Video Ninja
Jump Skill — Master orchestrator that routes video tasks to 79 globally installed skills from 10
repositories and one well-known source, Anatomy and DaVinci Resolve editing skills from locally
synced repositories, plus a methodology layer distilled from the My-Little-Studio pipeline.
This ninja routes any video task to the installed or locally synced skills. It is the required entry point: read it
before choosing a video skill.
Why this ninja exists
The ten globally installed source repositories cover rendering, media processing, craft, frameworks,
animation libraries, art styles, and 3D graphics subsystems, but each is a silo.
HyperFrames can render video, but it has no opinion on quality. motion-video-kit has a quality
doctrine, but no renderer. Remotion is
an alternative framework, not a plug-in for HyperFrames. opus-video-skills brings distinctive looks
such as watercolor and kinetic typography, but not the other repositories' craft doctrine.
ffmpeg-skill works on existing footage; it does not build compositions from scratch. gsap-skills
teaches correct GSAP patterns but is not a video engine. dotlottie-web handles Lottie assets but
does not compose them into video. The Three.js pack supplies advanced 3D graphics subsystems, but it
neither plans nor delivers a film.
This ninja is the layer that chooses and connects them, and keeps track of what the ecosystem
still lacks.
The golden rule
/hyperframes is the default entry point for video creation and composition.
It chooses among the 10 workflows and loads domain skills as needed. For footage edits that must
be built in DaVinci Resolve Studio, use the optional video-editor-skills route instead.
This ninja does not replace HyperFrames routing; it tells you which layer to use and when
HyperFrames alone is not enough.
For video creation, animation, composition, and rendering, start with /hyperframes. For a
talking-head, vlog, or class timeline that should be built in Resolve Studio, use the gated
video-editor-skills route. Other exceptions include Remotion, screen capture, craft doctrine,
pipeline methods, and the YouTube Video steer in references/youtube-video.md.
The globally installed source repositories
| Repository |
Skills |
Layer |
Status |
heygen-com/hyperframes |
27 |
Renderer + domain skills |
Installed, Apache-2.0 |
kajisho5/ffmpeg-skill |
1 (42 tools) |
Media processing |
Installed, MIT |
echris6/motion-video-kit |
1 |
Quality doctrine |
Installed, MIT |
remotion-dev/skills |
12 |
Alternative framework |
Installed |
Rieranthony/product-film-skill |
1 |
Screen capture |
Installed, MIT |
tugrawork-creator/saas-motion-kit |
1 |
Variety and anti-repetition |
Installed |
tuzhechen2005/opus-video-skills |
2 |
Procedural art styles |
Installed, MIT |
greensock/gsap-skills |
8 |
Official GSAP skills: timelines, ScrollTrigger, plugins, React |
Installed, MIT |
LottieFiles/dotlottie-web |
1 |
Modern Lottie player: Rust+WASM, state machines, themes |
Installed, MIT |
scottstts/Threejs-Awesome-Graphics-Agent-Skills |
24 |
Advanced Three.js graphics subsystems |
Installed by its own installer; excluded from sync (~261 MB), MIT |
Provenance for globally installed skills is recorded in ~/.agents/.skill-lock.json. The Three.js
pack is the exception: its own installer (npx threejs-awesome-graphics-agent-skills@latest install --agent universal) installs to ~/.agents/skills/ without a lockfile entry. fframes-video is
installed separately through fframes.studio.
Locally synced source skills
Both are declared in root repos.md and synced under repos/video-ninja/ so the Ninja can load
their instructions when needed. See references/repos.md.
Film style libraries and the character kit
| Repository |
What it adds |
How the Ninja uses it |
License |
lemomo-ai/lemo-opuscar |
66 film styles made in code, each with a demo film, STYLE.md and a director's guide |
Through the lemo-opuscar skill (Claude plugin), which keeps its own sparse library in ~/lemo-opuscar. Not synced (~195 MB) |
MIT code; demo films CC BY 4.0 |
Vincentwei1021/mg-styles-15 |
15 motion-design styles with full prompt, source, renderer and review rubric |
Sparse checkout of prompts/, harness/ and lib/ on demand. Not synced (~1.2 GB) |
MIT |
JohnHeibel/ClaudeAnimationBase |
p5.brush hand-painted character kit: 31 emotions, views, gestures, hats, contact-sheet review |
Synced locally under repos/video-ninja/ClaudeAnimationBase/; read its ANIMATION_GUIDE.md |
MIT; Clawd only in videos about Claude, otherwise your own character |
Families, styles, install steps and license notes:
references/film-families-and-styles.md.
Separately installed skill
| Source |
Skill |
Role |
Installation |
fframes.studio |
fframes-video |
Alternative Rust/SVG renderer with Skia GPU, FFmpeg, and agent-readable QA |
Well-known, installed globally |
Evaluated external tools that are not installed
| Source |
Role |
When to consider it |
Status |
m-bain/whisperX |
Local ASR with word-level timestamps and diarization |
Talking-head, interview, or podcast work that needs word timing or speaker identification |
Optional backend; not installed. See references/whisperx.md |
airbnb/lottie-web |
Player for After Effects Lottie animations |
Reuse a project-provided .json Lottie asset in a HyperFrames composition |
On-demand dependency; not installed by the Ninja. See references/lottie.md |
ManimCommunity/manim |
Python engine for mathematical animation |
Recurring math explainers that justify another renderer and adapter |
Evaluated, not installed. The tweet links to 3b1b/manim (ManimGL). See references/repos.md |
rive-app/rive-wasm |
Interactive animations with native state machines |
Project has .riv assets from Rive Editor, or needs animations that react to app state |
On-demand dependency. See references/rive.md |
goldfire/howler.js |
Web audio control: sprites, fades, spatial audio |
Sound effects with precise timing, audio sprites, 3D positional audio |
On-demand dependency. See references/howler.md |
vercel/satori |
JSX → SVG for title cards and thumbnails |
Batch-generate title cards, thumbnails, or text-heavy graphics from data |
On-demand dependency. See references/satori.md |
Anatomy produces a visual asset or scene, not the finished video. Its source is synchronized at
{{JUMP_SKILLS_DIR}}/repos/video-ninja/anatomy/; read that repository's SKILL.md when routing to
it. Build and inspect the figure, then bring the output into /hyperframes and follow the motion,
composition, and rendering doctrine. If the path is missing, treat Anatomy as unavailable and use
the fallback described in references/anatomy.md.
Do not assume WhisperX or Manim is installed or available. Lottie is an asset format: load its player
only when the project already includes that kind of animation.
Additional reference documentation
The following tools are documented in the references folder for on-demand use:
| Tool |
Reference |
Use case |
| Rive |
references/rive.md |
Interactive animations with state machines; alternative to Lottie when project has .riv assets |
| Howler.js |
references/howler.md |
Web audio control: sprites, fades, spatial audio; complements /hyperframes-audio |
| Satori |
references/satori.md |
JSX → SVG for title cards, thumbnails, OG images; batch generation of text graphics |
| YouTube Video |
references/youtube-video.md |
Raw talking-head edited into a polished YouTube video with explanatory motion graphics |
These tools are not installed skills but are documented for when their specific capabilities are needed.
The YouTube Video row is a pipeline steer, not a library.
Five more pipeline steers cover asset tooling used while producing graphics for a composition:
excalidraw.md (hand-drawn diagrams as video assets),
penpot.md (open-source design source with an official MCP),
fontsource.md (self-hosted fonts for deterministic render),
lucide.md (UI icon set), and
svgo.md (animation-safe SVG optimization). None of them installs a skill.
Engine map
The source image mixes composition engines, project frameworks, and a file editor. Use these
distinctions before choosing a workflow:
| Engine |
How it works |
When to choose it |
Status in the Ninja |
| HyperFrames |
HTML/CSS/JS in headless Chrome + FFmpeg |
New compositions, motion design, and agent-directed video |
Default, installed |
| ffmpeg-skill |
Probe → edit → validate existing files |
Cutting, joining, audio normalization, multicam, and delivery |
Processing, installed |
| fframes-video |
Per-frame Rust/SVG, Skia GPU, FFmpeg, and inspection CLI |
High-throughput vector rendering, batch work, and automated review |
Alternative engine, installed |
| Remotion |
React/TypeScript, local or Lambda rendering |
Existing React projects, composition ports, or distributed rendering |
Alternative framework, installed |
| Motion Canvas / Revideo |
TypeScript generators; Revideo adds a React player, headless rendering, and dynamic inputs |
Motion Canvas for editor-based vector animation; Revideo for parameterized templates and Node/serverless rendering |
Evaluated; no skill installed |
| MoviePy |
Python clips, compositions, and frame effects |
Data-driven Python pipelines or composition prototypes |
Evaluated; no skill installed |
| Manim Community Edition |
Python for programmatic math animation |
Recurring explainers about math, charts, or geometry |
Evaluated; no skill or adapter installed |
Do not present Motion Canvas, Revideo, MoviePy, or ManimCE as installed capabilities until a skill
defines routing, a render contract, and verification. If a project already uses one of these tools,
the Ninja can keep it and apply the same motion, audio, and validation doctrine.
Check Remotion's license before production: its code is source-available, and the free license covers
individuals and organizations of up to three people. Larger teams or automated use may require a
Company License. Do not describe it as MIT or OSI-approved open source.
