一键在 Manus 中运行任何 Skill

render-editorial-motion-podcast

星标1,046

分支193

更新时间2026年7月17日 11:45

Assemble an editorial-motion podcast-clip ad from a config — a real clipped podcast MP3 carries the narrative while N flat 2-tone editorial-illustration keyframes are animated NOT by generative i2v but by DETERMINISTIC ffmpeg ken-burns (zoompan) + hard cuts (no crossfades, which expose geometric drift), each beat snapped to its spoken line, the real audio muxed, Whisper-driven captions burned only mid-sentence, and closed on a PIL brand end card — never AI-rendered text. This is the FREE deterministic assembly stage (ffmpeg ken-burns + hard concat + audio mux + captions + end card); the real audio is clipped from source and the keyframes come from create-image-fal. Use for the editorial-motion-podcast format.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

gooseworks-ai

gooseworks-ai/goose-skills

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

render-editorial-motion-podcast

Assemble an editorial-motion podcast-clip ad from a config: a real clipped podcast audio line carries the whole narrative and every visual beat is timed to the sentence it describes, in a bold flat 2-tone editorial-illustration look ("a New Yorker spot-illustration that moves"). The motion is not generative video but deterministic ffmpeg ken-burns on static keyframes, so it reads as a printed page that moves. This capability is that FREE, deterministic assembly — the ffmpeg motion, hard-concat, audio mux, caption burn, and PIL end card.

scripts/config.example.json is the worked example (Klarify "Rat Park", ~40.8s 1080×1920 9:16, 6 beats); scripts/PIPELINE.md maps every config block to its source step and scripts/README.md documents the free assembly.

Run

This is the FREE, deterministic assembly stage — it spends nothing on the motion layer. The paid inputs are separate: the real podcast MP3 is clipped from source (free ffmpeg) with its Whisper word timings, and one editorial-illustration keyframe per beat (chained ref images so cage/character geometry holds) comes from create-image-fal (Nano Banana). Given the clipped audio + words.json + the per-beat keyframes + the real brand wordmark PNG, render-editorial-motion-podcast renders each keyframe as a ken-burns segment, hard-concats on the beat, muxes the real audio, burns the mid-sentence captions, and composites the PIL end card → the master. Re-cuts reuse the existing audio / keyframes and cost $0.

Contract (the free assembly)

A spoken narration carries the whole spot — no generated SONG. Mux the provided narration MP3 (-map 0:v:0 -map 1:a:0) — a real clipped podcast line (preferred) OR an approved generated VO (create-vo-elevenlabs). Never a sung/generated track. (Clip-vs-generate is the recipe's STEP-0 intake decision — if no source episode is supplied, ASK the user.)
NO generative i2v — deterministic ffmpeg ken-burns only. Animate each static keyframe with zoompan (push-in / pull-back, 1.0→~1.06×, 24fps); Seedance/Kling are photoreal-trained and invent naturalistic middle states that collapse the 2-tone look. Never -loop 1 with zoompan d=N (it balloons the duration); feed a single image and clamp with -t + trim.
Hard cuts on the beat — no crossfades. Crossfades ghost two drifting cages through each other; hard-concat each beat's segments and split long beats into micro-cuts (target 8–10 distinct visual moments). Each beat's visual STARTS within ~0.5s of its spoken line.
Captions from Whisper word-timestamps, ON only mid-sentence. Burn frosted-subtle captions while the speaker talks; leave silent/reflective beats and the end card uncaptioned. THREE mandatory rules (each bit us in prod — bake them in):
1. NON-OVERLAP — clamp every line to END before the next STARTS (end = min(last_word_end + ~0.15, next_start - 0.03)). Two boxes must never stack at the same spot; an end-tail bleeding into the next window is the #1 caption bug.
2. SAFE AREA — captions sit in the lower third, so the keyframe's subject must stay in the upper ~75% (see the recipe's look_pack.caption_safe_area). If a finished keyframe's subject intrudes into the caption band, deterministically shift the subject UP into the empty top space (PIL: paste up ~0.24H onto a canvas pre-filled with the exact paper color from a clean corner) — never let the box sit on the subject.
3. BURN ENGINE — prefer libass (ass/subtitles filter), but check ffmpeg -filters first: many builds (Homebrew) lack libass/drawtext. If absent, use the deterministic overlay fallback — render each line as a transparent PNG (frosted rounded box + white text, PIL) and composite via the ffmpeg overlay filter with timed enable='between(t,st,en)' windows. Same look, no libass.
End card via PIL from the real wordmark PNG — never AI-render brand text. The lockup is composited deterministically (stretched-gradient bg + feathered mascot crop + wordmark + tagline with a system font); a diffusion model garbles a wordmark ("therapits"). The video runs a ~1.5s silent hold past the audio on the end card (fade first/last 0.3s).
FFmpeg composite, deterministic, FREE. Ken-burns each keyframe, hard-concat, mux the real audio, burn the captions, hold on the end card → a 1080×1920 h264+aac master. No paid calls.

