Skip to content
Skills Library
Marketing & content · Automation

render-3d-character-explainer

/render-3d-character-explainer

Assemble an animated character-explainer video ad (~77s, 9:16, any art style: Pixar-style 3D, claymation, anime, paper-cut, felt) on an \"N types of X\" listicle spine: one recurring human protagonist plus one persona character per list item. Given per-scene clips, a scene timing table and narration, it trims, normalises, concatenates and mixes them, reusing the source ad's audio (restyle) or fresh per-scene voiceover over a music bed (original), loops a scene's keyframe when its clip failed, and burns captions last. Free, deterministic assembly (Python and ffmpeg, no paid calls); the recipe s

Licence
MIT
Last repository change
25.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
6
Scripts
2
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 25.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 2 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: scripts/compose.py, scripts/make_captions.py

What it does and when to use it

Assemble an animated character-explainer video ad (~77s, 9:16, any art style: Pixar-style 3D, claymation, anime, paper-cut, felt) on an \"N types of X\" listicle spine: one recurring human protagonist plus one persona character per list item. Given per-scene clips, a scene timing table and narration, it trims, normalises, concatenates and mixes them, reusing the source ad's audio (restyle) or fresh per-scene voiceover over a music bed (original), loops a scene's keyframe when its clip failed, and burns captions last. Free, deterministic assembly (Python and ffmpeg, no paid calls); the recipe s

Triggers from the description

N types of X\
Original author description

Assemble an animated character-explainer video ad (~77s, 9:16, any art style: Pixar-style 3D, claymation, anime, paper-cut, felt) on an \"N types of X\" listicle spine: one recurring human protagonist plus one persona character per list item. Given per-scene clips, a scene timing table and narration, it trims, normalises, concatenates and mixes them, reusing the source ad's audio (restyle) or fresh per-scene voiceover over a music bed (original), loops a scene's keyframe when its clip failed, and burns captions last. Free, deterministic assembly (Python and ffmpeg, no paid calls); the recipe s

How it works

  1. Choices
  2. Two modes
  3. What it does (the deterministic recipe)
  4. Scripts (free — Python + ffmpeg, no bash, no paid calls)
  5. Inputs (all via --config + a runtime work dir — NO hardcoded paths)
  6. Craft rules (load-bearing — faithful to the source molecule + reference run)
  7. Requires
Original SKILL.md headings · 123 lines, 1,231 words
SKILL.md preview
---
name: render-3d-character-explainer
description: "Assemble an animated character-explainer video ad (~77s, 9:16, any art style: Pixar-style 3D, claymation, anime, paper-cut, felt) on an \"N types of X\" listicle spine: one recurring human protagonist plus one persona character per list item. Given per-scene clips, a scene timing table and narration, it trims, normalises, concatenates and mixes them, reusing the source ad's audio (restyle) or fresh per-scene voiceover over a music bed (original), loops a scene's keyframe when its clip failed, and burns captions last. Free, deterministic assembly (Python and ffmpeg, no paid calls); the recipe supplies the clips, keyframes, audio and captions. Use for the 3d-character-explainer format."
status: active
---

# render-3d-character-explainer

The free, deterministic renderer for the **3d-character-explainer** video ad format — an
animated character spot (art style is the user's choice; the demo was glossy Pixar-style 3D) built on an **"N types of X" listicle** spine, where a recurring
human protagonist plus a locked cast of **N persona characters (one per list item)** carry a
hook → "deeper story" → cast-reveal → one beat per list item → kicker → product test →
relieved payoff. This capability is the **FREE assembly stage only**. All generative work
(Nano-Banana cast anchors + per-scene keyframes, Kling-V3 i2v clips, ElevenLabs VO + music,
or a source ad's audio reused verbatim) happens upstream in the recipe and is handed to this
capability as files.

It ports the validated compose recipe from the worked example — a "six types" Pixar-style 3D
listicle restyle (`_render_full.sh` — per-scene trim → normalize 1080×1920/fps30 → concat -c copy → mux the
source audio, with a static-still fallback on any failed clip). The assembly is
deterministic — iterate the cut for free, re-roll only the offending paid beat.

## Choices

The recipe asks these of the user before any paid step; this capability assembles whatever
comes back. None of them is fixed by the format.

