gooseworks-ai/goose-skills / skills/video/render-editorial-motion-podcast
render-editorial-motion-podcast
VerifiedAssemble an editorial-motion podcast-clip ad from a config — a real clipped podcast MP3 carries the narrative while N flat limited-palette editorial-illustration keyframes (one look pack) 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.0 KB |
| scripts/PIPELINE.md | markdown | 6.6 KB |
| scripts/README.md | markdown | 4.7 KB |
| scripts/config.example.json | config | 14.9 KB |
| skill.meta.json | config | 225 B |
| tests/smoke-test.md | markdown | 1.1 KB |
scripts/config.example.json
View on GitHub{
"_comment": "Ironfern 'The Trees With No Wind' editorial-motion podcast-clip ad — the worked example (a fictional demo brand). Copy to config.json and edit. A ~40.8s bold flat 2-tone editorial-illustration (EDITORIAL_2TONE) 9:16 explainer where a REAL podcast audio clip carries the whole narrative (NO generated song, NO AI VO). Pipeline: (1) clip the source episode MP3 to the payoff range + Whisper word timings; (2) one Nano Banana keyframe per beat (9:16, chained ref images off the style anchor, ONE look pack); (3) DETERMINISTIC ffmpeg ken-burns motion + hard-cut concat (NO generative i2v); (4) mux the real audio + frosted-subtle Whisper captions (ON only mid-sentence); (5) PIL brand end card (never AI text). Master 1080x1920, 24fps, h264+aac, ~40.8s. See scripts/PIPELINE.md for the step-by-step map. Creative fields — look_pack (name, palette, style_opener, negative_tail, anchor_keyframe), beats[] (the dome-tree metaphor), and audio.generated_vo (recipe choices illustration_style, palette, central_metaphor, tone, voice) — come from the recipe's choices; never copy them as defaults.",
"brand_name": "Ironfern",
"campaign": "the-trees-with-no-wind",
"title": "The Trees With No Wind",
"width": 1080,
"height": 1920,
"fps": 24,
"duration_sec": 40.8,
"aspect_ratio": "9:16",
"audio": {
"_comment": "This worked example uses a REAL clipped podcast line (NO generated song). Note the format ALSO supports a generated VO when no source episode is supplied — that's the recipe's STEP-0 intake decision (ASK the user; provider 'generated_vo' via create-vo-elevenlabs from a short truthful script). Here the payoff hinges on the host's real cadence at 'we need something to push against.' Clip to the payoff range + a fade-out tail so the host's next sentence doesn't bleed in. THIS AUDIO SETS THE TIMELINE.",
"provider": "podcast_clip",
"source_mp3": "source/podcast-episode.mp3",
"clip_start_sec": 412.0,
"clip_end_sec": 451.8,
"fade_out": { "st_sec": 39.3, "d_sec": 0.5, "_note": "afade=t=out:st=39.30:d=0.5 — cleans the sharp final 'against.' cut and drops the start of the host's next sentence" },
"clipped_output": "audio/podcast-clip-40s.mp3",
"_clip_cmd": "ffmpeg -y -ss 412.0 -to 451.80 -i <source_mp3> -af 'afade=t=out:st=39.30:d=0.5' -c:a libmp3lame -b:a 192k audio/podcast-clip-40s.mp3 -> 39.84s clip ending cleanly on the payoff line",
"transcript": {
"_note": "Default to fal-ai/whisper for podcast-length audio (paid, <30s vs. local whisper 40min+ CPU). Word-level timestamps used to mark each beat's payoff word.",
"provider": "fal",
"model": "whisper",
"word_timestamps": true,
"output": "audio/words.json"
}
},
"look_pack": {
"_comment": "ONE look pack + CHAINED ref images (pass the anchor + any earlier matching frame as an extra --ref-image) is what makes N beats read as one printed set. Independent Nano Banana rolls drift set/character geometry; crossfades then expose it, so hard-cut. Reference: moodboard/style-ref-01.png (Niemann/Steinberg/New Yorker lineage).",
"name": "EDITORIAL_2TONE",
"palette": {
"paper": "#F4EBD9",
"ink": "#1A1A1A",
"accent": "#86987A",
"_note": "STRICT 2-tone — cream paper + charcoal ink + ONE sage accent (on the 'RESISTANCE' label only). No rust, no other colors. Nano Banana sometimes adds ambient warmth (a faint orange lamp glow) unprompted — re-roll if it catches the eye."
