新合成。

Profile 感知

  • 有 Profile:从 style.md 取调性/视觉风格贯穿文案与配图 prompt;platforms.md 只用于给出画幅/时长建议,画幅仍须确认;preferences.md 红线过滤。
  • 无 Profile:先确认横版/竖版,再用通用口播风格。

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

ai-image-gen

FreeSummary

Generate images from written descriptions, transform existing images with editing instructions, or create several variations. Choose image dimensions and quantity, then save the results using an OpenAI-compatible service or apimart with your own API key.

  • Generating an illustration from a written description
  • Changing an image's background using instructions
  • Creating several variations of an existing image
ZJU-REAL/Easel4KUpdated Oct 23, 2026

ai-music

FreeSummary

Generate background music for short videos, vlogs, and social posts from descriptions of mood, style, and instruments. Download MP3 audio, optionally include sung lyrics, and use shared scripts to trim tracks, adjust loudness, or add music to videos.

  • Generating background music for a vlog intro
  • Creating instrumental music to match a social post
  • Generating a sung track from supplied lyrics
ZJU-REAL/Easel4KUpdated Oct 23, 2026

ai-video-gen

FreeSummary

Create new videos from written scene descriptions or still images using external AI services. Set the aspect ratio and duration, animate a character image, and request generated audio when the selected model supports it.

  • Generate a short video from a scene description
  • Animate a still image
  • Create character motion from a starting image
ZJU-REAL/Easel4KUpdated Oct 23, 2026

asset-manager

FreeSummary

Organize generated images, videos, and text in outputs/ by date, platform, and type. Add tags, search filenames and content, produce asset lists and reports, and preview archive moves before applying them to make past work easier to reuse.

  • Organizing generated assets by date, platform, and type
  • Finding past content through keywords and tags
  • Listing assets for a specific account or platform
ZJU-REAL/Easel4KUpdated Oct 23, 2026

audio-denoise

FreeSummary

Reduce background noise in audio recordings or video soundtracks with three processing levels. Keep the original file, create a cleaned version, and receive a report of the settings used and file details before and after processing.

  • Reducing fan or air conditioner noise in recordings
  • Cleaning speech in podcasts and interviews
  • Reducing noise in a video's audio track
ZJU-REAL/Easel4KUpdated Oct 23, 2026

audio-editing

FreeSummary

Edit audio files by trimming sections, converting formats, matching loudness, or extracting sound from videos. You can also join recordings, add fades, and change playback speed while keeping the original pitch.

  • Trim a recording to the section you need
  • Convert audio formats and match loudness
  • Extract audio from a video
ZJU-REAL/Easel4KUpdated Oct 23, 2026

See all skills by ZJU-REAL

Report a problem with this skill