Routing
Step 1 — Is this actually a video task?
If it is not a video task, this ninja does not apply:
| Request |
Route to |
| Website/app |
impeccable, apple-design |
| UI animation only (not a video) |
animate, improve-animations (Emil Kowalski pack) |
| Marketing copy or script only |
copywriting, social |
Step 2 — Route by deliverable
Let /hyperframes choose among the 10 workflows. Its priority table is authoritative. This ninja
only needs to identify the layer to add:
| Request |
Workflow |
Additional Ninja layer |
| Legenda em talking-head |
/embedded-captions |
+ /captions-overlay |
| Cards de overlay em podcast |
/talking-head-recut |
+ /cut-the-curve |
| Product or URL promo |
/product-launch-video |
+ /motion-doctrine, /seam-craft, §Product launch |
| Weekly changelog video |
/changelog-video |
— |
| Screen recording → demo |
/product-film (dedicated skill) |
See §Remotion |
| Business film (live action, AI, premium) |
/business-motion-film |
See §Doctrine |
| Anti-repetition SaaS promo |
/saas-motion-video |
See §Doctrine |
| Watercolor cartoon / karaoke lyric video |
/painted-animation |
See §Art styles |
| Kinetic type showreel / portfolio |
/kinetic-reel |
See §Art styles |
| Technical explainer with an isometric mechanism or object |
Anatomy (when synced) |
Read its local SKILL.md, build and inspect SVG/HTML; bring the asset into /hyperframes for composition and rendering. See references/anatomy.md |
| Talking-head, vlog, or class edit in DaVinci Resolve Studio |
video-editor-skills (when synced and license permits) |
Read its local skills/edit-video/SKILL.md; check Studio scripting and the commercial-use restriction first. See §DaVinci Resolve |
| Talking-head with word timing or diarization |
/embedded-captions + optional WhisperX (if installed) |
Align words or identify speakers, then check against the audio. The “tape” is still needed for cuts that depend on restarts or syllable onsets. See references/whisperx.md |
| Raw talking-head → polished YouTube video with explanatory motion graphics |
YouTube Video steer (Remotion) |
Do not start in HyperFrames. Read references/youtube-video.md. Keep the speech language. Do not publish without approval. |
Project supplies a Lottie .json animation |
/hyperframes + Lottie Web on demand |
Disable autoplay and seek explicitly by frame or time for deterministic capture. See references/lottie.md |
| High-rigor math explainer |
ManimCE (optional, if installed and justified) |
Specialized math renderer; inspect the final composition. HyperFrames remains the default for other videos |
| Code-generated motion, loops, or frame animation |
/hyperframes |
+ /motion-doctrine, see §Motion Lab |
| 3D scene, procedural graphics, or a Three.js subsystem (materials, ocean, clouds, planets, VFX) |
threejs-* pack (start at threejs-skill-router) |
Load only the targeted subsystem, then bring the result into /hyperframes or the project's engine. See §3D graphics |
| Cut, join, or process existing footage |
ffmpeg-skill |
See §FFmpeg |
| Adjust loudness for a platform |
ffmpeg-skill |
See §FFmpeg |
| Remove recording silences |
ffmpeg-skill |
See §FFmpeg |
| Sync multiple cameras |
ffmpeg-skill |
See §FFmpeg |
| Vector video with GPU rendering and CLI QA |
fframes-video |
See §fframes |
| Existing Motion Canvas/Revideo project |
Motion Canvas/Revideo |
Keep it only if the dependency already exists; apply §Doctrine |
| Python composition or data pipeline |
MoviePy |
Use only when Python is a requirement; finish with §FFmpeg |
| Explainer, PR, music, deck, motion, open-ended video |
The 10 workflows |
— |
| Film in a named style (e.g. Blueprint, Ukiyo-e, Satellite Briefing, Bauhaus) or "which styles are there?" |
lemo-opuscar for the 66 Opuscar styles; MG Styles prompt + harness for the 15 MG styles |
See Step 2b and references/film-families-and-styles.md. If lemo-opuscar is not installed, ask before installing it |
| Hand-animated character that acts (emotions, gestures), no text |
ClaudeAnimationBase (when synced) or /painted-animation |
Read its ANIMATION_GUIDE.md; use the Clawd mascot only when the video is about Claude. See §Art styles |
Step 2b — Pick the film family, then the style
For short-form films (Reels, Shorts, promos, explainers), name the family (how the story is
told) before the style (how it looks):
| Family |
Primary route |
| A · 3D cinema |
threejs-* pack; Blender only if the project already has it |
| B · 2D motion with 3D objects |
/hyperframes + /motion-graphics, threejs-* for objects |
| C · Phone and chat |
/hyperframes registry blocks, /product-launch-video |
| D · Device in 3D |
/product-film or /hyperframes device frame + threejs-* |
| E · Kinetic typography |
/kinetic-reel or /motion-graphics |
| F · Map and diagram |
Anatomy, /hyperframes data blocks, remotion-maps |
| G · You on camera |
/talking-head-recut, /embedded-captions, YouTube steer, video-editor-skills |
| H · Hand-animated character |
ClaudeAnimationBase, /painted-animation |
Then pick at most one of the 81 styles that fits the family and the use case. Upstream examples are
16:9: recompose for 9:16 instead of cropping. Full table, fit lists and production steps:
references/film-families-and-styles.md.
Step 3 — Load the relevant domains
Cross-cutting: whenever photography or other media is involved, consider /media-use.
Motion is mandatory: always load /motion-doctrine before composing any animation (see §Doctrine;
it declares itself the GATEWAY and supersedes generic guidance).
Video production layers
| # |
Layer |
Skills |
Responsibility |
| 1 |
Renderer |
hyperframes, hyperframes-cli, hyperframes-core |
Deterministic HTML-to-video. core is the composition contract; read it before writing HTML |
| 2 |
Processing engine |
ffmpeg-skill (42 tools) |
probe→edit→verify. Cuts, joins, loudness, captions, HDR-to-SDR, multicam, batch work |
| 3 |
Alternative engine |
fframes-video |
Rust/SVG, Skia GPU, lane rendering, frame inspection, snapshots, and audio analysis |
| 4 |
Workflows |
general-video, product-launch-video, talking-head-recut, embedded-captions, faceless-explainer, pr-to-video, music-to-video, motion-graphics, slideshow, figma, changelog-video |
The final deliverable |
| 5 |
Craft doctrine |
motion-doctrine, cut-the-curve, seam-craft, oversized-cursor, captions-overlay, business-motion-film, saas-motion-video |
An opinion on quality. What separates “it rendered” from “it looks good” |
| 6 |
Domains |
hyperframes-animation, hyperframes-keyframes, hyperframes-creative, hyperframes-audio, media-use, hyperframes-registry, hyperframes-studio |
Motion, camera, design, sound, media, and ready-made blocks |
| 7 |
Second framework |
remotion-* (12), product-film |
When Remotion is the right choice |
| 8 |
Art styles |
painted-animation, kinetic-reel, lemo-opuscar (66 styles), MG Styles (15), ClaudeAnimationBase |
Distinct procedural looks and film styles; see the family/style map |
| 9 |
Animation library |
gsap-* (8 skills) |
Correct GSAP patterns: timelines, ScrollTrigger, plugins, React cleanup, performance |
| 10 |
Motion assets |
dotlottie-web |
Lottie/dotLottie player: state machines, themes, Web Workers, deterministic capture |
| 11 |
3D graphics subsystems |
threejs-* (24 skills) |
Advanced Three.js graphics: procedural geometry/fields/materials, ocean, clouds, planets, shadows, GTAO, bloom, color grading, VFX, and visual validation |
| 12 |
Timeline editor |
video-editor-skills (12 locally synced skills) |
Optional transcript-led first-pass edits in DaVinci Resolve Studio; subject to CC BY-NC 4.0 |
§Doctrine — the layer engines lack
This is the part that is not obvious, and what makes this more than a skill index.
/motion-doctrine — the GATEWAY; load it first
"These rules SUPERSEDE generic / upstream motion guidance."
Without it, a multi-scene video becomes a stack of independently animated slides. With it, the
scenes become one continuous camera move. It covers the vector law (how you exit determines how
you enter), Z scale-sign, carrier elements, causal motion, the Seam Gate, and the ban on idle
wobble: movement must perform, not breathe.
It routes to lower-level techniques: /cut-the-curve, /oversized-cursor, and /seam-craft.
/cut-the-curve — the technique catalog
Five cuts with matched velocity (zoom-through, reverse zoom-through, cut-the-curve, waterfall cut,
rack-focus blur-cut), plus two in-scene techniques (staggered waterfall entry and slow-fast-slow
nudge curve). Includes the 10/65/25 slide ratio.
Read it before: authoring a transition, handing off text to a beat, a kinetic entrance, or group
repositioning.
/seam-craft — render correctness
Requirements for transitions to composite correctly on the master timeline. Load it when assembling
index.html and whenever a white flash appears in a cut or crossfade, especially in dark films.
It covers the opaque stage-ground guard (#root background).
/business-motion-film — the independent critic
The only one of the five with a critique loop: a builder and a separate, tough critic, with an
explicit quality bar. Its motion principles were distilled from 28 professional launch films.
It also covers sound design and a business-offer playbook, and uses Three.js selectively.
Use it when quality matters more than speed and the work is for a client.
/saas-motion-video — avoid repetition
Tone matrix, variety audit, a 24-transition atlas, and 100 storyboard themes. It solves one
problem: two product videos should not look like the same video. A seven-stage process.
/captions-overlay — captions are overlays
Three models, drop / rail / embed (35 styles in the catalog). Captions are composited over
the film; do not reserve a bottom strip and push the content out of the way. This doctrine applies
on top of /embedded-captions.
§Product launch — visual proof and QA
For a product promo or demo, route to /product-launch-video and apply these criteria during
storyboarding and final review. They are conditional gates based on the brief and available assets;
do not impose a fixed duration, feature count, or pace.
- Make the opening frame work as a thumbnail. Review the first frame on its own. It should
communicate the promise or create interest without relying on an empty fade. Keep the chosen hook;
do not force a UI screen when the story calls for another kind of opening.
- Show verifiable product behavior. When a feature proves the benefit, show the action, the
product's visible response, and the user outcome. Base screens, controls, and results on captured
or otherwise confirmed material. Do not invent behavior to fill the sequence.
- Compose for each aspect ratio. If the brief asks for both landscape and vertical versions,
plan and review each as its own layout. Reposition copy and product for the vertical frame instead
of relying on an automatic crop. Do not create extra versions by default.
- Keep data and claims truthful. Synthetic data is fine for protecting personal information,
as long as it looks plausible and is clearly fictional when that could be misleading. Never use
real personal data without authorization or show a capability, result, or CTA the product does
not offer.
These criteria do not replace real capture as the source of truth, the promise and story arc in
/product-launch-video, or HyperFrames storyboard and render gates. Source: 12 rules for a launch
video — Amanda Sartini.
/oversized-cursor — the house style
Oversized macOS cursor. Use it when the scene has a cursor, when a pointer leads the action, or
when a static or lifeless scene needs an effective, low-cost source of motion.
The sound layer
/hyperframes-audio handles audio already placed in the composition: fades, crossfades, gain,
automation, VO ducking/carving, effect chains, and submix buses. /media-use handles media
sources. Keep their roles straight: /media-use finds and generates assets; /hyperframes-audio
mixes what is already on the timeline.
§FFmpeg — the processing engine
Source: kajisho5/ffmpeg-skill
"Give your coding agent a video editor." — Local FFmpeg · No cloud · No API keys
HyperFrames creates video (HTML → MP4); ffmpeg-skill processes existing media. They work
together: one renders new compositions, while the other edits actual files.
Structured workflow
probe (measure) → edit (lossless when possible) → check (validate) → verify (contact sheet)
The key difference: the agent does not guess at parameters. It probes the media first (duration,
fps, resolution, HDR, audio channels), edits based on those facts, then checks the result.
42 tools
| Group |
Tools |
| Analysis |
probe, scenes, look |
| Editing |
cut, join, silence, fit, crop, cropdetect, denoise, stabilize, reverse, speedramp, loop, freeze, pad, broll, metadata, grid |
| Audio |
audio, sync, loudness |
| Image |
caption, overlay, graphics, color |
| Delivery |
export, proxy, check, report |
| Orchestration |
render, batch, multicam, verify |
When to use it
| Task |
Use |
| Create a video from scratch (promo, explainer, motion graphic) |
HyperFrames |
| Cut, join, or process existing footage |
ffmpeg-skill |
| Adjust loudness for a platform |
ffmpeg-skill |
| Remove recording silences |
ffmpeg-skill |
| Sync multiple cameras |
ffmpeg-skill |
| Convert HDR to SDR for delivery |
ffmpeg-skill |
| Add captions to an existing video |
ffmpeg-skill |
| Render an HTML-to-MP4 composition |
HyperFrames |
Delivery presets
Ready-made templates for: tiktok, reels, shorts, youtube, x, linkedin, facebook, and
podcast.
python3 $S/export.py input.mp4 --preset reels --json
python3 $S/render.py talk.mp4 --template tiktok --cues cues.txt
python3 $S/check.py output.mp4 --platform youtube # PASS/WARN/FAIL
Installation
npx ffmpeg-skill --all # install for Claude, Cursor, and Codex
npx ffmpeg-skill doctor # check available FFmpeg components
Requirements: FFmpeg 5.0+ and Python 3.9+ (standard library only).
§fframes — alternative engine
Source: dmtrKovalenko/fframes, skill installed through
fframes.studio.
Use fframes-video when the video is primarily vector-based and GPU rendering, automated
inspection, or batch processing is worth the added complexity of Rust and native libraries.
Recommended cycle:
timeline → inspect → strip/frame/onion → audio analyze → render --draft → render
inspect checks fonts, images, SVG, text clipping, and failures without rendering every pixel.
strip, frame, onion, and snapshot produce visual evidence; audio analyze measures LUFS,
true peak, clipping, and silence. Review these outputs before calling the video finished.
The engine is MIT-licensed, but installation requires Rust, Skia with Metal/Vulkan or a CPU backend,
libclang, nasm, Ninja, and FFmpeg codecs for the target platform. The project's performance
claims are hypotheses to test locally, not a guarantee from this Ninja.
Do not use fframes-video to edit existing media. Keep using ffmpeg-skill for probing, cuts,
normalization, multicam work, and delivery.
§Alternatives to integrate
The alternatives in the source image address real needs, but they do not yet have the same level of
agent integration as HyperFrames. Add support through small, verifiable adapters:
- Revideo/Motion Canvas skill: start with Revideo, which already exposes
renderVideo(), a
React player, dynamic inputs, and parallel rendering. Also cover Motion Canvas scaffolding,
generators, audio sync, FFmpeg export, check, and integration with motion-doctrine and
seam-craft.
- MoviePy skill: cover API v2, data-driven composition, effects, and audio. Delegate file
operations to
ffmpeg-skill and finish with check/verify.
- Benchmark matrix: compare all four paths for determinism, render time, alpha, audio,
1080×1920 output, local/server execution, and cost/licensing.
- Capability detection: the router should say when Motion Canvas or MoviePy is not installed
instead of routing to a nonexistent skill.
This would extend the Ninja without duplicating what ffmpeg-skill already handles.
§Art styles — watercolor, kinetic typography, film styles, characters, and technical illustrations
For the full family × style map (8 families, 81 styles), see
references/film-families-and-styles.md.
Source: tuzhechen2005/opus-video-skills
Two skills that produce video entirely in code: each frame is a pure function of time, with no
generative models. They render in headless Chrome with FFmpeg.
/painted-animation — animated watercolor cartoons
It draws each shot with p5.js and the p5.brush watercolor library. Characters have expression
libraries and motion principles. Music videos are cut to measured beats; lyric videos use
word-by-word karaoke captions.
Use it for: animated shorts, music videos, karaoke lyric videos, hand-painted or watercolor
looks, ink, and character-driven cartoons.
Extra dependency: Python 3 with numpy (for beat detection only).
/kinetic-reel — kinetic type showreels with WebGL
It combines a 2D typography canvas with Three.js layers (particle terrain, liquid marble, chrome
knot, and a cloud condensing into shape), followed by a WebGL post-pass. Shape-continuity
transitions connect the shots. The score is synthesized from the same timeline as the visuals.
Use it for: portfolio reels, work reels, product intros, and kinetic type with 3D visual effects.
Overlap: HyperFrames /motion-graphics also supports kinetic typography, but not these specific
WebGL layers (particle terrain, liquid marble). Choose /kinetic-reel when you need those 3D effects.
Film style libraries — Lemo-Opuscar (66) and MG Styles (15)
Two catalogs of complete film styles, each with an example film made entirely in code (picture,
music, voice). Opuscar groups its styles as Evidence Films, Edit & Documentary, Information &
Keynote, Graphic & Type, Hand-drawn & Painting, Materials & 3D, Print & Printmaking, Cartoon &
Anime, Games, East Asian Traditions, and Cinema & Eras. MG Styles covers motion-design looks such as
flat vector, isometric 2.5D, shape morph, Bauhaus, synthwave, aurora glass, sticker explainer, HUD,
and vertical variety captions.
- Opuscar runs through its own
lemo-opuscar skill. It directs the whole film from its
AGENTS.md and DIRECTOR.md. Install it only with the user's approval:
claude plugin marketplace add lemomo-ai/lemo-opuscar and
claude plugin install lemo-opuscar@lemolab.
- MG Styles is a prompt library: copy
prompts/<slug>.md, replace the Creative seed, keep the
Signature features, set Output to 1080×1920 for Reels, and review twice with rubric.md.
- Evidence and documentary styles require sourced numbers and real material; do not invent them.
ClaudeAnimationBase — a hand-painted character that acts
Locally synced at {{JUMP_SKILLS_DIR}}/repos/video-ninja/ClaudeAnimationBase/. It is a p5.js +
p5.brush kit for a painted character with 31 emotions, views, gazes, gestures, hats, and dances.
Its ANIMATION_GUIDE.md makes the agent storyboard first, build shot by shot, and check its own
contact sheets and frame strips before rendering.
Use it for: top-of-funnel shorts where a character lives the audience's situation, without text.
Mascot rule: the kit's character (Clawd) is Anthropic's mascot. Use Clawd when the video is
about Claude. For any other subject, brand, or client, create a new character with the same kit.
Either way, a person reviews the character before external use.
Overlap: /painted-animation uses the same p5.brush medium and adds beat-cut music videos and
karaoke lyrics. Choose ClaudeAnimationBase when the film needs a ready character rig and its review loop.
Anatomy — isometric illustrations for technical explainers
Anatomy is synchronized as a local source repository at
{{JUMP_SKILLS_DIR}}/repos/video-ninja/anatomy/. It turns a concept into an isometric object or
machine, with parts, motion, and model-generated data. Use it when showing a physical mechanism makes
the explanation clearer, such as a cache represented as a lock or a rate limiter as a reservoir.
It can produce standalone HTML, standalone SVG, or React/Next components; WebGL is optional.
Geometry audits and Chrome captures help check fit, lines, and visual states. Anatomy is not a chart
library, timeline, editor, or video engine. Its 3D mode is in beta, and detailed figures take time.
When the source path exists: read SKILL.md from the synced repository and follow its build and
verification workflow → /hyperframes integrates the asset and renders the video →
/motion-doctrine governs motion and transitions. If the source path is missing, use HyperFrames
composition tools without implying Anatomy is available.
Details, usage criteria, limits, and the original X post: references/anatomy.md.
Model recommendation
It works best with Claude Opus 5.5, but that is not a requirement. Other models can use these skills
with varying results.
§3D graphics — the Three.js pack
Source: scottstts/Threejs-Awesome-Graphics-Agent-Skills
— 24 skills, MIT. Installed globally by the pack's own installer
(npx threejs-awesome-graphics-agent-skills@latest install --agent universal); excluded from the
repo sync because its clone is about 261 MB.
A library of Three.js subsystems, not a workflow: each skill owns one visual system and ships
working examples and assets that carry much of the implementation value. Start at
threejs-skill-router — it maps a required visual result to the smallest skill set and defines the
execution order (visual contract → camera → subject → animation → fields → lighting/shadows →
image pipeline → atomic effects → validation).
| Group |
Skills |
| Routing and validation |
threejs-skill-router, threejs-visual-validation |
| Scene building |
threejs-camera-direction, threejs-procedural-animation, threejs-procedural-fields, threejs-procedural-geometry, threejs-procedural-architecture, threejs-procedural-vegetation |
| Surfaces, materials, and planets |
threejs-procedural-materials, threejs-parallax-occlusion-mapping, threejs-procedural-planets, threejs-temporal-surfaces |
| Sky and weather |
threejs-atmosphere-aerial-perspective, threejs-volumetric-clouds, threejs-precipitation-surfaces |
| Water |
threejs-spectral-ocean, threejs-water-optics |
| Space and effects |
threejs-raymarched-space-effects, threejs-procedural-vfx |
| Image pipeline |
threejs-shadow-systems, threejs-screen-space-ambient-occlusion, threejs-bloom, threejs-exposure-color-grading, threejs-image-pipeline |
When to use it: product films and promos that need a hero 3D element, motion graphics with a 3D
climax, explainers that show a mechanism as a rendered object, or any shot whose value is an
advanced graphics system (ocean, clouds, planets, bloom). It complements /kinetic-reel, which
already uses simple Three.js layers, and /business-motion-film, which uses Three.js selectively.
Boundaries:
- It does not plan, score, cut, or deliver a film. Bring the rendered output into
/hyperframes
(or Remotion) and apply the usual doctrine: /motion-doctrine, /cut-the-curve, /seam-craft.
- Do not load a skill for API setup alone; inspect the installed Three.js version and use the
official docs. WebGPU/TSL paths require a matching Three.js version.
- One example (
threejs-precipitation-surfaces, wet-puddle rain) includes GPL-licensed source
material — keep its license boundary when copying or publishing.
Coupling to the Ninja's flow: treat this layer as a shot generator. Define the visual
contract, build the subsystem, validate with threejs-visual-validation (fixed-view diagnostics,
seed sweeps, budget evidence), capture frames deterministically, and only then composite the shot
into the master timeline.
§Motion Lab — code-driven motion, from brief to validated loop
Use this method for loops, product films, and code-generated motion. Start with /hyperframes, load
/motion-doctrine, and treat the model as the author of the program that draws the frames. Every
frame must be reproducible and inspectable.
Before generating code, turn the brief into a frame-ranged state list: one main action per shot, the
handoff to the next shot, and what must stay consistent (product, shape, proportions, brand). Specify
the goal, engine, format, resolution, fps, duration, camera, and measurable parameters. Replace vague
requests such as “make it feel premium” with observable decisions. Name visual patterns to avoid,
then update the list after reviewing the first render.
Add review aids to the preview itself—frame labels, a playhead, or beat markers—to check timing and
landings; remove them from the final export. Render stills before the full video, review a contact
sheet and frames around any problems, and limit each pass to one or two adjustments described by
frame and measurement. Keep numerical audits separate from visual critique. Two to four passes is a
reference from the article, not a hard limit.
For sound, write frame-linked cues, measure the decoded file for sync, loudness, true peak, and
clipping, and listen to the final mix. Metrics do not replace listening. For an N-frame loop, render
0..N-1 and use phase = frame / N with whole cycles to close the seam. The article reports a
-14 LUFS/-1 dBTP target and sound hits about one frame after the image; treat these as that lab's
reference and check the delivery platform's requirements.
Separate product facts from creative decisions. Use real screens, logos, and assets. Check the asset
list before animating and stop to request anything missing; do not draw a replacement interface.
For visual references, identify the style grammar you can borrow without copying shots or assets
without permission. Compose and review each aspect ratio as its own variant. Save the brief, state
list, references, approved assets, acceptance criteria, and receipts for each stage. Gates should
let the workflow resume, request information, or stop when evidence is missing.
The procedure, checklist, and source comparison are in
references/motion-lab.md. The original sources are [Opus 5.5 Motion
Lab](https://x.com/i/article/21050
…(truncated)
1---2name: video-ninja3description: >-4 Master orchestrator for video production with agents. Routes to 79 globally installed skills5 from 10 repositories and one well-known source, plus Anatomy and 12 DaVinci Resolve editing skills6 from locally synced repositories, plus a film-family and film-style map (8 families, 81 styles from7 Lemo-Opuscar and MG Styles, and the ClaudeAnimationBase character kit). It also covers optional tools for speech timing, reusable motion8 assets, interactive animations, programmatic graphics, web audio, mathematical explainers, and9 advanced 3D graphics, and adds a proven video-pipeline methodology layer.10 Use for ANY video task: making, editing, cutting, captioning, animating, rendering, reviewing11 or publishing a video, motion graphic, promo, launch film, product demo, talking-head package,12 changelog reel, explainer, lyric video, slideshow deck, or Remotion project.13 Covers transcript-driven cutting, caption doctrine, motion craft and quality doctrine,14 body/framing awareness, color setups, media and sound design, and deterministic render pipelines.15 Triggers: video, vídeo, make a video, editar vídeo, corte, cortar, edit, trim, legendar,16 caption, legenda, subtitulo, animate, animação, motion graphic, motion design, promo, launch17 video, teaser, trailer, ad, comercial, product film, product demo, demo reel, showreel,18 sizzle, explainer, faceless, faceless-explainer, talking head, podcast, interview, overlay,19 kinetic typography, lower third, kinetic title, storyboard, slideshow, deck, pitch deck,20 changelog video, release video, lyric video, beat sync, render, mp4, composition, HyperFrames,21 Remotion, DaVinci Resolve, Resolve Studio, GSAP, Three.js, WebGL, LUT, grade, color grade, BGM,22 SFX, sound design, voiceover, TTS,23 thumbnail, screen recording, tutorial video, SaaS video, founder video, YouTube, youtube video,24 cold open, end card, Lottie, dotLottie, Rive, title card, Reels, film style, estilo de vídeo,25 família de vídeo, Opuscar, MG styles, personagem animado, character animation.26metadata:27 source: https://skillmd.com/skills/fabricioctelles/video-ninja28---2930# Video Ninja3132**Jump Skill** — Master orchestrator that routes video tasks to 79 globally installed skills from 1033repositories and one well-known source, Anatomy and DaVinci Resolve editing skills from locally34synced repositories, plus a methodology layer distilled from the My-Little-Studio pipeline.3536> This ninja routes any video task to the installed or locally synced skills. It is the required entry point: read it37> before choosing a video skill.3839---4041## Why this ninja exists4243The ten globally installed source repositories cover **rendering**, **media processing**, **craft**, **frameworks**,44**animation libraries**, **art styles**, and **3D graphics subsystems**, but each is a silo.45HyperFrames can render video, but it has no opinion on quality. motion-video-kit has a quality46doctrine, but no renderer. Remotion is47an alternative framework, not a plug-in for HyperFrames. opus-video-skills brings distinctive looks48such as watercolor and kinetic typography, but not the other repositories' craft doctrine.49ffmpeg-skill works on existing footage; it does not build compositions from scratch. gsap-skills50teaches correct GSAP patterns but is not a video engine. dotlottie-web handles Lottie assets but51does not compose them into video. The Three.js pack supplies advanced 3D graphics subsystems, but it52neither plans nor delivers a film.5354This ninja is the layer that **chooses and connects** them, and keeps track of what the ecosystem55still lacks.5657---5859## The golden rule6061> **`/hyperframes` is the default entry point for video creation and composition.**62> It chooses among the 10 workflows and loads domain skills as needed. For footage edits that must63> be built in DaVinci Resolve Studio, use the optional `video-editor-skills` route instead.64> This ninja does **not replace** HyperFrames routing; it tells you *which layer to use* and *when65> HyperFrames alone is not enough*.6667For video creation, animation, composition, and rendering, start with `/hyperframes`. For a68talking-head, vlog, or class timeline that should be built in Resolve Studio, use the gated69`video-editor-skills` route. Other exceptions include Remotion, screen capture, craft doctrine,70pipeline methods, and the YouTube Video steer in [references/youtube-video.md](references/youtube-video.md).7172---7374## The globally installed source repositories7576| Repository | Skills | Layer | Status |77|---|---|---|---|78| [`heygen-com/hyperframes`](https://github.com/heygen-com/hyperframes) | 27 | Renderer + domain skills | Installed, Apache-2.0 |79| [`kajisho5/ffmpeg-skill`](https://github.com/kajisho5/ffmpeg-skill) | 1 (42 tools) | Media processing | Installed, MIT |80| [`echris6/motion-video-kit`](https://github.com/echris6/motion-video-kit) | 1 | Quality doctrine | Installed, MIT |81| [`remotion-dev/skills`](https://github.com/remotion-dev/skills) | 12 | Alternative framework | Installed |82| [`Rieranthony/product-film-skill`](https://github.com/Rieranthony/product-film-skill) | 1 | Screen capture | Installed, MIT |83| [`tugrawork-creator/saas-motion-kit`](https://github.com/tugrawork-creator/saas-motion-kit) | 1 | Variety and anti-repetition | Installed |84| [`tuzhechen2005/opus-video-skills`](https://github.com/tuzhechen2005/opus-video-skills) | 2 | Procedural art styles | Installed, MIT |85| [`greensock/gsap-skills`](https://github.com/greensock/gsap-skills) | 8 | Official GSAP skills: timelines, ScrollTrigger, plugins, React | Installed, MIT |86| [`LottieFiles/dotlottie-web`](https://github.com/LottieFiles/dotlottie-web) | 1 | Modern Lottie player: Rust+WASM, state machines, themes | Installed, MIT |87| [`scottstts/Threejs-Awesome-Graphics-Agent-Skills`](https://github.com/scottstts/Threejs-Awesome-Graphics-Agent-Skills) | 24 | Advanced Three.js graphics subsystems | Installed by its own installer; excluded from sync (~261 MB), MIT |8889Provenance for globally installed skills is recorded in `~/.agents/.skill-lock.json`. The Three.js90pack is the exception: its own installer (`npx threejs-awesome-graphics-agent-skills@latest install91--agent universal`) installs to `~/.agents/skills/` without a lockfile entry. `fframes-video` is92installed separately through `fframes.studio`.9394### Locally synced source skills9596| Repository | Skill | Role | License |97|---|---|---|---|98| [`wheresryan22/anatomy`](https://github.com/wheresryan22/anatomy) | `anatomy` | Isometric technical figures for explainers | MIT |99| [`appariciojunior/video-editor-skills`](https://github.com/appariciojunior/video-editor-skills) | 12 skills | Optional first-pass editing in DaVinci Resolve Studio | CC BY-NC 4.0; non-commercial use only |100101Both are declared in root `repos.md` and synced under `repos/video-ninja/` so the Ninja can load102their instructions when needed. See [references/repos.md](references/repos.md).103104### Film style libraries and the character kit105106| Repository | What it adds | How the Ninja uses it | License |107|---|---|---|---|108| [`lemomo-ai/lemo-opuscar`](https://github.com/lemomo-ai/lemo-opuscar) | 66 film styles made in code, each with a demo film, `STYLE.md` and a director's guide | Through the `lemo-opuscar` skill (Claude plugin), which keeps its own sparse library in `~/lemo-opuscar`. Not synced (~195 MB) | MIT code; demo films CC BY 4.0 |109| [`Vincentwei1021/mg-styles-15`](https://github.com/Vincentwei1021/mg-styles-15) | 15 motion-design styles with full prompt, source, renderer and review rubric | Sparse checkout of `prompts/`, `harness/` and `lib/` on demand. Not synced (~1.2 GB) | MIT |110| [`JohnHeibel/ClaudeAnimationBase`](https://github.com/JohnHeibel/ClaudeAnimationBase) | p5.brush hand-painted character kit: 31 emotions, views, gestures, hats, contact-sheet review | Synced locally under `repos/video-ninja/ClaudeAnimationBase/`; read its `ANIMATION_GUIDE.md` | MIT; Clawd only in videos about Claude, otherwise your own character |111112Families, styles, install steps and license notes:113[references/film-families-and-styles.md](references/film-families-and-styles.md).114115### Separately installed skill116117| Source | Skill | Role | Installation |118|---|---|---|---|119| [`fframes.studio`](https://fframes.studio) | `fframes-video` | Alternative Rust/SVG renderer with Skia GPU, FFmpeg, and agent-readable QA | Well-known, installed globally |120121### Evaluated external tools that are not installed122123| Source | Role | When to consider it | Status |124|---|---|---|---|125| [`m-bain/whisperX`](https://github.com/m-bain/whisperX) | Local ASR with word-level timestamps and diarization | Talking-head, interview, or podcast work that needs word timing or speaker identification | Optional backend; not installed. See [references/whisperx.md](references/whisperx.md) |126| [`airbnb/lottie-web`](https://github.com/airbnb/lottie-web) | Player for After Effects Lottie animations | Reuse a project-provided `.json` Lottie asset in a HyperFrames composition | On-demand dependency; not installed by the Ninja. See [references/lottie.md](references/lottie.md) |127| [`ManimCommunity/manim`](https://github.com/ManimCommunity/manim) | Python engine for mathematical animation | Recurring math explainers that justify another renderer and adapter | Evaluated, not installed. The tweet links to `3b1b/manim` (ManimGL). See [references/repos.md](references/repos.md) |128| [`rive-app/rive-wasm`](https://github.com/rive-app/rive-wasm) | Interactive animations with native state machines | Project has `.riv` assets from Rive Editor, or needs animations that react to app state | On-demand dependency. See [references/rive.md](references/rive.md) |129| [`goldfire/howler.js`](https://github.com/goldfire/howler.js) | Web audio control: sprites, fades, spatial audio | Sound effects with precise timing, audio sprites, 3D positional audio | On-demand dependency. See [references/howler.md](references/howler.md) |130| [`vercel/satori`](https://github.com/vercel/satori) | JSX → SVG for title cards and thumbnails | Batch-generate title cards, thumbnails, or text-heavy graphics from data | On-demand dependency. See [references/satori.md](references/satori.md) |131132Anatomy produces a **visual asset or scene**, not the finished video. Its source is synchronized at133`{{JUMP_SKILLS_DIR}}/repos/video-ninja/anatomy/`; read that repository's `SKILL.md` when routing to134it. Build and inspect the figure, then bring the output into `/hyperframes` and follow the motion,135composition, and rendering doctrine. If the path is missing, treat Anatomy as unavailable and use136the fallback described in [references/anatomy.md](references/anatomy.md).137138Do not assume WhisperX or Manim is installed or available. Lottie is an asset format: load its player139only when the project already includes that kind of animation.140141### Additional reference documentation142143The following tools are documented in the references folder for on-demand use:144145| Tool | Reference | Use case |146|---|---|---|147| Rive | [references/rive.md](references/rive.md) | Interactive animations with state machines; alternative to Lottie when project has `.riv` assets |148| Howler.js | [references/howler.md](references/howler.md) | Web audio control: sprites, fades, spatial audio; complements `/hyperframes-audio` |149| Satori | [references/satori.md](references/satori.md) | JSX → SVG for title cards, thumbnails, OG images; batch generation of text graphics |150| YouTube Video | [references/youtube-video.md](references/youtube-video.md) | Raw talking-head edited into a polished YouTube video with explanatory motion graphics |151152These tools are not installed skills but are documented for when their specific capabilities are needed.153The YouTube Video row is a pipeline steer, not a library.154155Five more pipeline steers cover asset tooling used while producing graphics for a composition:156[excalidraw.md](references/excalidraw.md) (hand-drawn diagrams as video assets),157[penpot.md](references/penpot.md) (open-source design source with an official MCP),158[fontsource.md](references/fontsource.md) (self-hosted fonts for deterministic render),159[lucide.md](references/lucide.md) (UI icon set), and160[svgo.md](references/svgo.md) (animation-safe SVG optimization). None of them installs a skill.161162## Engine map163164The source image mixes composition engines, project frameworks, and a file editor. Use these165distinctions before choosing a workflow:166167| Engine | How it works | When to choose it | Status in the Ninja |168|---|---|---|---|169| **HyperFrames** | HTML/CSS/JS in headless Chrome + FFmpeg | New compositions, motion design, and agent-directed video | Default, installed |170| **ffmpeg-skill** | Probe → edit → validate existing files | Cutting, joining, audio normalization, multicam, and delivery | Processing, installed |171| **fframes-video** | Per-frame Rust/SVG, Skia GPU, FFmpeg, and inspection CLI | High-throughput vector rendering, batch work, and automated review | Alternative engine, installed |172| **Remotion** | React/TypeScript, local or Lambda rendering | Existing React projects, composition ports, or distributed