creativityGenerate novel ideas calibrated to user taste. Auto-learns preferred styles, risk levels, and creative directions through feedback.
Install via ClawdBot CLI:
clawdbot install ivangdavila/creativityCreativity isn't randomโit'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).
1. DIVERGE โ Generate many options, suspend judgment
2. FILTER โ Apply preferences from preferences.md
3. PRESENT โ Show range: safe โ stretch โ wild
4. LEARN โ Record reaction in preferences.md
5. REFINE โ Iterate based on feedbackAlways present options across a range:
๐จ Creative options for [goal]:
Safe (familiar territory):
โ [Option aligned with known preferences]
Stretch (new but grounded):
โ [Option that pushes slightly beyond comfort]
Wild (high risk, high reward):
โ [Option that breaks conventions]
Which direction feels right?| Dimension | Spectrum |
|-----------|----------|
| Tone | Serious โโ Playful |
| Density | Minimal โโ Rich |
| Novelty | Classic โโ Avant-garde |
| Structure | Rigid โโ Fluid |
| Abstraction | Concrete โโ Conceptual |
| Energy | Calm โโ Intense |
| Polish | Raw โโ Refined |
| 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 |
Periodically confirm your taste model:
๐จ Quick calibration
I've noticed you tend toward [observed pattern].
Should I keep leaning that direction, mix it up, or shift?| 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) |
Generated Mar 1, 2026
Generate novel campaign concepts for a brand, presenting safe, stretch, and wild options based on learned preferences for tone and novelty. Useful for brainstorming ad copy, social media themes, or product launches that align with user taste while exploring creative boundaries.
Create innovative product features or design variations by diverging across dimensions like structure and polish, then filtering through user preferences. Helps teams ideate on new models, packaging, or user interfaces with calibrated risk levels.
Produce content ideas for blogs, videos, or podcasts, ranging from safe topics to wild concepts based on learned energy and density preferences. Assists creators in maintaining freshness while staying aligned with audience interests.
Design engaging lesson plans or learning activities by exploring creative directions in abstraction and tone, then refining based on feedback. Supports educators in developing novel teaching methods that resonate with student preferences.
Offer monthly access to the AI for generating ideas across marketing, design, or content, with pricing tiers based on usage volume and customization depth. Revenue comes from recurring subscriptions, appealing to freelancers and small teams seeking consistent creative support.
License the skill to large organizations for internal use in R&D, product development, or strategy sessions, with custom integrations and premium support. Revenue is generated through annual contracts, targeting industries like tech and manufacturing that require structured creativity.
Provide an API allowing developers to integrate the creativity skill into their own applications, charging per API call or batch of ideas. Revenue streams from usage-based billing, ideal for startups and platforms needing on-demand creative generation without full ownership.
๐ฌ Integration Tip
Start by integrating the skill into brainstorming tools or feedback loops, ensuring preferences.md is updated after each session to refine outputs over time.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Humanize AI-generated text to bypass detection. This humanizer rewrites ChatGPT, Claude, and GPT content to sound natural and pass AI detectors like GPTZero,...
Collaborative thinking partner for exploring complex problems through questioning
Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 24 pattern detectors, 500+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
ๆ นๆฎ็จๆท็ๅ่ฝ้ๆฑ๏ผๅฎๆไธ VeADK ็ธๅ ณ็ๅ่ฝใ
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.