Creativity Skill
Workflow
1. Ask → "What problem/challenge?"
2. Context → Understand current state BEFORE suggesting
3. Diagnose → Match situation to technique(s)
4. Generate → Walk through technique step-by-step
5. Evaluate → Score and filter ideas
6. Develop → Shape top ideas into actionable concepts
7. Output → Structured ideas + next actions (Thai if user uses Thai)
Context questions (step 2):
- "What do you currently do?"
- "What have you tried?"
- "What's working? What's not?"
Anti-pattern: Jumping to solutions without understanding context = generic noise
Situation -> Technique Matrix
| Situation |
Techniques |
Combination Recipe |
| Stuck / No ideas |
Random Word, Forced Connections, Oblique Strategies |
Random Word -> Forced Connections -> Dot Vote |
| Need breakthrough |
First Principles, Challenging Assumptions, Combinatorial Engine |
HMW -> Worst Idea -> SCAMPER -> Brainwriting |
| Improve existing |
SCAMPER, Reverse Brainstorming, TRIZ-AI |
SCAMPER -> Reverse Brainstorm -> Impact/Effort |
| Explore systematically |
Morphological Box, Six Thinking Hats, Constraint Injection |
Morphological Box -> Constraint Injection -> Clustering |
| Reframe problem |
How Might We (HMW), Jobs to be Done |
HMW -> JTBD -> First Principles |
| Team ideation |
6-3-5 Brainwriting, Multi-Persona Parallel |
Mind Map -> Brainwriting -> Affinity -> Multi-Vote |
| Too many ideas |
Impact/Effort Matrix, Idea Clustering, NAF Scoring |
Clustering -> NAF Quick Score -> Impact/Effort |
| AI ideas too similar |
Divergence Guard, Constraint Injection, Incubation Cycling |
Divergence Guard -> Domain Shift -> Incubation |
| Technical/engineering |
TRIZ-AI, First Principles |
TRIZ -> First Principles -> Assumption Mapping |
| Cross-domain innovation |
Combinatorial Engine, Analogical Thinking |
Combinatorial Engine -> Analogical -> Constraint |
| Content ideas (blog/video/course) |
Content Pillars, Audience Pain Points, Gap Analysis |
Pillars -> Pain Points -> SCAMPER -> Validate |
| Business/product ideas |
JTBD, Opportunity Canvas, Lean Validation |
JTBD -> HMW -> Morphological -> ICE Score |
Technique Quick Reference
Divergent (Generate)
| Technique |
One-liner |
| SCAMPER |
7 lenses: Substitute, Combine, Adapt, Modify, Put to other use, Eliminate, Reverse |
| Random Word |
Random noun -> list attributes -> force connections to problem |
| Reverse Brainstorm |
"How to make it worse?" -> Invert each idea |
| First Principles |
Strip to fundamentals -> Rebuild from scratch |
| Six Hats |
6 perspectives: Facts, Feelings, Risks, Benefits, Ideas, Process |
| HMW |
Reframe as "How Might We [verb] for [user] so that [outcome]?" |
| Morphological Box |
Parameters x Variations matrix -> Combine systematically |
| Analogies |
"How does [other domain] solve this?" |
| Assumptions |
List assumptions -> Challenge/invert each |
| Forced Connections |
Combine 2 unrelated concepts |
| Jobs to be Done |
"When [situation], I want [motivation], so I can [outcome]" |
| Oblique Strategies |
Random creative prompts to break deadlocks |
AI-Optimized (Generate + Diversify)
| Technique |
One-liner |
| Incubation Cycling |
Generate -> Pause -> Fresh restart (no prior context) -> Compare |
| Combinatorial Engine |
Abstract -> Retrieve 3 domains -> Generalize -> Combine -> Instantiate |
| Multi-Persona Parallel |
Run 4+ personas SIMULTANEOUSLY (not sequentially) |
| Constraint Injection |
Add random constraint -> Force novel solutions |
| Divergence Guard |
Force opposite -> Domain shift -> Absurdity injection |
| TRIZ-AI |
Apply inventive principles (segmentation, nesting, dynamization, etc.) |
| Tree of Thoughts |
Explore multiple reasoning branches simultaneously (74% vs CoT 49%) |
Convergent (Evaluate + Refine)
| Technique |
One-liner |
| NAF Quick Score |
Rate Novelty + Attractiveness + Feasibility (1-10 each) |
| Impact/Effort Matrix |
2x2: Quick Wins, Big Bets, Fill-ins, Avoid |
| ICE Scoring |
Impact x Confidence x Ease (1-10 each) |
| Idea Clustering |
Group similar -> Name clusters -> Pick best from each |
| Dot Voting |
Each person gets 3-5 votes -> Surface favorites |
| Assumption Mapping |
Map assumptions on Importance x Certainty -> Test riskiest first |
Idea Evaluation
After generating ideas, ALWAYS offer evaluation. Default to NAF Quick Score.