},
"style_ref": "moodboard/style-ref-01.png",
"anchor_keyframe": "generated/style-anchor/anchor-dome-1.png",
"style_opener": "Editorial illustration: bold flat 2-tone — solid charcoal-black silhouettes on warm cream off-white paper, thick uniform line weight, halftone-dot shading for depth. Christoph Niemann / Saul Steinberg / New Yorker spot-illustration lineage. Printed-magazine editorial illustration, NOT vector-clean, NOT Kurzgesagt, NOT pen-and-marker. 9:16 vertical with cream negative space.",
"negative_tail": "No color besides cream and charcoal (plus the single sage accent only where specified). No gradients (halftone dots for shading). No vector cleanliness, no motion-graphics-template look, no photorealism. CRITICAL: ABSOLUTELY NO TEXT, NO LETTERS, NO WORDS, NO LABELS anywhere in the image."
},
"keyframe_engine": {
"_note": "create-image-nano-banana-fal. Per beat: prompt = look_pack.style_opener + beats[i].keyframe_prompt + look_pack.negative_tail, --ref-image style_ref --ref-image anchor_keyframe (+ any earlier matching frame). Generate the anchor FIRST and approve it before fanning out. ~26 rolls incl. re-rolls.",
"provider": "fal",
"model": "nano-banana",
"skill": "create-image-nano-banana-fal",
"aspect_ratio": "9:16",
"chain_refs": true
},
"motion_engine": {
"_comment": "NO generative i2v. fal-ai/bytedance/seedance/v1/pro/image-to-video was tried and dropped: it (a) hallucinated photoreal human hands on a drawing beat and (b) morphed flat silhouettes into naturalistic shapes and added stray cartoon elements — Seedance is photoreal-trained and invents naturalistic middle states, collapsing the 2-tone discipline. Retired it, which also cut the paid calls. Deterministic ffmpeg zoompan on static keyframes = 'printed page that moves' + exact timing control.",
"engine": "ffmpeg_kenburns",
"fps": 24,
"render_scale": "2x_then_downscale",
"helpers": {
"render_kb": "push-in ken-burns: scale to 2x, crop, zoompan z=min(zoom+step,zoom_end) 1.0->zoom_end (default 1.04), d=dur*fps, trim=duration",
"render_kb_out": "pull-back ken-burns: zoompan z from zoom_start (default 1.08) down to 1.0"
},
"concat": "hard_cut",
"_concat_note": "Hard cuts on the beat — NO crossfades (they ghost two slightly drifted frames through each other; different pane counts / branch positions). Belt-and-suspenders: NEVER use -loop 1 with zoompan d=N — d runs per input frame per loop, so a 3s target ballooned to 225s. Feed a single image, let zoompan d=<frames> + -t <dur> + trim=duration=<dur> clamp."
