Coding

Creativity

Generate novel ideas calibrated to user taste. Auto-learns preferred styles, risk levels, and creative directions through feedback.

What it does

Creativity isn't random—it's controlled divergence. Learn the user's creative taste, then explore within and beyond those boundaries intentionally.

The skill document

Core Principle

Creativity isn't random—it's controlled divergence. Learn the user's creative taste, then explore within and beyond those boundaries intentionally.

Check techniques.md for generation methods. Check preferences.md for learned taste (update after each creative task).


The Creative Process

1. DIVERGE  — Generate many options, suspend judgment
2. FILTER   — Apply preferences from preferences.md
3. PRESENT  — Show range: safe → stretch → wild
4. LEARN    — Record reaction in preferences.md
5. REFINE   — Iterate based on feedback

Output Spectrum

Always present options across a range:

🎨 Creative options for [goal]:

Safe (familiar territory):
→ [Option aligned with known preferences]

Stretch (new but grounded):  
→ [Option that pushes slightly beyond comfort]

Wild (high risk, high reward):
→ [Option that breaks conventions]

Which direction feels right?

Taste Dimensions

DimensionSpectrum
ToneSerious ←→ Playful
DensityMinimal ←→ Rich
NoveltyClassic ←→ Avant-garde
StructureRigid ←→ Fluid
AbstractionConcrete ←→ Conceptual
EnergyCalm ←→ Intense
PolishRaw ←→ Refined

Learning Signals

SignalAction
"Love it" / "Perfect"Record in preferences.md: this direction works
"Interesting but..."Note what worked, what didn't
Silence / moves onAssume miss, try different vector
"Too X" / "Not enough Y"Adjust dimension in preferences.md
Chooses from optionsRecord which spectrum end picked

Calibration

Periodically confirm your taste model:

🎨 Quick calibration

I've noticed you tend toward [observed pattern].
Should I keep leaning that direction, mix it up, or shift?

Anti-Patterns

Don'tDo instead
Single optionAlways provide spectrum
Only safe optionsInclude stretch/wild
Ignore negative signalsUpdate preferences.md
Same technique every timeRotate (see techniques.md)

Related skills

Generate short stories, novel drafts, screenplays, and story worlds via the CellCog SDK.

263 installs19 stars

Generate article covers with six customizable dimensions: type, palette, rendering, text, mood, and font.

261 installs7 stars

Conversational partner for refining complex ideas through iterative dialogue.

129 installs7 stars

Crafts Suno style prompts, structured lyrics, and full generation pipelines via API, browser, or manual paste.

by Iván59 installs

Generate and edit images from text or references using routed AI models, with character consistency and product photography support.

536 installs10 stars

Turn content into reading-friendly slide deck images with style presets and optional PPTX/PDF merge.

110 installs2 stars

More from Iván

Browse all skills

Run Git operations — commits, branches, merges, rebases, conflict resolution, and recovery — with safety rules enforced.

by Iván527 installs31 stars

Create and critique visual artifacts with quantified rules for hierarchy, spacing, type scale, color, and layout.

by Iván137 installs5 stars

Debug CSS mechanics and write component stylesheets grounded in named mechanisms, not trial-and-error.

by Iván97 installs5 stars

Plans and runs self-directed learning as a system: exit test, spaced review, deliberate practice, and transfer proof.

by Iván93 installs3 stars

Get Azure architecture, debugging, security, and cost reviews grounded in a live inventory of your subscription.

by Iván86 installs2 stars

Diagnoses Java and JVM issues from exception messages to container OOM-kills, and writes Java code matching the configured JDK.

by Iván130 installs9 stars