Communitygithub.com

gooseworks-ai/goose-skills

根据配置组装编辑动感播客片段广告:真实的播客MP3承载叙述,配合扁平有限色调的编辑插图关键帧,通过确定性ffmpeg ken-burns动画和硬剪切,将每个节拍与台词对齐。

goose-skills 是什么?

这个技能(gooseworks-ai/goose-skills)实现了一个完整的“编辑动感播客片段”广告组装流水线。它接收一个配置文件,其中定义了播客音频、每句台词的Whisper时间戳、每节拍的关键帧图像以及品牌logo,然后完全通过确定性ffmpeg操作(无生成式AI视频)输出最终视频。用户提供真实的播客剪辑音频和通过 `create-image-fal` 生成的有限色调编辑插图关键帧,该技能负责执行ken-burns缩放动画、在节拍处进行硬剪切(无交叉淡化)、将真实音频混流、仅在句子中间烧录字幕(基于Whisper词级时间戳,并遵循严格的不重叠和安全区域规则),最后通过PIL合成品牌结束卡片。整个过程完全免费且可复现,重新剪切时无需额外成本。支持的平台包括任何可以调用命令行ffmpeg和Python PIL的环境,如Claude Code或自定义脚本。该技能解决了传统生成式视频(如I2V)无法保持扁平插图画风一致性的问题,通过确定性动画实现“会动的印刷页面”效果。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/gooseworks-ai/goose-skills/tree/HEAD/skills/ads/capabilities/render-editorial-motion-podcast

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

render-editorial-motion-podcast

根据配置组装一个编辑动感播客片段广告:真实的播客音频剪辑 承载整个叙述,每个视觉节拍都精确对应它所描述的句子, 采用单一的、严格限制色调的编辑插图风格包(“一幅会动的杂志 插画”——风格和色调由调用者选择)。动画不是生成式视频, 而是对静态关键帧进行确定性的ffmpeg ken-burns处理, 使其看起来像一张会动的印刷页面。本功能就是那个免费、 确定性的组装过程——包含ffmpeg运动、硬连接、音频混流、 字幕烧录和PIL结束卡片。

scripts/config.example.json 是工作示例(Klarify “Rat Park”, 约40.8秒,1080×1920 9:16,6个节拍——其双色调Niemann风格、 奶油色/炭黑色/鼠尾草色调以及Rat Park隐喻是该演示的选择, 绝非默认值);scripts/PIPELINE.md 将每个配置块映射到其 源步骤,scripts/README.md 记录了免费组装过程。

选择

创意决策由调用者决定(视频格式配方会询问用户);本组装 从不自行选择。演示的价值仅在于提供一个示例:

  • 插图风格 — 演示:大胆的扁平双色剪影,半色调(Niemann / Steinberg 流派)。
  • 色调 — 演示:奶油色 #F4EBD9 + 炭黑色 #1A1A1A + 一个鼠尾草绿 #86987A 强调色。
  • 核心隐喻 — 演示:Rat Park 研究。
  • 语调 / 声音 — 演示:温暖而反思,真实的播客主持人(无生成语音)。

运行

这是免费、确定性的组装阶段——在运动层上不花费任何成本。 付费输入是分开的:真实的播客MP3从源文件剪辑而来(免费ffmpeg), 附带其Whisper词时间戳,每个节拍对应一张编辑插图关键帧 (通过链式参考图像保持笼/角色几何结构)来自 create-image-fal (Nano Banana)。给定剪辑音频 + words.json + 每节拍关键帧

  • 真实品牌文字标记PNG,render-editorial-motion-podcast 将每个关键帧渲染为ken-burns片段,在节拍处硬连接,混流真实音频, 在句子中间烧录字幕,并合成PIL结束卡片 → 主视频。 重新剪切时使用已有的音频/关键帧,成本为0美元。

约定(免费组装)

  • 语音叙述承载整个广告——不能使用生成的歌曲。 混流所提供的 叙述MP3(-map 0:v:0 -map 1:a:0)——可以是真实的播客 剪辑片段(首选)或经批准的生成VO(create-vo-elevenlabs)。 绝不能使用演唱/生成曲目。(剪辑vs生成由配方的STEP-0摄入决策 决定——如果未提供源剧集,则询问用户。)
  • 不能使用生成式i2v——仅使用确定性的ffmpeg ken-burns。 用 zoompan(推近/拉远,1.0→约1.06倍,24fps)对每个 静态关键帧进行动画处理;Seedance/Kling 使用照片级训练数据, 会创造出破坏扁平有限色调风格的自然主义中间状态。 绝不能使用带 zoompan d=N 的 -loop 1(会使时长膨胀); 传入单张图像并用 -t + trim 进行钳制。
  • 在节拍处硬剪切——不能使用交叉淡化。 交叉淡化会让两个 漂移的笼子相互叠影;对每个节拍的片段进行硬连接, 并将长节拍拆分为微剪切(目标8–10个不同的视觉时刻)。 每个节拍的视觉在其对应语音台词约0.5秒内开始。
  • 字幕来自Whisper词时间戳,仅在句子中间显示。 在说话者讲话时烧录 frosted-subtle 字幕; 让静默/反思节拍和结束卡片保持无字幕。 三条强制规则(每一条都在生产环境中咬过我们——务必牢记):
    1. 不重叠 — 将每一行钳制到下一行开始时结束 (end = min(last_word_end + ~0.15, next_start - 0.03))。 两个盒子绝不能同时堆叠在同一位置;结束尾部渗入下一个 时间窗口是#1字幕错误。
    2. 安全区域 — 字幕位于下方三分之一处,因此关键帧的 主体必须保持在上方约75%区域(请参见配方的 look_pack.caption_safe_area)。如果已完成的关键帧的 主体侵入字幕带,则确定性地将主体向上移动到空白 顶部空间(PIL:向上粘贴约0.24H到预先填充了来自干净边角 的精确纸张颜色的画布上)——绝不能让字幕框位于主体上。
    3. 烧录引擎 — 优先使用libass(ass/subtitles 滤镜), 但首先检查 ffmpeg -filters:许多构建(如Homebrew) 缺少libass/drawtext。如果缺失,使用确定性的覆盖回退 — 将每一行渲染为透明PNG(磨砂圆角框+白色文字,PIL), 并通过带有时控 enable='between(t,st,en)' 窗口的 ffmpeg overlay 滤镜进行合成。同样外观,无需libass。
  • 通过PIL使用真实文字标记PNG生成结束卡片——绝不能使用 AI渲染品牌文字。 标志组合是确定性合成的(渐变背景 + 羽化吉祥物裁剪 + 文字标记 + 系统字体标语);扩散模型 会破坏文字标记(例如“therapits”)。视频在结束卡片上 比音频多停留约1.5秒(前/后各淡出0.3秒)。
  • FFmpeg合成,确定性,免费。 对每个关键帧进行ken-burns 处理,硬连接,混流真实音频,烧录字幕,停留在结束卡片上 → 生成1080×1920 h264+aac主视频。无需付费调用。

