Back to skills
SKILL.md
Creativity
ASecurityGenerate novel ideas calibrated to user taste. Auto-learns preferred styles, risk levels, and creative directions through feedback.
- 17 stars
- 0 votes
- 0 copies
- 13 views
- Added September 6, 2026
Security analysis
100/100Pro scans all 4 files and shows the line behind each finding
npx -y skills add clawic/skills --skill creativity --agent claude-codeAre you the author of Creativity?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/clawic-creativity)---
name: Creativity
slug: creativity
version: 1.0.0
description: Generate novel ideas calibrated to user taste. Auto-learns preferred styles, risk levels, and creative directions through feedback.
homepage: https://clawic.com/skills/creativity
metadata:
clawdbot:
emoji: π¨
displayName: Creativity
---
## Core Principle
Creativity isn't randomβit'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 β Generate many options, suspend judgment
2. FILTER β Apply preferences from preferences.md
3. PRESENT β Show range: safe β stretch β wild
4. LEARN β Record reaction in preferences.md
5. REFINE β Iterate based on feedback
```
---
## Output Spectrum
Always present options across a range:
```
π¨ Creative options for [goal]:
Safe (familiar territory):
β [Option aligned with known preferences]
Stretch (new but grounded):
β [Option that pushes slightly beyond comfort]
Wild (high risk, high reward):
β [Option that breaks conventions]
Which direction feels right?
```
---
## Taste Dimensions
| Dimension | Spectrum |
|-----------|----------|
| Tone | Serious ββ Playful |
| Density | Minimal ββ Rich |
| Novelty | Classic ββ Avant-garde |
| Structure | Rigid ββ Fluid |
| Abstraction | Concrete ββ Conceptual |
| Energy | Calm ββ Intense |
| Polish | Raw ββ Refined |
---
## Learning Signals
| Signal | Action |
|--------|--------|
| "Love it" / "Perfect" | Record in preferences.md: this direction works |
| "Interesting but..." | Note what worked, what didn't |
| Silence / moves on | Assume miss, try different vector |
| "Too X" / "Not enough Y" | Adjust dimension in preferences.md |
| Chooses from options | Record which spectrum end picked |
---
## Calibration
Periodically confirm your taste model:
```
π¨ Quick calibration
I've noticed you tend toward [observed pattern].
Should I keep leaning that direction, mix it up, or shift?
```
---
## Anti-Patterns
| Don't | Do instead |
|-------|------------|
| Single option | Always provide spectrum |
| Only safe options | Include stretch/wild |
| Ignore negative signals | Update preferences.md |
| Same technique every time | Rotate (see techniques.md) |
Files in this skill
- SKILL.md
- _meta.json
- preferences.md
- techniques.md
Attribution
Comments
Loading commentsβ¦