NAF Quick Score (Default)
| Criterion |
Question |
Scale |
| Novelty |
How new/surprising is this? |
1-10 |
| Attractiveness |
How well does it solve the problem? |
1-10 |
| Feasibility |
How realistic to implement? |
1-10 |
Interpretation:
- Total 24-30: Strong candidate -> develop further
- Total 18-23: Promising -> refine or combine
- Total < 18: Weak -> park or discard
- Feasibility 8+: Worth trying (remaining 20% is implementation)
- High N+A but low F: Reframe feasibility barriers as new problems to solve
When to Use Which Evaluation
| Situation |
Method |
| Quick screening (5+ ideas) |
NAF or Dot Voting |
| Growth experiments |
ICE Scoring |
| Data-driven product decisions |
RICE Scoring |
| Complex multi-criteria |
Weighted Scoring Matrix |
| Visual team alignment |
Impact/Effort 2x2 |
Rules:
- NEVER evaluate during divergent phase -- generate first, judge later
- Take a break between generating and evaluating (different mindset)
- Different idea types need different criteria (incremental vs disruptive)
Details: evaluation.md
Content Creator Mode
When ideating for blog posts, videos, courses, or social media:
Step 1: Define Content Pillars (3-5 themes)
Pillar = Core theme that reflects expertise + audience needs
Example: Excel -> [Formulas, Data Viz, Automation, Tips & Tricks, Career]
Step 2: Audience-First Ideation
| Source |
Questions |
| Pain Points |
What frustrates them most? |
| Questions |
What do they repeatedly ask? |
| Gaps |
What's poorly explained by competitors? |
| Wishes |
What do they wish existed? |
| Mistakes |
What common errors do they make? |
Step 3: Generate Ideas (use any technique from matrix)
Apply creativity techniques TO the content pillars:
- SCAMPER on existing popular content
- Reverse brainstorm: "How to make the worst tutorial?"
- Analogies: "How would Netflix teach Excel?"
Step 4: Validate Before Creating
[ ] Search demand? (keyword research)
[ ] Real audience pain point? (comments, surveys)
[ ] Can I add unique value? (gap analysis)
[ ] Fits my pillars? (strategy alignment)
[ ] Would I click this? (title/thumbnail test)
[ ] Can be repurposed? (1 piece -> 5+ formats)
Repurposing Chain
Blog post -> YouTube video -> Shorts/Reels -> Social posts -> Email -> Course module
Details: content-ideation.md
Idea Development Pipeline
Shape raw ideas into actionable concepts:
[Generate] -> [Cluster] -> [Evaluate] -> [Develop] -> [Validate] -> [Execute]
Quick Concept Card (for top ideas)
IDEA: [Name]
TAGLINE: [One compelling sentence]
PROBLEM: [What pain it solves]
SOLUTION: [How it works - 2-3 sentences]
TARGET USER: [Who benefits]
KEY INSIGHT: [The "aha" behind this]
EFFORT: [S / M / L]
BIGGEST RISK: [What could go wrong]
QUICKEST TEST: [How to validate cheaply]
NEXT STEP: [One concrete action]
Assumption Mapping (for important ideas)
- List assumptions: "What must be true for this to work?"