同仓库更多 Skills

同仓库

create-image-gpt-image-fal

gooseworks-ai/goose-skills

Generate a single photoreal or designed image with OpenAI gpt-image via fal.ai. Supports gpt-image-1 (default, fixed sizes — the FAL fallback for Higgsfield's `gpt_image_2`) and gpt-image-2 (`openai/gpt-image-2`, custom output sizes up to 3840px). Routes to text-to-image or the edit variant depending on whether a reference image is provided. Use for photoreal character anchors, scene keyframes, and designed sheets (e.g. storyboards) where precise layout and legible text matter.

2026-07-191.0k

render-cartoon-music-video

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.

2026-07-191.0k

render-cosmic-mythology-voiceover

gooseworks-ai/goose-skills

Assemble a cosmic-mythology-voiceover reel from a config — a warm spoken voiceover carries the whole narrative while N curated cosmic stills are weighted beat-synced across the delivered VO duration (cut_dur = VO_dur times weight over the weight sum, so emotional beats hold longer), Ken-Burns-zoomed per still (scale 2x, center crop, zoompan, fade-in first and fade-out last), ffmpeg-concatenated, the VO composited under the picture (libx264 crf18 plus aac), the ONE on-screen hook line faded on over the open with a drawtext alpha window, and Whisper/VEED captions burned along the bottom — never in-world text on a still. This is the FREE deterministic assembly stage (weighted sequence plus Ken-Burns plus concat plus VO composite plus hook overlay plus caption burn); the VO and the stills come from create-vo-elevenlabs and create-image-fal. Use for the cosmic-mythology-voiceover format.

2026-07-191.0k

render-creator-pip-listicle

gooseworks-ai/goose-skills

Assemble a creator picture-in-picture product-listicle ad from a config — the creator stays FULL-FRAME the whole beat (voice plus lips generated together per beat, no separate VO, no cut to a full-frame product shot), and on each product beat three persistent overlays ride on top for the WHOLE beat — a title pill top-center, the DEMO in a rounded PiP window top-right (the brand's real UGC clip MUTED, or for a no-UGC brand the product's own autocropped UI still / screen-recording sized to fill the window), and a bottom product card (rounded thumbnail plus 'N · CATEGORY' small-caps plus product NAME in a serif face). Hook plus CTA beats are the creator full-frame with the title pill only. Assembly builds ONE full-1080x1920 transparent overlay PNG per beat, overlays it on the creator clip (cover-scaled to 1080x1920) for the whole beat keeping the native audio, concats all beats, then burns captions LAST as timed PIL PNG overlays (this ffmpeg has no libass) timed deterministically from the known per-beat script.

2026-07-191.0k

render-food-product-sizzle

gooseworks-ai/goose-skills

Assemble a wordless macro-tabletop food-product sizzle ad from a config — normalize fps and SAR across ~4 photorealistic macro clips (hands tearing, flat lay, bite, box hero), concat them, apply a global anti-AI grain pass (eq plus hqdn3d plus noise), composite the audio (a non-diegetic acoustic music bed plus a couple of short diegetic SFX like a snap and a tear placed at measured cue points, loudnorm), composite a STATIC end card entirely in PIL (real logo PNG plus real product PNG plus a serif heritage headline plus a CTA — never AI-rendered text), and burn optional serif stat-callout pills at beats. This is the FREE deterministic assembly stage (normalized concat plus grain plus music and SFX mix plus PIL end card plus callouts); the macro keyframes, i2v clips, and music bed come from create-image-fal, create-video-fal, and create-music-elevenlabs. Use for the food-product-sizzle format.