rendering | Alternative framework, installed |173| **Motion Canvas / Revideo** | TypeScript generators; Revideo adds a React player, headless rendering, and dynamic inputs | Motion Canvas for editor-based vector animation; Revideo for parameterized templates and Node/serverless rendering | Evaluated; no skill installed |174| **MoviePy** | Python clips, compositions, and frame effects | Data-driven Python pipelines or composition prototypes | Evaluated; no skill installed |175| **Manim Community Edition** | Python for programmatic math animation | Recurring explainers about math, charts, or geometry | Evaluated; no skill or adapter installed |176177Do not present Motion Canvas, Revideo, MoviePy, or ManimCE as installed capabilities until a skill178defines routing, a render contract, and verification. If a project already uses one of these tools,179the Ninja can keep it and apply the same motion, audio, and validation doctrine.180181Check Remotion's license before production: its code is source-available, and the free license covers182individuals and organizations of up to three people. Larger teams or automated use may require a183Company License. Do not describe it as MIT or OSI-approved open source.184185---186187## Routing188189### Step 1 — Is this actually a video task?190191If it is **not** a video task, this ninja does not apply:192193| Request | Route to |194|---|---|195| Website/app | `impeccable`, `apple-design` |196| UI animation only (not a video) | `animate`, `improve-animations` (Emil Kowalski pack) |197| Marketing copy or script only | `copywriting`, `social` |198199### Step 2 — Route by deliverable200201**Let `/hyperframes` choose among the 10 workflows.** Its priority table is authoritative. This ninja202only needs to identify the **layer** to add:203204| Request | Workflow | Additional Ninja layer |205|---|---|---|206| Legenda em talking-head | `/embedded-captions` | + `/captions-overlay` |207| Cards de overlay em podcast | `/talking-head-recut` | + `/cut-the-curve` |208| Product or URL promo | `/product-launch-video` | + `/motion-doctrine`, `/seam-craft`, §Product launch |209| Weekly changelog video | `/changelog-video` | — |210| Screen recording → demo | **`/product-film`** (dedicated skill) | See §Remotion |211| Business film (live action, AI, premium) | **`/business-motion-film`** | See §Doctrine |212| Anti-repetition SaaS promo | **`/saas-motion-video`** | See §Doctrine |213| Watercolor cartoon / karaoke lyric video | **`/painted-animation`** | See §Art styles |214| Kinetic type showreel / portfolio | **`/kinetic-reel`** | See §Art styles |215| Technical explainer with an isometric mechanism or object | **Anatomy (when synced)** | Read its local `SKILL.md`, build and inspect SVG/HTML; bring the asset into `/hyperframes` for composition and rendering. See [references/anatomy.md](references/anatomy.md) |216| Talking-head, vlog, or class edit in DaVinci Resolve Studio | **`video-editor-skills` (when synced and license permits)** | Read its local `skills/edit-video/SKILL.md`; check Studio scripting and the commercial-use restriction first. See [§DaVinci Resolve](#davinci-resolve) |217| Talking-head with word timing or diarization | `/embedded-captions` + **optional WhisperX** (if installed) | Align words or identify speakers, then check against the audio. The “tape” is still needed for cuts that depend on restarts or syllable onsets. See [references/whisperx.md](references/whisperx.md) |218| Raw talking-head → polished YouTube video with explanatory motion graphics | **YouTube Video steer** (Remotion) | Do not start in HyperFrames. Read [references/youtube-video.md](references/youtube-video.md). Keep the speech language. Do not publish without approval. |219| Project supplies a Lottie `.json` animation | `/hyperframes` + **Lottie Web on demand** | Disable autoplay and seek explicitly by frame or time for deterministic capture. See [references/lottie.md](references/lottie.md) |220| High-rigor math explainer | **ManimCE (optional, if installed and justified)** | Specialized math renderer; inspect the final composition. HyperFrames remains the default for other videos |221| Code-generated motion, loops, or frame animation | **`/hyperframes`** | + `/motion-doctrine`, see §Motion Lab |222| **3D scene, procedural graphics, or a Three.js subsystem** (materials, ocean, clouds, planets, VFX) | **`threejs-*` pack** (start at `threejs-skill-router`) | Load only the targeted subsystem, then bring the result into `/hyperframes` or the project's engine. See §3D graphics |223| **Cut, join, or process existing footage** | **`ffmpeg-skill`** | See §FFmpeg |224| **Adjust loudness for a platform** | **`ffmpeg-skill`** | See §FFmpeg |225| **Remove recording silences** | **`ffmpeg-skill`** | See §FFmpeg |226| **Sync multiple cameras** | **`ffmpeg-skill`** | See §FFmpeg |227| Vector video with GPU rendering and CLI QA | **`fframes-video`** | See §fframes |228| Existing Motion Canvas/Revideo project | **Motion Canvas/Revideo** | Keep it only if the dependency already exists; apply §Doctrine |229| Python composition or data pipeline | **MoviePy** | Use only when Python is a requirement; finish with §FFmpeg |230| Explainer, PR, music, deck, motion, open-ended video | The 10 workflows | — |231| Film in a **named style** (e.g. Blueprint, Ukiyo-e, Satellite Briefing, Bauhaus) or "which styles are there?" | **`lemo-opuscar`** for the 66 Opuscar styles; **MG Styles prompt + harness** for the 15 MG styles | See Step 2b and [references/film-families-and-styles.md](references/film-families-and-styles.md). If `lemo-opuscar` is not installed, ask before installing it |232| Hand-animated character that acts (emotions, gestures), no text | **ClaudeAnimationBase (when synced)** or `/painted-animation` | Read its `ANIMATION_GUIDE.md`; use the Clawd mascot only when the video is about Claude. See §Art styles |233234### Step 2b — Pick the film family, then the style235236For short-form films (Reels, Shorts, promos, explainers), name the **family** (how the story is237told) before the **style** (how it looks):238239| Family | Primary route |240|---|---|241| A · 3D cinema | `threejs-*` pack; Blender only if the project already has it |242| B · 2D motion with 3D objects | `/hyperframes` + `/motion-graphics`, `threejs-*` for objects |243| C · Phone and chat | `/hyperframes` registry blocks, `/product-launch-video` |244| D · Device in 3D | `/product-film` or `/hyperframes` device frame + `threejs-*` |245| E · Kinetic typography | `/kinetic-reel` or `/motion-graphics` |246| F · Map and diagram | Anatomy, `/hyperframes` data blocks, `remotion-maps` |247| G · You on camera | `/talking-head-recut`, `/embedded-captions`, YouTube steer, `video-editor-skills` |248| H · Hand-animated character | ClaudeAnimationBase, `/painted-animation` |249250Then pick at most one of the 81 styles that fits the family and the use case. Upstream examples are25116:9: recompose for 9:16 instead of cropping. Full table, fit lists and production steps:252[references/film-families-and-styles.md](references/film-families-and-styles.md).253254### Step 3 — Load the relevant domains255256Cross-cutting: whenever photography or other media is involved, **consider `/media-use`**.257Motion is mandatory: **always load `/motion-doctrine` before composing** any animation (see §Doctrine;258it declares itself the GATEWAY and supersedes generic guidance).259260---261262## Video production layers263264| # | Layer | Skills | Responsibility |265|---|---|---|---|266| 1 | **Renderer** | `hyperframes`, `hyperframes-cli`, `hyperframes-core` | Deterministic HTML-to-video. `core` is the composition contract; read it before writing HTML |267| 2 | **Processing engine** | `ffmpeg-skill` (42 tools) | probe→edit→verify. Cuts, joins, loudness, captions, HDR-to-SDR, multicam, batch work |268| 3 | **Alternative engine** | `fframes-video` | Rust/SVG, Skia GPU, lane rendering, frame inspection, snapshots, and audio analysis |269| 4 | **Workflows** | `general-video`, `product-launch-video`, `talking-head-recut`, `embedded-captions`, `faceless-explainer`, `pr-to-video`, `music-to-video`, `motion-graphics`, `slideshow`, `figma`, `changelog-video` | The final deliverable |270| 5 | **Craft doctrine** | `motion-doctrine`, `cut-the-curve`, `seam-craft`, `oversized-cursor`, `captions-overlay`, `business-motion-film`, `saas-motion-video` | **An opinion on quality.** What separates “it rendered” from “it looks good” |271| 6 | **Domains** | `hyperframes-animation`, `hyperframes-keyframes`, `hyperframes-creative`, `hyperframes-audio`, `media-use`, `hyperframes-registry`, `hyperframes-studio` | Motion, camera, design, sound, media, and ready-made blocks |272| 7 | **Second framework** | `remotion-*` (12), `product-film` | When Remotion is the right choice |273| 8 | **Art styles** | `painted-animation`, `kinetic-reel`, `lemo-opuscar` (66 styles), MG Styles (15), ClaudeAnimationBase | Distinct procedural looks and film styles; see the family/style map |274| 9 | **Animation library** | `gsap-*` (8 skills) | Correct GSAP patterns: timelines, ScrollTrigger, plugins, React cleanup, performance |275| 10 | **Motion assets** | `dotlottie-web` | Lottie/dotLottie player: state machines, themes, Web Workers, deterministic capture |276| 11 | **3D graphics subsystems** | `threejs-*` (24 skills) | Advanced Three.js graphics: procedural geometry/fields/materials, ocean, clouds, planets, shadows, GTAO, bloom, color grading, VFX, and visual validation |277| 12 | **Timeline editor** | `video-editor-skills` (12 locally synced skills) | Optional transcript-led first-pass edits in DaVinci Resolve Studio; subject to CC BY-NC 4.0 |278279---280281## §Doctrine — the layer engines lack282283This is the part that is **not** obvious, and what makes this more than a skill index.284285### `/motion-doctrine` — the GATEWAY; load it first286287> *"These rules SUPERSEDE generic / upstream motion guidance."*288289Without it, a multi-scene video becomes a stack of independently animated slides. With it, the290scenes become **one continuous camera move**. It covers the vector law (how you exit determines how291you enter), Z scale-sign, carrier elements, causal motion, the Seam Gate, and the **ban on idle292wobble**: movement must **perform**, not breathe.293294It routes to lower-level techniques: `/cut-the-curve`, `/oversized-cursor`, and `/seam-craft`.295296### `/cut-the-curve` — the technique catalog297298Five cuts with matched velocity (zoom-through, reverse zoom-through, cut-the-curve, waterfall cut,299rack-focus blur-cut), plus two in-scene techniques (staggered waterfall entry and slow-fast-slow300nudge curve). Includes the 10/65/25 slide ratio.301302**Read it before:** authoring a transition, handing off text to a beat, a kinetic entrance, or group303repositioning.304305### `/seam-craft` — render correctness306307Requirements for transitions to composite correctly on the master timeline. Load it when assembling308`index.html` and **whenever a white flash** appears in a cut or crossfade, especially in dark films.309It covers the opaque stage-ground guard (`#root` background).310311### `/business-motion-film` — the independent critic312313The only one of the five with a **critique loop**: a builder and a separate, tough critic, with an314explicit quality bar. Its motion principles were distilled from **28 professional launch films**.315It also covers sound design and a business-offer playbook, and uses Three.js selectively.316317**Use it when** quality matters more than speed and the work is for a client.318319### `/saas-motion-video` — avoid repetition320321Tone matrix, variety audit, a 24-transition atlas, and **100 storyboard themes**. It solves one322problem: two product videos should not look like the same video. A seven-stage process.323324### `/captions-overlay` — captions are overlays325326Three models, `drop` / `rail` / `embed` (35 styles in the catalog). Captions are **composited over327the film**; do not reserve a bottom strip and push the content out of the way. This doctrine applies328**on top of** `/embedded-captions`.329330## §Product launch — visual proof and QA331332For a product promo or demo, route to `/product-launch-video` and apply these criteria during333storyboarding and final review. They are conditional gates based on the brief and available assets;334do not impose a fixed duration, feature count, or pace.3353361. **Make the opening frame work as a thumbnail.** Review the first frame on its own. It should337 communicate the promise or create interest without relying on an empty fade. Keep the chosen hook;338 do not force a UI screen when the story calls for another kind of opening.3392. **Show verifiable product behavior.** When a feature proves the benefit, show the action, the340 product's visible response, and the user outcome. Base screens, controls, and results on captured341 or otherwise confirmed material. Do not invent behavior to fill the sequence.3423. **Compose for each aspect ratio.** If the brief asks for both landscape and vertical versions,343 plan and review each as its own layout. Reposition copy and product for the vertical frame instead344 of relying on an automatic crop. Do not create extra versions by default.3454. **Keep data and claims truthful.** Synthetic data is fine for protecting personal information,346 as long as it looks plausible and is clearly fictional when that could be misleading. Never use347 real personal data without authorization or show a capability, result, or CTA the product does348 not offer.349350These criteria do not replace real capture as the source of truth, the promise and story arc in351`/product-launch-video`, or HyperFrames storyboard and render gates. Source: [12 rules for a launch352video — Amanda Sartini](https://x.com/i/article/2109015312729587712).353354### `/oversized-cursor` — the house style355356Oversized macOS cursor. Use it when the scene has a cursor, when a pointer leads the action, or357when a static or lifeless scene needs an effective, low-cost source of motion.358359### The sound layer360361`/hyperframes-audio` handles audio already placed in the composition: fades, crossfades, gain,362automation, VO ducking/carving, effect chains, and submix buses. `/media-use` handles **media363sources**. Keep their roles straight: `/media-use` finds and generates assets; `/hyperframes-audio`364mixes what is already on the timeline.365366---367368## §FFmpeg — the processing engine369370Source: [`kajisho5/ffmpeg-skill`](https://github.com/kajisho5/ffmpeg-skill)371372*"Give your coding agent a video editor."* — Local FFmpeg · No cloud · No API keys373374HyperFrames **creates** video (HTML → MP4); ffmpeg-skill **processes** existing media. They work375together: one renders new compositions, while the other edits actual files.376377### Structured workflow378379```380probe (measure) → edit (lossless when possible) → check (validate) → verify (contact sheet)381```382383The key difference: the agent does not guess at parameters. It probes the media first (duration,384fps, resolution, HDR, audio channels), edits based on those facts, then checks the result.385386### 42 tools387388| Group | Tools |389|---|---|390| Analysis | `probe`, `scenes`, `look` |391| Editing | `cut`, `join`, `silence`, `fit`, `crop`, `cropdetect`, `denoise`, `stabilize`, `reverse`, `speedramp`, `loop`, `freeze`, `pad`, `broll`, `metadata`, `grid` |392| Audio | `audio`, `sync`, `loudness` |393| Image | `caption`, `overlay`, `graphics`, `color` |394| Delivery | `export`, `proxy`, `check`, `report` |395| Orchestration | `render`, `batch`, `multicam`, `verify` |396397### When to use it398399| Task | Use |400|--------|-----|401| Create a video from scratch (promo, explainer, motion graphic) | HyperFrames |402| Cut, join, or process existing footage | **ffmpeg-skill** |403| Adjust loudness for a platform | **ffmpeg-skill** |404| Remove recording silences | **ffmpeg-skill** |405| Sync multiple cameras | **ffmpeg-skill** |406| Convert HDR to SDR for delivery | **ffmpeg-skill** |407| Add captions to an existing video | **ffmpeg-skill** |408| Render an HTML-to-MP4 composition | HyperFrames |409410### Delivery presets411412Ready-made templates for: `tiktok`, `reels`, `shorts`, `youtube`, `x`, `linkedin`, `facebook`, and413`podcast`.414415```bash416python3 $S/export.py input.mp4 --preset reels --json417python3 $S/render.py talk.mp4 --template tiktok --cues cues.txt418python3 $S/check.py output.mp4 --platform youtube # PASS/WARN/FAIL419```420421### Installation422423```bash424npx ffmpeg-skill --all # install for Claude, Cursor, and Codex425npx ffmpeg-skill doctor # check available FFmpeg components426```427428**Requirements:** FFmpeg 5.0+ and Python 3.9+ (standard library only).429430---431432## §fframes — alternative engine433434Source: [`dmtrKovalenko/fframes`](https://github.com/dmtrKovalenko/fframes), skill installed through435[`fframes.studio`](https://fframes.studio).436437Use `fframes-video` when the video is primarily vector-based and GPU rendering, automated438inspection, or batch processing is worth the added complexity of Rust and native libraries.439440Recommended cycle:441442```443timeline → inspect → strip/frame/onion → audio analyze → render --draft → render444```445446`inspect` checks fonts, images, SVG, text clipping, and failures without rendering every pixel.447`strip`, `frame`, `onion`, and `snapshot` produce visual evidence; `audio analyze` measures LUFS,448true peak, clipping, and silence. Review these outputs before calling the video finished.449450The engine is MIT-licensed, but installation requires Rust, Skia with Metal/Vulkan or a CPU backend,451`libclang`, `nasm`, Ninja, and FFmpeg codecs for the target platform. The project's performance452claims are hypotheses to test locally, not a guarantee from this Ninja.453454Do not use `fframes-video` to edit existing media. Keep using `ffmpeg-skill` for probing, cuts,455normalization, multicam work, and delivery.456457---458459## §Alternatives to integrate460461The alternatives in the source image address real needs, but they do not yet have the same level of462agent integration as HyperFrames. Add support through small, verifiable adapters:4634641. **Revideo/Motion Canvas skill:** start with Revideo, which already exposes `renderVideo()`, a465 React player, dynamic inputs, and parallel rendering. Also cover Motion Canvas scaffolding,466 generators, audio sync, FFmpeg export, `check`, and integration with `motion-doctrine` and467 `seam-craft`.4682. **MoviePy skill:** cover API v2, data-driven composition, effects, and audio. Delegate file469 operations to `ffmpeg-skill` and finish with `check`/`verify`.4703. **Benchmark matrix:** compare all four paths for determinism, render time, alpha, audio,471 1080×1920 output, local/server execution, and cost/licensing.4724. **Capability detection:** the router should say when Motion Canvas or MoviePy is not installed473 instead of routing to a nonexistent skill.474475This would extend the Ninja without duplicating what `ffmpeg-skill` already handles.476477---478479## §Art styles — watercolor, kinetic typography, film styles, characters, and technical illustrations480481> For the full family × style map (8 families, 81 styles), see482> [references/film-families-and-styles.md](references/film-families-and-styles.md).483484Source: [`tuzhechen2005/opus-video-skills`](https://github.com/tuzhechen2005/opus-video-skills)485486Two skills that produce video **entirely in code**: each frame is a pure function of time, with no487generative models. They render in headless Chrome with FFmpeg.488489### `/painted-animation` — animated watercolor cartoons490491It draws each shot with p5.js and the p5.brush watercolor library. Characters have expression492libraries and motion principles. Music videos are cut to measured beats; lyric videos use493word-by-word karaoke captions.494495**Use it