- Categorize: Desirability / Feasibility / Viability
- Map on 2x2: Importance (high/low) x Certainty (high/low)
- Test high-importance + low-certainty FIRST
Details: idea-pipeline.md
Output Formats
Use these when presenting ideas to the user:
Quick List (5+ ideas)
1. **[Idea Name]** -- [One-line description]
2. **[Idea Name]** -- [One-line description]
...
Scored List (after evaluation)
| # | Idea | N | A | F | Total |
|---|------|---|---|---|-------|
| 1 | ... | 8 | 9 | 7 | 24 |
Concept Cards (top 3 ideas)
Use the Quick Concept Card format above for each top idea.
Comparison Matrix (deciding between options)
| Criteria | Idea A | Idea B | Idea C |
|-------------|--------|--------|--------|
| Novelty | 4/5 | 3/5 | 5/5 |
| Feasibility | 3/5 | 5/5 | 2/5 |
| Impact | 5/5 | 3/5 | 4/5 |
AI Creativity Guidelines
Key Research Insights (2025-2026)
| Finding |
Implication |
| Ask AI HOW to think, not WHAT to think |
Process prompts > product prompts |
| Human-first ideation preserves diversity |
User brainstorms first, THEN AI expands |
| LLMs match average creativity (52nd percentile) |
AI is a partner, not a replacement |
| Homogenization effect (g ~ -0.86) |
Use Divergence Guard actively |
| "Creative Scar" -- creativity drops after AI withdrawal |
Don't outsource all creative thinking |
| Tree of Thoughts: 74% vs CoT 49% |
Use ToT for complex creative tasks |
| Multi-LLM collaboration enhances originality |
Stack techniques, vary approaches |
| Only 0.28% of LLM ideas reach top 10% human creativity |
Push past first outputs aggressively |
AI Role Rules
- Best as: Exploration partner, constraint enforcer, analogy finder, elaborator
- Avoid: Sole ideation source, final decision maker
- Timing: After initial human ideation, not before
- Override rate: Maintain 15-25% human override for optimal outcomes
Anti-Patterns
| Don't |
Do Instead |
| "Give me ideas for X" |
"Give me 10 ideas for X that would surprise an expert" |
| Accept first outputs |
Push past 2-3 rounds; first ideas are "greatest hits" |
| Use AI before thinking |
Brainstorm independently first, then expand with AI |
| "Be creative" |
Use specific technique (SCAMPER, constraints, personas) |
Details: methodology.md | prompt-templates.md
References
- Step-by-step guides: techniques.md
- AI methodology & research: methodology.md
- Random word bank: random-words.md
- Evaluation frameworks: evaluation.md
- Content creator ideation: content-ideation.md
- Idea development pipeline: idea-pipeline.md
- AI prompt templates: prompt-templates.md
Related Skills
/triz — Systematic innovation methodology (complements brainstorming)
/deep-research — Research inspiration and cross-industry solutions
/boost-intel — Critical evaluation of generated ideas
/design-business-model — Apply creative ideas to business models
/problem-solving — Structure the problem before ideating
1---2name: generate-creative-ideas3description: Creative problem-solving and ideation using SCAMPER, First Principles, Random Word, and AI-optimized techniques. Use when generating ideas, breaking creative blocks, brainstorming alternatives, or innovating.4---56# Creativity Skill78## Workflow910```111. Ask → "What problem/challenge?"122. Context → Understand current state BEFORE suggesting133. Diagnose → Match situation to technique(s)144. Generate → Walk through technique step-by-step155. Evaluate → Score and filter ideas166. Develop → Shape top ideas into actionable concepts177. Output → Structured ideas + next actions (Thai if user uses Thai)18```1920**Context questions (step 2):**21- "What do you currently do?"22- "What have you tried?"23- "What's working? What's not?"2425> Anti-pattern: Jumping to solutions without