Individual skills in this repo

This repo contains 10 individual skills — each has its own dedicated page.

gooseworks-ai/goose-skills

Burned-in captions for a finished vertical video, three kinds. transcribe.py gets word timings from the video's own audio through the GooseWorks proxy (fal Whisper, bills the Ads agent, cents); captions.py burns one to three words at a time with Pillow + ffmpeg (no libass needed), either pinned to a split-screen seam (plate 25% above / 75% below) or at a fixed height, in a plate, outline or one-word serif style, with an optional red hook card; plates.py burns per-beat caption blocks (black, one union silhouette, placed in the emptiest band) for formats with no voice. The last caption (the CTA) holds to the final frame. Use as the last step of any video ad.

gooseworks-ai/goose-skills

Assemble a cartoon / animated / hand-crafted music-video ad from a config — a sung song carries the whole narrative while N per-bar i2v clips (one recurring animated character, one look pack) are each cut to their BAR window from librosa beat-tracking and hard-concatenated on the bar, VEED-whisper white bold-sans captions in the BOTTOM third (Alignment 2, above the logo bug, no pill) burned from the song's word timings re-spelled against the locked lyrics, a persistent brand logo bug held over the body (suppressed on the end card), and closed on a solid-brand-color PIL end card with the song still playing under it — never AI-rendered text. This is the FREE deterministic assembly stage (cut-to-bar + hard concat + logo bug + captions + end card + song mux); the song, character, keyframes, and clips come from create-music-elevenlabs / create-image-fal / create-video-fal. Use for the cartoon-music-video format.

gooseworks-ai/goose-skills

Assemble a cinematic live-action-style music-video ad from a config — an original sung anthem carries the whole narrative while N 35mm-film-look i2v clips are each cut to their lyric window and hard-concatenated on the beat as a 3-act arc, the anthem muxed at loudnorm I=-14, cinematic lower-third serif captions built from the song's OWN word timings (never Whisper) with the hook line landing on the chorus drop, and closed on a brand end card composited from the real asset — never AI-rendered text. This is the FREE deterministic assembly stage (cut-to-window + hard concat + anthem mux + captions + end card); the anthem, keyframes, and clips come from create-music-elevenlabs / create-image-gpt-image-fal / create-video-fal. Use for the cinematic-music-video format.

gooseworks-ai/goose-skills

Analyze the message match between your ads and landing pages. Checks if the promise in the ad copy carries through to the landing page headline, body, and CTA. Flags disconnects that kill conversion rates. Works with Google, Meta, and LinkedIn ads.

gooseworks-ai/goose-skills

Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills the Ads agent). The default clip atom for AI-creator UGC ads built on the NB2 + Seedance architecture. Validated on beauty-by-earth/video-01.

gooseworks-ai/goose-skills

Mandatory pre-publish review gate for a UGC video render. Transcribes the finished render's AUDIO with Whisper and word-diffs it against the approved spoken script, then gates set_final_render — blocking a render whose generated audio mis-voices a word (e.g. the approved "human-vetted" spoken as "human witted"), drops an approved phrase, or comes back silent. Runnable, gating counterpart to content-goose's review-transcript-integrity atom. Every ugc-video-formats recipe runs this after render and BEFORE set_final_render.

gooseworks-ai/goose-skills

Render pixel-accurate Apple Notes (iPhone, light mode) screenshot mockups from a JSON note spec. Outputs HTML + PNG at the iPhone 16/15 Pro native 1180×2556. Supports paragraphs, images, checklists, dividers, autocorrect underline, smart quotes, and an optional iOS keyboard chrome overlay used by the parent video-ad molecule.

gooseworks-ai/goose-skills

Extract competitor and customer intelligence from any company's landing page HTML. Discovers tech stack, analytics tools, ad pixels, customer logos, SEO metadata, CTAs, hidden elements, and more. No API keys required.

gooseworks-ai/goose-skills

Find speakers, hosts, and guest profiles at conferences and events on Luma. Two modes - free direct scrape for hosts, or Apify-powered search for full guest profiles with LinkedIn/Twitter/bio.

gooseworks-ai/goose-skills

Find Twitter/X influencers to promote a product or brand. Use when asked to find influencers, discover Twitter accounts for partnerships, identify creators in a niche, or build an influencer outreach list.

相关技能