- `visual_style` — the art style of the anchors, keyframes and Kling motion prompts (Pixar-style
  3D, claymation, anime, paper-cut, felt). Asked of the user; the demo used glossy Pixar-style 3D.
- `narrator` — who tells the story and in whose POV the lines / captions are written. Asked of
  the user; the demo used an off-screen storyteller.
- `narrator_voice` — the VO voice (ORIGINAL mode only). Asked of the user; the demo used one
  ElevenLabs narrator.
- `tone` — cute/comedic, sincere, educational, dramatic, punchy; shapes the style prefix, the
  delivery and the script. Asked of the user; the demo was cute and comedic.
- `protagonist` — the human's age, gender, look and outfit (locked via the world lock). Asked of
  the user; the demo used a young protagonist in a single tee.
- `music` — the bed under the VO, or none (ORIGINAL mode → `music_bed`). Asked of the user; the
  demo used a light instrumental underscore.

## Two modes

- **Restyle mode** (`audio_mode: "restyle"`, the reference run) — re-tell a finished source
  ad, beat for beat, as an animated character story in the chosen style and tone. The source ad's **audio mix (VO + music bed) is
  reused VERBATIM** (`source_audio`), and the per-scene `target_sec` table is inherited from
  the source's scene timing. No new VO or music is rendered. The trims must sum to the source
  audio length.
- **Original mode** (`audio_mode: "original"`) — the ad authors its own narration. Each scene
  carries a measured VO cue (`scenes[].vo`, `target_sec` = the ffprobe'd VO duration) which is
  concatenated into a VO track (loudnorm I=-14) and optionally mixed under a `music_bed`
  (loudnorm I=-26 then `volume`, `amix normalize=0`).

## What it does (the deterministic recipe)

1. **Per-scene retime.** Each i2v clip is trimmed to its scene `target_sec` and normalized to
   identical dims/fps/SAR
   (`scale=W:H:force_original_aspect_ratio=decrease,pad=W:H:(ow-iw)/2:(oh-ih)/2:color=<pad>,fps=30,setsar=1`).
   A clip **shorter** than its window is extended with `tpad=stop_mode=clone`; a longer one is
   `-t` trimmed. Decrease+pad (never crop) preserves the full 9:16 keyframe framing.
2. **Static-still fallback.** For any scene whose `clip` is missing or failed to render, the
   scene's `keyframe` PNG is looped (`-loop 1`) for `target_sec`, so the master always
   assembles. Fallback scenes are printed at the end.
3. **Identical re-encode + concat.** Every segment is re-encoded `libx264 -crf 18 -pix_fmt
   yuv420p -r 30` even if already correct — a dims/framerate mismatch makes the concat demuxer
   silently drop frames — then concatenated via the concat demuxer (`-c copy`).
4. **Audio.** Restyle: `source_audio` muxed verbatim (`-map 0:v -map 1:a`), clamped to the
   video length. Original: per-scene VO track (optional `atempo`, `apad`, `-t` clamp) → loudnorm
   → optionally mixed under the music bed.
5. **Captions last.** `make_captions.py` emits a libass `.ass` (one cue per scene, `start =
   scene_start + 0.08s`, suppressed on any scene with no caption — e.g. a product/end-card beat
   carrying its own typeset copy). `compose.py` burns it as the final filter so captions sit on
   top. Word-level energy-pop captions (Whisper on the narration) are the recipe's upstream
   option — produce that `.ass` externally and point `captions_ass` at it; compose burns
   whatever `.ass` it's handed.

## Scripts (free — Python + ffmpeg, no bash, no paid calls)

- `scripts/make_captions.py` — emits the per-scene libass `.ass` from the SAME scene table
  compose reads, so caption windows stay in lockstep with the cut. Run before `compose.py`
  (or leave `captions_ass` unset / pointing at nothing to skip captions).
- `scripts/compose.py` — the assembler: per-scene trim + identical 1080×1920/30fps re-encode
  (static-still fallback on missing clips) → concat → audio (restyle verbatim / original
  mix) → burn captions → master mp4.
- `scripts/config.example.json` — the shape of the `config` the recipe binds (the
  "six types of laundry stains" restyle demo, a made-up brand, as a worked example; captions, audio and
  music are the demo's, never defaults).

## Inputs (all via `--config` + a runtime work dir — NO hardcoded paths)

`config.json` carries: `audio_mode` (`restyle` | `original`), `scenes[]` (each `{id, clip,
keyframe, target_sec, caption?, vo?, atempo?}` where `target_sec` is the source-inherited
window in restyle mode or the **measured** VO window in original mode, and `keyframe` is the
static-still fallback source), `source_audio` (restyle), `music_bed` + `music_volume` +
`atempo` (original), `width`/`height` (default 1080×1920), `pad_color` (letterbox colour),
`captions_ass`, and `caption_style`. See `config.example.json`. `pad_color` defaults to neutral
black; set it from the brand palette.