understanding context = generic noise2627---2829## Situation -> Technique Matrix3031| Situation | Techniques | Combination Recipe |32|-----------|------------|-------------------|33| Stuck / No ideas | Random Word, Forced Connections, Oblique Strategies | Random Word -> Forced Connections -> Dot Vote |34| Need breakthrough | First Principles, Challenging Assumptions, Combinatorial Engine | HMW -> Worst Idea -> SCAMPER -> Brainwriting |35| Improve existing | SCAMPER, Reverse Brainstorming, TRIZ-AI | SCAMPER -> Reverse Brainstorm -> Impact/Effort |36| Explore systematically | Morphological Box, Six Thinking Hats, Constraint Injection | Morphological Box -> Constraint Injection -> Clustering |37| Reframe problem | How Might We (HMW), Jobs to be Done | HMW -> JTBD -> First Principles |38| Team ideation | 6-3-5 Brainwriting, Multi-Persona Parallel | Mind Map -> Brainwriting -> Affinity -> Multi-Vote |39| Too many ideas | Impact/Effort Matrix, Idea Clustering, NAF Scoring | Clustering -> NAF Quick Score -> Impact/Effort |40| AI ideas too similar | Divergence Guard, Constraint Injection, Incubation Cycling | Divergence Guard -> Domain Shift -> Incubation |41| Technical/engineering | TRIZ-AI, First Principles | TRIZ -> First Principles -> Assumption Mapping |42| Cross-domain innovation | Combinatorial Engine, Analogical Thinking | Combinatorial Engine -> Analogical -> Constraint |43| **Content ideas** (blog/video/course) | Content Pillars, Audience Pain Points, Gap Analysis | Pillars -> Pain Points -> SCAMPER -> Validate |44| **Business/product ideas** | JTBD, Opportunity Canvas, Lean Validation | JTBD -> HMW -> Morphological -> ICE Score |4546---4748## Technique Quick Reference4950### Divergent (Generate)5152| Technique | One-liner |53|-----------|-----------|54| **SCAMPER** | 7 lenses: Substitute, Combine, Adapt, Modify, Put to other use, Eliminate, Reverse |55| **Random Word** | Random noun -> list attributes -> force connections to problem |56| **Reverse Brainstorm** | "How to make it worse?" -> Invert each idea |57| **First Principles** | Strip to fundamentals -> Rebuild from scratch |58| **Six Hats** | 6 perspectives: Facts, Feelings, Risks, Benefits, Ideas, Process |59| **HMW** | Reframe as "How Might We [verb] for [user] so that [outcome]?" |60| **Morphological Box** | Parameters x Variations matrix -> Combine systematically |61| **Analogies** | "How does [other domain] solve this?" |62| **Assumptions** | List assumptions -> Challenge/invert each |63| **Forced Connections** | Combine 2 unrelated concepts |64| **Jobs to be Done** | "When [situation], I want [motivation], so I can [outcome]" |65| **Oblique Strategies** | Random creative prompts to break deadlocks |6667### AI-Optimized (Generate + Diversify)6869| Technique | One-liner |70|-----------|-----------|71| **Incubation Cycling** | Generate -> Pause -> Fresh restart (no prior context) -> Compare |72| **Combinatorial Engine** | Abstract -> Retrieve 3 domains -> Generalize -> Combine -> Instantiate |73| **Multi-Persona Parallel** | Run 4+ personas SIMULTANEOUSLY (not sequentially) |74| **Constraint Injection** | Add random constraint -> Force novel solutions |75| **Divergence Guard** | Force opposite -> Domain shift -> Absurdity injection |76| **TRIZ-AI** | Apply inventive principles (segmentation, nesting, dynamization, etc.) |77| **Tree of Thoughts** | Explore multiple reasoning branches simultaneously (74% vs CoT 49%) |7879### Convergent (Evaluate + Refine)8081| Technique | One-liner |82|-----------|-----------|83| **NAF Quick Score** | Rate Novelty + Attractiveness + Feasibility (1-10 each) |84| **Impact/Effort Matrix** | 2x2: Quick Wins, Big Bets, Fill-ins, Avoid |85| **ICE Scoring** | Impact x Confidence x Ease (1-10 each) |86| **Idea Clustering** | Group similar -> Name clusters -> Pick best from each |87| **Dot Voting** | Each person gets 3-5 votes -> Surface favorites |88| **Assumption Mapping** | Map assumptions on Importance x Certainty -> Test riskiest first |8990---9192## Idea Evaluation9394After generating ideas, ALWAYS offer evaluation. Default to **NAF Quick Score**.9596### NAF Quick Score (Default)9798| Criterion | Question | Scale |99|-----------|----------|-------|100| **Novelty** | How new/surprising is this? | 1-10 |101| **Attractiveness** | How well does it solve the problem? | 1-10 |102| **Feasibility** | How realistic to implement? | 1-10 |103104**Interpretation:**105- Total 24-30: Strong candidate -> develop further106- Total 18-23: Promising -> refine or combine107- Total < 18: Weak -> park or discard108- Feasibility 8+: Worth trying (remaining 20% is implementation)109- High N+A but low F: Reframe feasibility barriers as new problems to solve110111### When to Use Which Evaluation112113| Situation | Method |114|-----------|--------|115| Quick screening (5+ ideas) | NAF or Dot Voting |116| Growth experiments | ICE Scoring |117| Data-driven product decisions | RICE Scoring |118| Complex multi-criteria | Weighted Scoring Matrix |119| Visual team alignment | Impact/Effort 2x2 |120121**Rules:**1221. NEVER evaluate during divergent phase -- generate first, judge later1232. Take a break between generating and evaluating (different mindset)1243. Different idea types need different criteria (incremental vs disruptive)125126Details: [evaluation.md](references/evaluation.md)127128---129130## Content Creator Mode131132When ideating for blog posts, videos, courses, or social media:133134### Step 1: Define Content Pillars (3-5 themes)135136```137Pillar = Core theme that reflects expertise + audience needs138Example: Excel -> [Formulas, Data Viz, Automation, Tips & Tricks, Career]139```140141### Step 2: Audience-First Ideation142143| Source | Questions |144|--------|-----------|145| Pain Points | What frustrates them most? |146| Questions | What do they repeatedly ask? |147| Gaps | What's poorly explained by competitors? |148| Wishes | What do they wish existed? |149| Mistakes | What common errors do they make? |150151### Step 3: Generate Ideas (use any technique from matrix)152153Apply creativity techniques TO the content pillars:154- SCAMPER on existing popular content155- Reverse brainstorm: "How to make the worst tutorial?"156- Analogies: "How would Netflix teach Excel?"157158### Step 4: Validate Before Creating159160```161[ ] Search demand? (keyword research)162[ ] Real audience pain point? (comments, surveys)163[ ] Can I add unique value? (gap analysis)164[ ] Fits my pillars? (strategy alignment)165[ ] Would I click this? (title/thumbnail test)166[ ] Can be repurposed? (1 piece -> 5+ formats)167```168169### Repurposing Chain170171```172Blog post -> YouTube video -> Shorts/Reels -> Social posts -> Email -> Course module173```174175Details: [content-ideation.md](references/content-ideation.md)176177---178179## Idea Development Pipeline180181Shape raw ideas into actionable concepts:182183```184[Generate] -> [Cluster] -> [Evaluate] -> [Develop] -> [Validate] -> [Execute]185```186187### Quick Concept Card (for top ideas)188189```190IDEA: [Name]191TAGLINE: [One compelling sentence]192PROBLEM: [What pain it solves]193SOLUTION: [How it works - 2-3 sentences]194TARGET USER: [Who benefits]195KEY INSIGHT: [The "aha" behind this]196EFFORT: [S / M / L]197BIGGEST RISK: [What could go wrong]198QUICKEST TEST: [How to validate cheaply]199NEXT STEP: [One concrete action]200```201202### Assumption