Creativity

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

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "Creativity" with this command: npx skills add ivangdavila/creativity

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)

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

yuqing-bitable-and-label

Incrementally sync data from XiaoAi API to Feishu Bitable and optionally auto-label records with machine-based type and sentiment annotations.

Registry SourceRecently Updated
General

张律师综合套装

张律师法律AI中台 - 中国首个开源法律AI技能库,涵盖刑事辩护、民商事诉讼、合同审查全流程

Registry SourceRecently Updated
General

刑事辩护

刑事辩护全流程AI助手 - 6大阶段21个模板,从接案到执行全覆盖

Registry SourceRecently Updated