},
"beats": [
{
"id": "beat-1",
"role": "HOOK_DOME_REVEAL",
"t_start": 0.0,
"t_end": 3.5,
"audio_line": "I once heard about the trees inside that glass dome",
"payoff_word": "dome",
"caption_on": true,
"keyframe": "generated/style-anchor/anchor-dome-1.png",
"keyframe_prompt": "Subject: a small glass geodesic dome with one tall, thin, perfectly straight tree inside and a tiny sun icon above it. Cream negative space. This is the ANCHOR frame — every later frame chains off it via --ref-image so the dome geometry stays consistent.",
"motion": { "type": "render_kb", "dur": 3.5, "zoom_end": 1.05 }
},
{
"id": "beat-2",
"role": "DECLINE_ARC",
"t_start": 3.5,
"t_end": 11.5,
"audio_line": "they had perfect light and perfect water ... grew tall and then just tipped over",
"payoff_word": "tipped over",
"caption_on": true,
"panels": [
"generated/beat2-consistent/p-tall.png",
"generated/beat2-consistent/p-leaning.png",
"generated/beat2-consistent/p-tilting.png",
"generated/beat2-consistent/p4-fallen.png"
],
"keyframe_prompt": "EXACT SAME dome as the reference image — same panes, same tree, same charcoal silhouette + halftone style. The ONLY change across the 4 panels is the tree progressively leaning (tall -> leaning -> tilting -> fallen). USE METAPHOR-FORWARD LANGUAGE ('settles / leans to rest / lies down softly / halftone leaves drift like quiet breath') — blunt words for harm or death can trip FAL's content_policy filter; a metaphor prompt gives the same visual and passes.",
"motion": { "type": "render_kb", "dur": 2.0, "per_panel": true, "zoom_end": 1.04, "concat": "hard_cut", "_note": "4 x 2.0s panels, hard-cut concat = 8s" }
},
{
"id": "beat-3",
"role": "REFRAME_GROVE",
"t_start": 11.5,
"t_end": 22.0,
"audio_line": "for years nobody could work out why ... then somebody asked what was missing ... and it was just the wind",
"payoff_word": "the wind",
"caption_on": true,
"_note": "Split into 3 sub-beats so each aligns to a DIFFERENT sentence: 12-15 'for years nobody could work out why' -> fallen-tree reflective hold; 15-19 'somebody asked what was missing' -> empty windy hillside; 19-22 'it was just the wind' -> windswept grove lands exactly on its line. Concat sub-segments hard-cut. Total 10s.",
"sub_segments": [
{ "id": "b3a-fallen-hold", "dur": 3.0, "audio_anchor": "for years nobody could work out why (reflective hold)", "keyframe": "generated/beat2-consistent/p4-fallen.png", "motion": { "type": "render_kb_out", "zoom_start": 1.06 } },
{ "id": "b3b-empty", "dur": 4.0, "audio_anchor": "then somebody asked what was missing", "keyframe": "generated/hillside-empty.png", "motion": { "type": "render_kb", "zoom_end": 1.05 } },
{ "id": "b3c-full", "dur": 3.0, "audio_anchor": "it was just the wind (windswept grove revealed)", "keyframe": "generated/style-anchor/anchor-grove-2.png", "motion": { "type": "render_kb", "zoom_end": 1.04 } }
],
"motion": { "concat": "hard_cut" }
},
{
"id": "beat-4",
"role": "PULLBACK_RESISTANCE",
"t_start": 22.0,
"t_end": 30.0,
"audio_line": "trees out in the open get shoved around all day long and, believe it or not, they're the ones still standing",
"payoff_word": "standing",
"caption_on": true,
"keyframe": "generated/beat4-wide-v3.png",
"keyframe_prompt": "Wide pull-back — the dome and the windswept grove side-by-side. A 'RESISTANCE' label punches in — the ONLY sage-accent element in the whole spot. NOTE: wide pull-backs tend to sprout tiny stray labels even with 'NO TEXT'; the all-caps 'ABSOLUTELY NO TEXT, NO LETTERS, NO WORDS, NO LABELS' tail fixes it. Composite the deliberate RESISTANCE label separately (PIL/drawtext) if Nano Banana can't be trusted with it.",
"motion": { "type": "render_kb", "dur": 8.0, "zoom_end": 1.05, "_note": "pull-back zoompan + render_kb on the RESISTANCE reveal" }
},
{
"id": "beat-5",
"role": "PIVOT_PEOPLE",
"t_start": 30.0,
"t_end": 37.0,
"audio_line": "wild, right? I think about it a lot. And it's the same for us.",
"payoff_word": "us",
"caption_on": true,
"_note": "THE PIVOT (the conceptual fix): the trees dissolve into people — one person slouched on a couch at midnight scrolling a phone (the dome side) vs. one person mid-swing with an Ironfern kettlebell in a sunny garage (the grove side). Split into 3 micro-cuts (full split 3s -> couch CU 1.5s -> training CU 2.5s) = 3 visual moments in one beat so it doesn't read static. Point the metaphor at the buyer (the person who trains), not at the story's subject.",