Mapping (for important ideas)2032041. List assumptions: "What must be true for this to work?"2052. Categorize: Desirability / Feasibility / Viability2063. Map on 2x2: Importance (high/low) x Certainty (high/low)2074. Test high-importance + low-certainty FIRST208209Details: [idea-pipeline.md](references/idea-pipeline.md)210211---212213## Output Formats214215Use these when presenting ideas to the user:216217### Quick List (5+ ideas)218219```2201. **[Idea Name]** -- [One-line description]2212. **[Idea Name]** -- [One-line description]222...223```224225### Scored List (after evaluation)226227```228| # | Idea | N | A | F | Total |229|---|------|---|---|---|-------|230| 1 | ... | 8 | 9 | 7 | 24 |231```232233### Concept Cards (top 3 ideas)234235Use the Quick Concept Card format above for each top idea.236237### Comparison Matrix (deciding between options)238239```240| Criteria | Idea A | Idea B | Idea C |241|-------------|--------|--------|--------|242| Novelty | 4/5 | 3/5 | 5/5 |243| Feasibility | 3/5 | 5/5 | 2/5 |244| Impact | 5/5 | 3/5 | 4/5 |245```246247---248249## AI Creativity Guidelines250251### Key Research Insights (2025-2026)252253| Finding | Implication |254|---------|-------------|255| Ask AI HOW to think, not WHAT to think | Process prompts > product prompts |256| Human-first ideation preserves diversity | User brainstorms first, THEN AI expands |257| LLMs match average creativity (52nd percentile) | AI is a partner, not a replacement |258| Homogenization effect (g ~ -0.86) | Use Divergence Guard actively |259| "Creative Scar" -- creativity drops after AI withdrawal | Don't outsource all creative thinking |260| Tree of Thoughts: 74% vs CoT 49% | Use ToT for complex creative tasks |261| Multi-LLM collaboration enhances originality | Stack techniques, vary approaches |262| Only 0.28% of LLM ideas reach top 10% human creativity | Push past first outputs aggressively |263264### AI Role Rules265266- **Best as:** Exploration partner, constraint enforcer, analogy finder, elaborator267- **Avoid:** Sole ideation source, final decision maker268- **Timing:** After initial human ideation, not before269- **Override rate:** Maintain 15-25% human override for optimal outcomes270271### Anti-Patterns272273| Don't | Do Instead |274|-------|-----------|275| "Give me ideas for X" | "Give me 10 ideas for X that would surprise an expert" |276| Accept first outputs | Push past 2-3 rounds; first ideas are "greatest hits" |277| Use AI before thinking | Brainstorm independently first, then expand with AI |278| "Be creative" | Use specific technique (SCAMPER, constraints, personas) |279280Details: [methodology.md](references/methodology.md) | [prompt-templates.md](references/prompt-templates.md)281282---283284## References285286- **Step-by-step guides**: [techniques.md](references/techniques.md)287- **AI methodology & research**: [methodology.md](references/methodology.md)288- **Random word bank**: [random-words.md](references/random-words.md)289- **Evaluation frameworks**: [evaluation.md](references/evaluation.md)290- **Content creator ideation**: [content-ideation.md](references/content-ideation.md)291- **Idea development pipeline**: [idea-pipeline.md](references/idea-pipeline.md)292- **AI prompt templates**: [prompt-templates.md](references/prompt-templates.md)293294---295296## Related Skills297298- `/triz` — Systematic innovation methodology (complements brainstorming)299- `/deep-research` — Research inspiration and cross-industry solutions300- `/boost-intel` — Critical evaluation of generated ideas301- `/design-business-model` — Apply creative ideas to business models302- `/problem-solving` — Structure the problem before ideating