Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A creative-direction (taste) layer for music videos and short-form edits in the angelcore / cloud-trance / hyperpop visual family. Distills a named-genre aesthetic vocabulary, a mood + color + light system, and a beat-synced editing grammar, then chains ECC's video skills (video-editing, fal-ai-media, remotion-video-creation, motion-*, content-engine) into one production pipeline. Use when the work is not just making a video function but making it feel intentional, when building a music video, a
.claude/skills/affaan-m-taste/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 91% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 120% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 166% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 177% | 0% |
Most AI video advice stops at how to render frames. This skill is the layer above that: what the frames should look like, in what order, cut to what rhythm, so the result reads as one intentional thing instead of a pile of generations.
It encodes a specific taste — the angelcore / cloud-trance / hyperpop family (Bladee "Silver Surfer"-era ethereal trance crossed with heavy angelcore) — distilled from a corpus of saved Reels and a tour through a ~70-entry visual-genre library. It is opinionated on purpose. Taste is a point of view, not a menu.
> The companion file references/genre-taxonomy.md holds the full named-genre catalog. > This file is the actionable layer: mood, grammar, pipeline, and a beat-mapped shot plan.
coherent direction instead of one-off vibes.
"cloud trance", "hyperpop edit", "Bladee", "dreamcore", or names a saved reference.
This skill sits on top of video-editing (the mechanics) and remotion-video-creation (the renderer). Use those for how. Use this for what and why.
video-editing correctlysays taste is the final human pass. The trap: if you only decide taste at the end, every generation and cut upstream was a guess. Pick the direction before the first prompt, then let it constrain everything.
genre (below) is a constraint that buys coherence for free.
Every hard cut lands on a beat or a transient. Frame math is in the pipeline section.
not make taste. You still throw away 80%.
The reference corpus tours a large library of named visual genres. The full list lives in references/genre-taxonomy.md. The useful move is not memorizing 70 names — it is seeing that a genre name is a complete prompt-and-grade preset. When you pick one, you inherit its palette, texture, lighting, and subject matter as a unit.
The genres cluster into families. Pick a primary family and at most one accent:
| Family | Genres in it | Reads as | |--------|-------------|----------| | Ethereal / divine | spiritualism, glacial folk, beacons, zen core, fairy tale | weightless, holy, glowing, soft | | Hyperpop / Y2K-cyber | cyberdelia, acid house, acid nora, neo aggressano, new liquid | glossy, chrome, neon, kawaii-cyber | | Dark / occult | dark academia, smoke nostalgia, communist core, abstract tech | high-contrast, ominous, grain | | Retro / print | retro surfers, art deco, adventure pulp, classic advertising, magazine collage, bumper stickers | flat, graphic, halftone, nostalgic | | Organic / textural | microbiology core, weaving patterns, fruitage retro, cozy blanket, pacific punk wave | tactile, macro, woven, wet | | Systemic / data | numbers, mazes, code web, heatmap, pixel, 8-bit | gridded, generative, schematic |
For the current project, the primary is Ethereal / divine with a Hyperpop / Y2K-cyber accent — i.e. holy light and crystalline bloom, punctuated by chrome and neon. That pairing is the angelcore × cloud-trance brief.
Distilled directly from the strongest reference reels. This is the concrete grade.
hyperpop bloom, used in bright frames.
shock cuts only.
Rule: one accent per shot. Gold lives in dark frames; iridescence lives in light frames; never both in one shot.
From the reference edits, the techniques that recur and define the style:
feel the BPM.
held for 1–2 beats, then cut. Rhythmic montage of these = the cloud-trance signature.
then resolves into the next shot. The "divine flash" transition.
gold flame, pink hair) punches through on the downbeat.
drop, hard-cut to tempo on the one.
words highlighted in the accent color, synced to the vocal. Use for lyric video, not for the pure visualizer.
b-roll. Out of scope for the music video itself; documented because the corpus uses it heavily.
Do-nots: crossfade transitions in tempo sections; more than one accent color per shot; a shot held past its musical phrase; readable on-screen UI chrome (crop it out); mixed aspect ratios in one timeline.
This skill is the conductor. Each ECC skill is an instrument. Do not skip layers.