## Craft rules (load-bearing — faithful to the source molecule + reference run)

- **Restyle inherits the source timing.** A restyle reuses the source ad's exact audio, scene
  order, and per-beat durations verbatim; only an original-mode remix authors its own VO +
  timing table. Merge any sub-1.5s flash scene into a neighbour upstream to avoid a dead
  micro-cut (the reference folded scene 7 into scene 8).
- **Normalize decrease+pad, never crop** — the listicle's cast-reveal + per-persona framing
  must not lose edges; letterbox-pad to the canvas colour instead. Re-encode every segment to
  30fps before concat, even if already correct, or the concat demuxer silently drops frames.
- **Static-still fallback is mandatory** — Kling can 403 mid-run (a billing wall after a burst
  of successes, not a rate limit). Any failed clip loops its keyframe so the master still
  assembles; re-roll only the missing beat and recompose (free).
- **`generate_audio` was false upstream** — Kling would otherwise invent its own dialog track;
  the real narration is muxed here separately. (This is the recipe's upstream call, not this
  capability.)
- **No AI-rendered brand text** — the product-beat keyframe shows a BLANK-label box; the real
  wordmark/end-card copy is composited upstream, never AI-drawn. Suppress captions on any
  product/end-card beat (its typeset copy carries the message — two text layers at one spot are
  both unreadable).
- **Caption `start = scene_start + 0.08s`** (avoids the caption flashing a frame before a cut).

## Requires

`watch` (QC the final master — the human protagonist reads as the SAME person every scene
(wardrobe/hair/lighting held), each persona is on-model, the cast-reveal lineup matches the N
list items, the product beat shows the REAL box, narration lands beat-for-beat, and duration is
within ±0.1s of the summed windows). The recipe gates the paid `create-image-fal` (cast
anchors + keyframes), `create-video-fal` (Kling-V3 i2v), `create-vo-elevenlabs`, and
`create-music-elevenlabs` calls to their own capabilities — this capability itself makes NO
paid calls.
Files in this package (6)
  • SKILL.md 9 KB
  • skill.meta.json 1 KB
  • scripts/compose.py 12 KB
  • scripts/config.example.json 4 KB
  • scripts/make_captions.py 3 KB
  • tests/smoke-test.md 4 KB

Versions

The database has no other skills named render-3d-character-explainer.

Database snapshot: 13.11.2026 · package version 19f80aa57a25 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 91pixar-ad
    Builds a stylized 3D animated ad on the Novoads REST API as a STORYBOARD: four to six beats, each rendered from its own key frame, narration laid into the gaps, a music bed, captions burned on, assembled locally with ffmpeg. Carries the genre's beat formulas (anthropomorphized…
  • 100explainer-voiceover
    Makes the narration of an explainer video, scene by scene, for a video editor (Premiere Pro, DaVinci Resolve, Final Cut Pro, CapCut) with Vois Studio, on the user's computer. It writes each scene for the ear and renders one WAV for each scene with vois-cli. Then it puts all…
  • 95animated-explainer
    Produce an original, vector-style 2D animated explainer or promotional film from a topic: research, script, timestamped shot plan, character and environment art direction, layered asset generation with chroma-key cutouts, voiceover-first timing, a deterministic seek(t) animation…
  • 100render-absurdist-explainer
    Assemble an absurdist animated-explainer video ad (~38s, 9:16) from per-scene i2v clips + their measured VO windows — retime each clip to its VO, re-encode every segment to identical 30fps/libx264/yuv420p so the concat demuxer never drops frames, concat, build a REAL-product PIL…
  • 100render-multiworld
    Assemble a silent, music-led 3-world product-tour ad — trim and hard-cut-concat the per-world WIDE-arrival + top-down-macro clips, composite the HTML/Playwright brand end card (approved headline + handwritten product labels + arrows) over an AI flat-lay background, and mux one…
  • 100storyframes
    Make character-driven motion explainer videos for a product (flat illustrated people, crowds, the product's own UI rebuilt big, kinetic type, a synthesised music bed and placed sound effects), rendered to MP4 with HyperFrames. Use when someone asks for an animated product video,…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.