for:** animated shorts, music videos, karaoke lyric videos, hand-painted or watercolor496looks, ink, and character-driven cartoons.497498**Extra dependency:** Python 3 with numpy (for beat detection only).499500### `/kinetic-reel` — kinetic type showreels with WebGL501502It combines a 2D typography canvas with Three.js layers (particle terrain, liquid marble, chrome503knot, and a cloud condensing into shape), followed by a WebGL post-pass. Shape-continuity504transitions connect the shots. The score is synthesized from the same timeline as the visuals.505506**Use it for:** portfolio reels, work reels, product intros, and kinetic type with 3D visual effects.507508**Overlap:** HyperFrames `/motion-graphics` also supports kinetic typography, but not these specific509WebGL layers (particle terrain, liquid marble). Choose `/kinetic-reel` when you need those 3D effects.510511### Film style libraries — Lemo-Opuscar (66) and MG Styles (15)512513Two catalogs of complete film styles, each with an example film made entirely in code (picture,514music, voice). Opuscar groups its styles as Evidence Films, Edit & Documentary, Information &515Keynote, Graphic & Type, Hand-drawn & Painting, Materials & 3D, Print & Printmaking, Cartoon &516Anime, Games, East Asian Traditions, and Cinema & Eras. MG Styles covers motion-design looks such as517flat vector, isometric 2.5D, shape morph, Bauhaus, synthwave, aurora glass, sticker explainer, HUD,518and vertical variety captions.519520- **Opuscar** runs through its own `lemo-opuscar` skill. It directs the whole film from its521 `AGENTS.md` and `DIRECTOR.md`. Install it only with the user's approval:522 `claude plugin marketplace add lemomo-ai/lemo-opuscar` and523 `claude plugin install lemo-opuscar@lemolab`.524- **MG Styles** is a prompt library: copy `prompts/<slug>.md`, replace the Creative seed, keep the525 Signature features, set Output to 1080×1920 for Reels, and review twice with `rubric.md`.526- Evidence and documentary styles require sourced numbers and real material; do not invent them.527528### ClaudeAnimationBase — a hand-painted character that acts529530Locally synced at `{{JUMP_SKILLS_DIR}}/repos/video-ninja/ClaudeAnimationBase/`. It is a p5.js +531p5.brush kit for a painted character with 31 emotions, views, gazes, gestures, hats, and dances.532Its `ANIMATION_GUIDE.md` makes the agent storyboard first, build shot by shot, and check its own533contact sheets and frame strips before rendering.534535**Use it for:** top-of-funnel shorts where a character lives the audience's situation, without text.536537**Mascot rule:** the kit's character (Clawd) is Anthropic's mascot. Use Clawd when the video is538about Claude. For any other subject, brand, or client, create a new character with the same kit.539Either way, a person reviews the character before external use.540541**Overlap:** `/painted-animation` uses the same p5.brush medium and adds beat-cut music videos and542karaoke lyrics. Choose ClaudeAnimationBase when the film needs a ready character rig and its review loop.543544### Anatomy — isometric illustrations for technical explainers545546Anatomy is synchronized as a local source repository at547`{{JUMP_SKILLS_DIR}}/repos/video-ninja/anatomy/`. It turns a concept into an isometric object or548machine, with parts, motion, and model-generated data. Use it when showing a physical mechanism makes549the explanation clearer, such as a cache represented as a lock or a rate limiter as a reservoir.550551It can produce standalone HTML, standalone SVG, or React/Next components; WebGL is optional.552Geometry audits and Chrome captures help check fit, lines, and visual states. Anatomy is not a chart553library, timeline, editor, or video engine. Its 3D mode is in beta, and detailed figures take time.554555**When the source path exists:** read `SKILL.md` from the synced repository and follow its build and556verification workflow → `/hyperframes` integrates the asset and renders the video →557`/motion-doctrine` governs motion and transitions. If the source path is missing, use HyperFrames558composition tools without implying Anatomy is available.559560Details, usage criteria, limits, and the original X post: [references/anatomy.md](references/anatomy.md).561562### Model recommendation563564It works best with Claude Opus 5.5, but that is not a requirement. Other models can use these skills565with varying results.566567---568569## §3D graphics — the Three.js pack570571Source: [`scottstts/Threejs-Awesome-Graphics-Agent-Skills`](https://github.com/scottstts/Threejs-Awesome-Graphics-Agent-Skills)572— 24 skills, MIT. Installed globally by the pack's own installer573(`npx threejs-awesome-graphics-agent-skills@latest install --agent universal`); excluded from the574repo sync because its clone is about 261 MB.575576A library of **Three.js subsystems**, not a workflow: each skill owns one visual system and ships577working examples and assets that carry much of the implementation value. Start at578`threejs-skill-router` — it maps a required visual result to the smallest skill set and defines the579execution order (visual contract → camera → subject → animation → fields → lighting/shadows →580image pipeline → atomic effects → validation).581582| Group | Skills |583|---|---|584| Routing and validation | `threejs-skill-router`, `threejs-visual-validation` |585| Scene building | `threejs-camera-direction`, `threejs-procedural-animation`, `threejs-procedural-fields`, `threejs-procedural-geometry`, `threejs-procedural-architecture`, `threejs-procedural-vegetation` |586| Surfaces, materials, and planets | `threejs-procedural-materials`, `threejs-parallax-occlusion-mapping`, `threejs-procedural-planets`, `threejs-temporal-surfaces` |587| Sky and weather | `threejs-atmosphere-aerial-perspective`, `threejs-volumetric-clouds`, `threejs-precipitation-surfaces` |588| Water | `threejs-spectral-ocean`, `threejs-water-optics` |589| Space and effects | `threejs-raymarched-space-effects`, `threejs-procedural-vfx` |590| Image pipeline | `threejs-shadow-systems`, `threejs-screen-space-ambient-occlusion`, `threejs-bloom`, `threejs-exposure-color-grading`, `threejs-image-pipeline` |591592**When to use it:** product films and promos that need a hero 3D element, motion graphics with a 3D593climax, explainers that show a mechanism as a rendered object, or any shot whose value is an594advanced graphics system (ocean, clouds, planets, bloom). It complements `/kinetic-reel`, which595already uses simple Three.js layers, and `/business-motion-film`, which uses Three.js selectively.596597**Boundaries:**598599- It does not plan, score, cut, or deliver a film. Bring the rendered output into `/hyperframes`600 (or Remotion) and apply the usual doctrine: `/motion-doctrine`, `/cut-the-curve`, `/seam-craft`.601- Do not load a skill for API setup alone; inspect the installed Three.js version and use the602 official docs. WebGPU/TSL paths require a matching Three.js version.603- One example (`threejs-precipitation-surfaces`, wet-puddle rain) includes GPL-licensed source604 material — keep its license boundary when copying or publishing.605606**Coupling to the Ninja's flow:** treat this layer as a **shot generator**. Define the visual607contract, build the subsystem, validate with `threejs-visual-validation` (fixed-view diagnostics,608seed sweeps, budget evidence), capture frames deterministically, and only then composite the shot609into the master timeline.610611---612613## §Motion Lab — code-driven motion, from brief to validated loop614615Use this method for loops, product films, and code-generated motion. Start with `/hyperframes`, load616`/motion-doctrine`, and treat the model as the author of the program that draws the frames. Every617frame must be reproducible and inspectable.618619Before generating code, turn the brief into a frame-ranged state list: one main action per shot, the620handoff to the next shot, and what must stay consistent (product, shape, proportions, brand). Specify621the goal, engine, format, resolution, fps, duration, camera, and measurable parameters. Replace vague622requests such as “make it feel premium” with observable decisions. Name visual patterns to avoid,623then update the list after reviewing the first render.624625Add review aids to the preview itself—frame labels, a playhead, or beat markers—to check timing and626landings; remove them from the final export. Render stills before the full video, review a contact627sheet and frames around any problems, and limit each pass to one or two adjustments described by628frame and measurement. Keep numerical audits separate from visual critique. Two to four passes is a629reference from the article, not a hard limit.630631For sound, write frame-linked cues, measure the decoded file for sync, loudness, true peak, and632clipping, and listen to the final mix. Metrics do not replace listening. For an N-frame loop, render633`0..N-1` and use `phase = frame / N` with whole cycles to close the seam. The article reports a634-14 LUFS/-1 dBTP target and sound hits about one frame after the image; treat these as that lab's635reference and check the delivery platform's requirements.636637Separate product facts from creative decisions. Use real screens, logos, and assets. Check the asset638list before animating and stop to request anything missing; do not draw a replacement interface.639For visual references, identify the style grammar you can borrow without copying shots or assets640without permission. Compose and review each aspect ratio as its own variant. Save the brief, state641list, references, approved assets, acceptance criteria, and receipts for each stage. Gates should642let the workflow resume, request information, or stop when evidence is missing.643644The procedure, checklist, and source comparison are in645[references/motion-lab.md](references/motion-lab.md). The original sources are [Opus 5.5 Motion646Lab](https://x.com/i/article/21050647648…(truncated)