0. TASTE (this skill) decide genre + mood + grammar BEFORE anything renders
1. STRUCTURE (video-editing) map the song: timestamps for intro/verse/drop/bridge/outro
2. GENERATE (fal-ai-media) make b-roll per genre prompt-presets; throw away 80%
3. CUT (video-editing/FFmpeg) beat-cut + reframe to 9:16; assemble selects on the grid
4. COMPOSE (remotion-video-creation) overlays, blooms, lyric text, beat-synced sequencing
5. MOTION (motion-* skills) easing curves, light-leak/particle motion, transition timing
6. AUDIO (fal-ai-media) transition risers/impacts to sell the cuts (track itself is in Ableton)
7. POLISH grade to the palette above, final pacing pass, export
8. DISTRIBUTE (content-engine) platform-native versions + caption/cover| Step | ECC skill to load | What it does here | |------|-------------------|-------------------| | Structure & cut | video-editing | FFmpeg cut/concat/reframe, EDL, scene/silence detection | | Generate b-roll | fal-ai-media | image/video models per genre preset | | Compose & overlay | remotion-video-creation | beat-synced <Sequence>s, text, blooms, masks | | Motion timing | motion-foundations, motion-patterns, motion-advanced, motion-ui | easing, springs, light/particle motion | | Server-side video | videodb | smart reframe, indexing if footage is large | | Distribution | content-engine | per-platform cuts, covers, captions | | Voice/lyric VO | video-editing (ElevenLabs section) | only if a spoken layer is needed |
The current track is 138 BPM, B minor. Constants:
seconds_per_beat = 60 / 138 = 0.43478sframes_per_beat = fps × 0.43478 → 24fps: 10.43, 30fps: 13.04, 60fps: 26.091 bar (4 beats) = 1.7391s → 30fps: 52.17 frames8-bar phrase = 13.913s → the loop length from the trackIn Remotion, snap every from={} to a beat:
tsconst FPS = 30; const BPM = 138; const beat = (n: number) => Math.round(n * (60 / BPM) * FPS); // beat(n) → frame // cut on beats 0,4,8,... : <Sequence from={beat(0)} durationInFrames={beat(4)}> ...
The song arrangement (from the project's own notes) is Intro → Verse → Drop → Bridge → Drop → Outro (~2:05). Map taste to each section:
| Section | Genre/mood lean | Grammar | Shot ideas | |---------|-----------------|---------|------------| | Intro | Ethereal/divine, near-black | slow push, no cuts | ember bloom in the void; a single shaft of gold; dust rising | | Verse | Dark + macro hero-on-black | hard cuts every 2 beats | key, eye, gear, water drop, petal — rhythmic macro montage | | Drop | Hyperpop bloom + crystalline | speed-ramp in, cut on the one, fast | candy-pink figure, chrome, iridescent bokeh, winged ascension | | Bridge | Spiritualism, weightless | one long held shot, color-pop | clouds + halo; single red accent punches once | | Drop 2 | as Drop, intensify | add divine-flash blooms on transients | wings open, glitter burst, light leaks maxed | | Outro | Glacial folk, cold calm | slow fade to black | crystalline structure dissolving; ember dies out |
Use with fal-ai-media. Each preset is the genre rendered to the project palette. Append 9:16, vertical, cinematic, film grain, volumetric light, no text, no watermark to all.
deep shadow, one warm light source, weightless dust particles, holy, high contrast"
centered on pure black negative space, razor-sharp detail, single rim light"
refraction, dreamy lens flares, heavenly glow, soft focus, hyperpop angelcore"
Y2K hyperpop, clean gloss, saturated, kawaii-cyber"
gold, volumetric god-rays, ethereal, religious iconography, soft"
and bone white, minimal, calm, fading to black"
Generate 6–10 per preset, keep 2–3. For motion, animate stills with an image-to-video model or generate short clips directly; keep camera moves slow per the Motion rules.
bash# Reframe any landscape/raw clip to 9:16 (center crop) ffmpeg -i in.mp4 -vf "crop=ih*9/16:ih,scale=1080:1920" v.mp4 # Beat-cut a clip to exactly N beats at 138 BPM (e.g. 2 beats = 0.8696s) ffmpeg -i in.mp4 -t 0.8696 -c copy beat2.mp4 # Concatenate beat-selects into the verse montage for f in selects/*.mp4; do echo "file '$f'"; done > concat.txt ffmpeg -f concat -safe 0 -i concat.txt -c copy verse.mp4 # Strip UI chrome / status bar from a screen-recorded reference (crop top+bottom) ffmpeg -i reel.mp4 -vf "crop=iw:ih-300:0:150" clean.mp4
tsximport { AbsoluteFill, Sequence, Video, Img, useCurrentFrame, interpolate } from "remotion"; const FPS = 30, BPM = 138; const beat = (n: number) => Math.round(n * (60 / BPM) * FPS); const Bloom: React.FC = () => { const f = useCurrentFrame(); const o = interpolate(f, [0, 3, 12], [0, 1, 0], { extrapolateRight: "clamp" }); // divine flash on a transient return <AbsoluteFill style={{ background: "radial-gradient(#fff,#ffb24d)", opacity: o, mixBlendMode: "screen" }} />; }; export const AngelcoreMV: React.FC = () => ( <AbsoluteFill style={{ background: "#05060a" }}> {/* Verse: macro hero-on-black, hard cut every 2 beats */} <Sequence from={beat(0)} durationInFrames={beat(2)}><Video src="/selects/key.mp4" /></Sequence> <Sequence from={beat(2)} durationInFrames={beat(2)}><Video src="/selects/eye.mp4" /></Sequence> <Sequence from={beat(4)} durationInFrames={beat(2)}><Video src="/selects/gear.mp4" /></Sequence> {/* Drop: crystalline bloom + flash on the one */} <Sequence from={beat(8)} durationInFrames={beat(16)}><Video src="/selects/crystalline.mp4" /></Sequence> <Sequence from={beat(8)} durationInFrames={beat(1)}><Bloom /></Sequence> </AbsoluteFill> );
Render: npx remotion render src/index.ts AngelcoreMV out.mp4. See remotion-video-creation for project setup, audio track binding, and render flags.