"sub_segments": [
{ "id": "b5-split", "dur": 3.0, "keyframe": "generated/beat5-split.png", "motion": { "type": "render_kb", "zoom_end": 1.04 } },
{ "id": "b5-couch-cu", "dur": 1.5, "keyframe": "generated/beat5-couch-closeup.png", "motion": { "type": "render_kb", "zoom_end": 1.05 } },
{ "id": "b5-training-cu", "dur": 2.5, "keyframe": "generated/beat5-training-closeup.png", "motion": { "type": "render_kb", "zoom_end": 1.05 } }
],
"motion": { "concat": "hard_cut" }
},
{
"id": "beat-6",
"role": "END_CARD",
"t_start": 37.0,
"t_end": 40.8,
"audio_line": "We need something to push against. (+ ~1.5s silent hold)",
"payoff_word": "",
"caption_on": false,
"keyframe": "generated/ironfern-endcard-9x16-final.png",
"motion": { "type": "kenburns_static", "dur": 4.3, "zoom_end": 1.03, "fade_in": 0.3, "fade_out": 0.3, "_note": "PIL-composited end card; ~2.8s active + ~1.5s silent hold. The video runs past the audio for the hold (fade the first/last 0.3s so it doesn't hard-black-flash)." }
}
],
"captions": {
"_comment": "Whisper (fal) on the MASTER -> frosted-subtle ASS burn. ON only while the speaker is mid-sentence — leave silent/reflective beats (and the end card) uncaptioned so captions don't fight the visual. This is REAL spoken VO, so Whisper works (unlike sung audio, which returns 'Music Playing'). ls the burn-in-captions skill's templates/ before assuming a style exists — only frosted-subtle + karaoke-fill were present (clean-bubble was documented but missing).",
"provider": "fal",
"model": "whisper",
"style": "frosted-subtle",
"skill": "burn-in-captions",
"on_when": "speaker_mid_sentence_only",
"no_overlap": "MANDATORY — clamp each line to end before the next starts (end = min(last_word_end+~0.15, next_start-0.03)); two boxes must never stack. The #1 caption bug.",
"safe_area": "Captions sit in the lower third; keep the subject in the upper ~75%. If a keyframe subject intrudes into the caption band, shift the subject UP into the empty top space (PIL) before assembly.",
"burn_engine": "Prefer libass; if `ffmpeg -filters` lacks it (common on Homebrew), render each line as a transparent PNG (frosted box + text) and composite via the `overlay` filter with timed enable windows."
},
"end_card": {
"_comment": "Brand lockup composited via PIL from the REAL brand asset (the canonical Ironfern wordmark PNG) — NEVER AI-rendered text (Nano Banana misspells words in rendered text). Before generating an end card from scratch, `find <brand> -name '*wordmark*'` — the brand team already produced the right asset.",
"engine": "pil",
"script": "build_endcard.py",
"brand_asset": "brand-assets/logos/ironfern-wordmark-on-green.png",
"wordmark_text": "ironfern",
"wordmark_font": "/System/Library/Fonts/Helvetica.ttc",
"tagline_text": "Strength for people who sit all day",
"tagline_font": "/System/Library/Fonts/Helvetica.ttc",
"background": "stretch a 1px-wide center column of the source PNG to 1080x1920, GaussianBlur(80) to kill banding",
"mascot_crop": "feathered radial-alpha ellipse crop of the brand's fern-leaf mascot from the source PNG (box 1290,700,1750,1200), resized to ~30% width, pasted centered-upper (cy = 0.30*H)",
"overlay_window_sec": [37.0, 40.8]
},
"audio_mix": {
"_note": "The real podcast VO carries the spot. Any bed is soft licensed acoustic (finger-picked guitar / soft strings, swell on 'push against') at <= -22 LUFS ducked under the VO — NEVER a generated song. Pencil-scribble SFX per drawn line, light not cartoony.",
"loudness_lufs": -22,
"vo_source": "real_podcast_clip",
"music_bed": "optional_licensed_only",
"duck_under_vo": true
},
"post_production": {
"music": {
"default": "off",
"note": "the real podcast VO carries the spot; a bed is optional licensed acoustic <= -22 LUFS ducked under the VO, never generated"
},
"captions": {
"default": "on",
"note": "frosted-subtle Whisper captions, ON only while the speaker is mid-sentence (not silent beats)"
},
"end_card": {
"default": "on",
"note": "PIL end card from the real brand wordmark PNG, default on"
}
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |