Skip to content
cccskills
FreePublished on GitHub

render-hypermotion

Assemble the FREE steps of the product-hypermotion + kinetic-typography video format — dice ONE Seedance 2.0 hypermotion clip into 5-6 segments and intercut them with PIL kinetic-typography spec/CTA cards (italic skew, 1.08x outline echo, 3D extrusion, slam-with-shake, inversion flash) plus a real-logo PIL end card (base64-decoded from the brand SVG), center-crop 1:1 to 9:16, and explicit-map mux a music bed. Deterministic, FREE (PIL + FFmpeg), no paid calls, the real logo and spec typography stay pixel-crisp. The paid steps (the ONE Seedance i2v, the music) are separate capabilities; the recipe orchestrates them. Use for the product-hypermotion format.

The English summary is being prepared. Showing the original description.

Works withElevenLabs

Run score Not tested

See how to install

Files included (6)

  • SKILL.md5.6 KB
  • scripts/config.example.json6.5 KB
  • scripts/PIPELINE.md9.6 KB
  • scripts/README.md5.1 KB
  • skill.meta.json335 B
  • tests/smoke-test.md1.3 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

render-hypermotion

Assembles a product-hypermotion + kinetic-typography ad: a vertical 9:16 sizzle (~20–30s) where ONE spectacular AI-gen hypermotion clip of the hero product carries the energy and punchy PIL-rendered spec cards carry the facts. Music-led, no VO — it reads as a high-production sizzle, not UGC.

The reusable IP is one-call-many-cuts + intercut: dice ONE 12–15s Seedance 2.0 hypermotion i2v into 5–6 segments (never a paid call per segment) and interleave PIL kinetic-typography spec cards between the cuts, capped by a real-logo end card, over a beat-driven music bed.

This capability ships the FREE, deterministic assembly — everything between the two paid model calls. It is documentation-grade + config: the format has no runnable driver. scripts/ carries the worked config + the step-by-step pipeline doc; the Soundboks reference PIL impls (gen_kinetic_v6.py, gen_endcard_v10.py, assemble_v10.py) are copied + adapted per run, not vendored.

  • config.example.json — the Soundboks worked example: hero product, 5 spec callouts, the 5-block Seedance prompt, per-card treatments, beat structure, end-card spec, music brief, dims. Copy its structure to config.json; never its creative values. Card labels equal their text_cards keys (intro, spec_1..spec_N, cta) so beat_structure.concat_order resolves to kinetic-movs/<key>.mp4.
  • PIPELINE.md — the full config-field → step map: Phase 0 assets → Phase 1 PAID Seedance + music (parallel, gated) → Phase 2 FREE PIL cards → Phase 3 FREE dice/intercut/concat/mux → Phase 4 watch/QC. Names the atom/tool each step uses, plus 20s/25s/30s beat-structure variants.
  • README.md — documents the FREE assembly (below).

Choices

The calling recipe asks the user these before any paid step; this capability only assembles what they produced. The Soundboks values are a worked example, never defaults.

  • energy → config.brand_voice, Seedance block 1, music.bpm (demo: party, 124 BPM).
  • environment → Seedance blocks 3–4 (demo: beach festival deck).
  • lighting → Seedance blocks 2–3 (demo: dusk, magenta/blue rim).
  • music → config.music.prompt (demo: bass-driven party banger).

The assembly itself is choice-agnostic: segment cut points, card order and the end card read only from config.

The FREE assembly

  • PIL kinetic-typography spec/CTA cards — full-frame 1080×1920 clips rendered frame-by-frame on a dark grain BG with the static Space Grotesk Bold TTF: italic skew (~6°), outline echo at 1.08× (bleed-safe), 3D extrusion (hero stat + CTA, side = brand accent), slam-with-shake, and color/inversion flash. No VO — the cards carry every fact.
  • Real-logo PIL end card — the brand's actual logo PNG (base64-decoded out of the SVG, never typeset) with a slam-motion-blur entry, settle, continuous micro-motion (±1% scale + ±3px drift for the full hold — never freeze), an inversion flash at ~60%, and a cascade reveal of the spec-dot subtitle + CTA.
  • FFmpeg dice + intercut — center-crop the ONE hypermotion clip 1:1 → 9:16, dice into 5–6 decreasing-length segments at Seedance's natural beats (crash-zoom → orbit → settle), then concat in the fixed intercut order: open on the intro card, alternate segment ↔ spec card, end on the CTA + brand end card.
  • Explicit-map mux — mux the music bed as a SEPARATE pass with -map 0:v -map 1:a (the default mapping silently ships ~1 kbps garbage audio; verify ffprobe ≈ 192 kbps).

Run

# Phase 2 — FREE PIL cards (per config.text_cards + config.end_card)
#   render each spec/CTA card + the real-logo end card, 1080x1920, frame-by-frame → mov
# Phase 3 — FREE dice + intercut + mux
#   center-crop 1:1→9:16, dice into 5-6 segments, concat in beat_structure order,
#   then explicit-map mux the music bed → master-final.mp4

Output: master-final.mp4, 1080×1920, ≈20–30s (25s default) h264 (+ 192 kbps aac music) — 14 segments: intro + 6 hypermotion cuts + 5 spec cards + CTA + real-logo end card. All FREE, $0.

Contract

  • Deterministic + FREE (PIL + FFmpeg); no paid calls, no AI-rendered logo or spec text.
  • ONE hypermotion clip, diced into 5–6 segments — never a paid call per segment (cheaper AND identity-consistent: same camera/grade/subject in one call).
  • The end card is the brand's real logo PNG, base64-decoded from the SVG — never typeset; it must micro-move for the full hold (never freeze).
  • Spec cards carry every fact (no VO); outline echoes stay ≤1.08× so nothing bleeds off frame; use the static Space Grotesk Bold TTF (variable renders as Regular in PIL).
  • The paid steps — the ONE Seedance 2.0 hypermotion i2v (5-block prompt with the mandatory ABSOLUTE CONSTRAINTS block, or the geometry drifts) + the ElevenLabs music bed — are separate capabilities (create-video-fal, create-music-elevenlabs); the recipe orchestrates them and gates the spend.

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

Research supported advertising promises from a specific buyer's context, current product facts, customer language and observed ads. Turn them into static, video or copy ideas; match video ideas to actual recipes and save a product-scoped angle bank for write-video-ad-script. Product-led discovery can use verified facts without reviews. Reference persistence and reach are observations, not proof of performance.

The English summary is being prepared. Showing the original description.

gooseworks-ai/goose-skills1.3KUpdated Oct 24, 2026

Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift recommendations and scenario modeling.

The English summary is being prepared. Showing the original description.

gooseworks-ai/goose-skills1.3KUpdated Oct 24, 2026

For paid lead-gen and participant-recruitment ads, replaces vanity CPA with true CAC per qualified lead by joining ad-platform data with downstream funnel events, surfaces tracking gaps, and classifies every creative into Scale / Keep / Investigate / Cut.

The English summary is being prepared. Showing the original description.

gooseworks-ai/goose-skills1.3KUpdated Oct 24, 2026

The intake stage of a Meta ad harness. Researches the brand first, states what it assumes, and asks only what it cannot infer and what would change money, claims or legal exposure if guessed wrong — at most four questions a turn, in plain business language. Writes the brand's stable facts (ads/brand.md), the campaign brief, and a log of what was asked vs assumed. Use it when someone wants to run Meta ads and the brand's ad facts are not yet recorded.

The English summary is being prepared. Showing the original description.

gooseworks-ai/goose-skills1.3KUpdated Oct 24, 2026

Checks paid ads against the ad platform's rules (Meta, TikTok, Google, LinkedIn and others) and the brand's category rules: the copy, on-image or on-screen text, pictures and people. Rewrites what can be fixed honestly, adds the disclosures that are needed, and flags anything that needs a human or legal review, with one pass, fixed or flag line per ad and platform. Use alone when you already have the ad text or images and know where they will run; otherwise run the playbook for the job (e.g. make-static-ads, make-content, email-lifecycle).

The English summary is being prepared. Showing the original description.

gooseworks-ai/goose-skills1.3KUpdated Oct 24, 2026

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.

The English summary is being prepared. Showing the original description.

gooseworks-ai/goose-skills1.3KUpdated Oct 24, 2026

See all skills by gooseworks-ai

Report a problem with this skill