video-editing — the mechanical pipeline (FFmpeg, reframe, EDL, polish) this sits on top ofremotion-video-creation — programmable beat-synced composition and renderingfal-ai-media — generate the b-roll, transition SFX, and risersmotion-foundations, motion-patterns, motion-advanced, motion-ui — easing and motion timingvideodb — server-side smart reframe and indexing for large footagecontent-engine — platform-native distribution, covers, captionsfrontend-design-direction — the same "decide a direction first" discipline, for UI| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 25,516 | 27,169 | +6% | 1 | 1 | 0% | 4,652 | 8,893 | +91% | 0 | 0 | — |
case-02 | fail→pass | 24,985 | 16,429 | -34% | 1 | 1 | 0% | 5,065 | 7,667 | +51% | 0 | 0 | — |
case-03 | fail→pass | 20,025 | 16,448 | -18% | 1 | 1 | 0% | 3,319 | 7,307 | +120% | 0 | 0 | — |
case-04 | fail→pass | 16,272 | 13,919 | -14% | 1 | 1 | 0% | 2,513 | 6,681 | +166% | 0 | 0 | — |
case-05 | fail→pass | 15,116 | 13,374 | -12% | 1 | 1 | 0% | 2,408 | 6,677 | +177% | 0 | 0 | — |
case-06 | fail→pass | 9,643 | 9,676 | +0% | 1 | 1 | 0% | 1,560 | 5,929 | +280% | 0 | 0 | — |
case-07 | pass→pass | 12,997 | 7,735 | -40% | 1 | 1 | 0% | 2,213 | 5,825 | +163% | 0 | 0 | — |
case-08 | pass→pass | 14,175 | 6,622 | -53% | 1 | 1 | 0% | 2,999 | 5,420 | +81% | 0 | 0 | — |
case-09 | fail→pass | 4,903 | 3,326 | -32% | 1 | 1 | 0% | 988 | 4,886 | +395% | 0 | 0 | — |
case-10 | fail→fail | 11,626 | 9,870 | -15% | 1 | 1 | 0% | 2,049 | 5,924 | +189% | 0 | 0 | — |
case-11 | fail→fail | 8,544 | 9,335 | +9% | 1 | 1 | 0% | 1,484 | 5,814 | +292% | 0 | 0 | — |
case-12 | fail→pass | 12,879 | 9,741 | -24% | 1 | 1 | 0% | 2,034 | 5,674 | +179% | 0 | 0 | — |
case-13 | fail→pass | 10,512 | 9,727 | -7% | 1 | 1 | 0% | 1,705 | 5,684 | +233% | 0 | 0 | — |
case-14 | fail→pass | 16,062 | 8,001 | -50% | 1 | 1 | 0% | 3,321 | 5,764 | +74% | 0 | 0 | — |
case-15 | pass→pass | 14,419 | 8,534 | -41% | 1 | 1 | 0% | 2,316 | 5,433 | +135% | 0 | 0 | — |
case-16 | fail→pass | 15,110 | 13,578 | -10% | 1 | 1 | 0% | 2,408 | 6,684 | +178% | 0 | 0 | — |
case-17 | fail→pass | 11,633 | 26,965 | +132% | 1 | 1 | 0% | 2,003 | 4,775 | +138% | 0 | 0 | — |
case-18 | pass→pass | 12,204 | 4,102 | -66% | 1 | 1 | 0% | 2,133 | 4,811 | +126% | 0 | 0 | — |
case-19 | fail→pass | 12,408 | 6,980 | -44% | 1 | 1 | 0% | 2,081 | 5,337 | +156% | 0 | 0 | — |
case-20 | pass→pass | 8,151 | 6,533 | -20% | 1 | 1 | 0% | 1,846 | 5,540 | +200% | 0 | 0 | — |
case-21 | pass→pass | 8,600 | 6,770 | -21% | 1 | 1 | 0% | 1,586 | 5,264 | +232% | 0 | 0 | — |
case-22 | pass→pass | 14,504 | 35,384 | +144% | 1 | 1 | 0% | 2,880 | 7,318 | +154% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +59 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/3/2026 | +50% |
Other measured skills in the registry, with their headline benchmark lift.