2026-07-191.0k

render-split-screen-creator

gooseworks-ai/goose-skills

Assemble a split-screen creator ad from a config — a two-zone vertical composite where a supplied AI-creator lip-sync take fills the BOTTOM ~48% while real 16:9 product/demo clips run uncropped in the TOP ~52%, each top clip contain-fit with a darkened blurred cover-scale fill of the same clip (never black bars), a 3px brand-color divider between the zones, the creator slice cover-fit per the per-scene VO timing, scenes hard-concatenated with the body audio being the concatenated creator VO slices, an end card held on the last sharp frame ~3s, then the ASSEMBLED cut transcribed with local Whisper (not the raw VO — concat drops inter-scene silence) and word-level captions burned in the chosen style. This is the FREE deterministic assembly + caption stage (two-zone composite + blurred fill + divider + hard-concat + end card + captions); the VO comes from create-vo-elevenlabs, the anchor from create-image-gpt-image-fal, and the whole-VO lip-sync from a paid VEED Fabric 1.0 take (a no-atom upstream input). Use fo

2026-07-191.0k

name	render-editorial-motion-podcast
description	Assemble an editorial-motion podcast-clip ad from a config — a real clipped podcast MP3 carries the narrative while N flat 2-tone editorial-illustration keyframes are animated NOT by generative i2v but by DETERMINISTIC ffmpeg ken-burns (zoompan) + hard cuts (no crossfades, which expose geometric drift), each beat snapped to its spoken line, the real audio muxed, Whisper-driven captions burned only mid-sentence, and closed on a PIL brand end card — never AI-rendered text. This is the FREE deterministic assembly stage (ffmpeg ken-burns + hard concat + audio mux + captions + end card); the real audio is clipped from source and the keyframes come from create-image-fal. Use for the editorial-motion-podcast format.
status	active

render-editorial-motion-podcast

Run

Contract (the free assembly)

A spoken narration carries the whole spot — no generated SONG. Mux the provided narration MP3 (-map 0:v:0 -map 1:a:0) — a real clipped podcast line (preferred) OR an approved generated VO (create-vo-elevenlabs). Never a sung/generated track. (Clip-vs-generate is the recipe's STEP-0 intake decision — if no source episode is supplied, ASK the user.)
NO generative i2v — deterministic ffmpeg ken-burns only. Animate each static keyframe with zoompan (push-in / pull-back, 1.0→~1.06×, 24fps); Seedance/Kling are photoreal-trained and invent naturalistic middle states that collapse the 2-tone look. Never -loop 1 with zoompan d=N (it balloons the duration); feed a single image and clamp with -t + trim.
Hard cuts on the beat — no crossfades. Crossfades ghost two drifting cages through each other; hard-concat each beat's segments and split long beats into micro-cuts (target 8–10 distinct visual moments). Each beat's visual STARTS within ~0.5s of its spoken line.
Captions from Whisper word-timestamps, ON only mid-sentence. Burn frosted-subtle captions while the speaker talks; leave silent/reflective beats and the end card uncaptioned. THREE mandatory rules (each bit us in prod — bake them in):
1. NON-OVERLAP — clamp every line to END before the next STARTS (end = min(last_word_end + ~0.15, next_start - 0.03)). Two boxes must never stack at the same spot; an end-tail bleeding into the next window is the #1 caption bug.
2. SAFE AREA — captions sit in the lower third, so the keyframe's subject must stay in the upper ~75% (see the recipe's look_pack.caption_safe_area). If a finished keyframe's subject intrudes into the caption band, deterministically shift the subject UP into the empty top space (PIL: paste up ~0.24H onto a canvas pre-filled with the exact paper color from a clean corner) — never let the box sit on the subject.
3. BURN ENGINE — prefer libass (ass/subtitles filter), but check ffmpeg -filters first: many builds (Homebrew) lack libass/drawtext. If absent, use the deterministic overlay fallback — render each line as a transparent PNG (frosted rounded box + white text, PIL) and composite via the ffmpeg overlay filter with timed enable='between(t,st,en)' windows. Same look, no libass.
End card via PIL from the real wordmark PNG — never AI-render brand text. The lockup is composited deterministically (stretched-gradient bg + feathered mascot crop + wordmark + tagline with a system font); a diffusion model garbles a wordmark ("therapits"). The video runs a ~1.5s silent hold past the audio on the end card (fade first/last 0.3s).
FFmpeg composite, deterministic, FREE. Ken-burns each keyframe, hard-concat, mux the real audio, burn the captions, hold on the end card → a 1080×1920 h264+aac master. No paid calls.