Bisociative Creativity
Core principle: Creativity = collision between two unrelated frames of reference. Koestler's bisociation — two "matrices of thought" intersect, producing something that belongs to neither but couldn't exist without both.
LLMs default to mode-seeking (most likely continuation). Creativity is off the mode. This skill forces the model into productive collision space.
When to Use
| Skill |
Use case |
| lateral-thinking |
Escape a dominant pattern when stuck |
| analogical-thinking |
Transfer structural solutions across domains |
| bisociative-creativity |
Deliverable is an idea (not a diagnosis or decision) |
Phase 1 — Frame Selection (Divergent)
Quality of output depends on distance of the colliding frames. Close frames = incremental ideas. Distant frames = surprising ones.
Step 1: Name the seed domain. State the topic/brief.
Step 2: Generate 5–7 distant frames with no obvious connection to the seed:
| Generator |
Method |
| Sensory world |
Physical material, texture, natural process (mycelium, tidal erosion, fermentation) |
| Historical era |
Non-obvious period (Venetian glassmaking, Rosetta Stone decipherment) |
| Art form |
Discipline far from seed (Butoh dance, mosaic restoration, jazz comping) |
| Everyday ritual |
Mundane activity (packing a suitcase, mise en place, tuning a guitar) |
| Unrelated industry |
Zero surface overlap (perfumery, air traffic control, wine terroir) |
| Emotional state |
Specific feeling (the moment before a sneeze, homesickness, flow) |
| Constraint injection |
Arbitrary rule from another domain ("what if context expired like fresh produce?") |
Frame rules:
- If the connection is immediately visible, the frame is too close
- ≥2 frames should feel absurd or uncomfortable
- Reject dead metaphors (orchestra conductor for leadership; journey for change)
Phase 2 — Collision
For each frame, force collision via structural interrogation. Ask in order:
- Core mechanic — How does this frame work, physically or conceptually?
- Tensions/trade-offs — What does it balance? What can go wrong?
- Bisociation point — Where does its structure intersect the seed's structure?
- Idea produced — Concrete concept, not abstract connection.
Critical: no judgment in Phase 2. Premature convergence is the #1 killer.
Example — seed: "name for visual knowledge mapping tool", frame: fermentation:
- Mechanic: transformation over time; raw inputs become new through controlled conditions
- Tensions: speed vs. depth; control vs. wild cultures
- Bisociation: knowledge isn't organized — it develops
- Ideas: "Kultur", "Starter", tagline "Let your ideas develop"
Phase 3 — Harvest (Convergent)
Triage every idea:
| Bucket |
Criteria |
Action |
| Live spark |
Surprising AND structurally sound |
Develop immediately |
| Kernel |
Idea impractical, but useful concept buried inside |
Extract, restate, find better vehicle |
| Dead end |
Forced, generic, or only works if you squint |
Discard |
For each live spark: state in one sentence; explain the collision; give 2–3 variations; pick strongest expression.
For each kernel: extract the usable concept; combine with another kernel/spark; collide with a different Phase 1 frame.
Output Format
Creative Brief
Restate seed + kind of ideas needed.
Frame Selection
List 5–7 frames + one-line distance justification each.
Collisions
For each: Frame × Seed | Core mechanic | Bisociation point | Ideas produced.
Live Sparks
3–5 strongest. Each: idea (one sentence), why it works, 2–3 variations, strongest expression.
Kernels Worth Saving
Extracted concepts for later/combination.
Oblique Strategy Injections
Use when the collision phase feels mechanical:
- "What if the opposite of this idea were the idea?"
- "What would make someone laugh about this?"
- "What would this be if it were a sound? A smell? A temperature?"
- "What's the version that would get you fired?"
- "What's the version a 6-year-old would invent?"
- "Honor thy error as a hidden intention."
- "What would this look like in 1926? In 2126?"
- "Remove the most important element. What's left?"
Anti-Patterns
| Anti-pattern |
Symptom |
Fix |
| Mode-seeking |
Ideas sound like generic "creative AI" |
Increase frame distance; add constraint injection |
| Dead metaphor |
Tired comparisons (journey, tapestry, compass) |
Reject any frame already a cliché for the seed |
| Premature convergence |
Filtering during Phase 2 |
No judgment until Phase 3 |
| Surface bisociation |
Wordplay, not structural |
"Does this work if I remove the pun?" |
| Quantity collapse |
Stopping at 3 ideas |
Set a quota (min 15 raw ideas) |
| Comfort zone frames |
All frames adjacent to seed |
Mandate ≥2 from sensory/emotional/everyday |
Recombination Protocol
After initial harvest, cross-pollinate:
- Take top 3 live sparks
- Ask: "What if Spark A and Spark B were the same idea?"
- Force the combination — don't ask if it makes sense yet
- Best idea often comes from second-order collision (two bisociations bisociating)
Calibration by Task
| Task |
Frame distance |
Collision depth |
Output style |
| Naming |
Maximum — absurd frames welcome |
Sound, rhythm, double meaning |
Short, punchy, memorable |
| Concepts |
High — cross-industry |
Mechanics + UX |
Functional + emotional hook |
| Writing angles |
Medium-high — surprising but graspable |
Narrative tension + audience surprise |
Thesis + opening line |
| Visual concepts |
Maximum — synesthetic frames |
Sensory overlap + spatial metaphor |
Image description + mood |
| Strategy/positioning |
Medium — credible but differentiated |
Competitive contrast + audience psychology |
One-line positioning + why defensible |
Thinking Triggers
- "What two things never combined would produce this?"
- "What frame would make an expert in [seed] uncomfortable?"
- "What's the version that doesn't exist yet because no one connected these two worlds?"
- "If I couldn't use any word associated with [seed], how would I describe this?"
- "What would someone from [random profession] find interesting about this?"
Example Applications
- Open-source context standard name → cartography × mycology × textile weaving × astronomical navigation × culinary mise en place → 15+ candidates
- Fresh angle for conference talk → thesis × sommelier service × ER triage × darkroom photography × archaeological stratigraphy → metaphor reframes the audience
- Team offsite ideas → "team alignment" × improv × foraging × radio astronomy × bread baking → activities that embody the goal, not discuss it
- Marketing angles → value prop × magician's misdirection × geological sedimentation × DJ mixing × sourdough → angle competitors can't copy
1---2name: bisociative-creativity3description: Apply bisociative creativity whenever the user wants to generate genuinely novel ideas, concepts, names, narratives, metaphors, or creative directions. Triggers on phrases like "give me ideas for", "brainstorm", "I need something creative", "help me come up with", "what's a fresh angle on", "I want something original", "make this more interesting", "surprise me", "help me ideate", or any request where the deliverable is creative output rather than analytical output. Also trigger when ideas feel generic or like AI slop. This is the go-to skill for creative generation across any domain — naming, writing, product concepts, marketing, talk themes, visual concepts, anything. Distinct from lateral-thinking (escaping stuck patterns) and analogical-thinking (transferring structural solutions) — this skill generates novel ideas by colliding unrelated frames of reference.4---56# Bisociative Creativity78**Core principle**: Creativity = collision between two unrelated frames of reference. Koestler's **bisociation** — two "matrices of thought" intersect, producing something that belongs to neither but couldn't exist without both.910LLMs default to mode-seeking (most likely continuation). Creativity is off the mode. This skill forces the model into productive collision space.1112---1314## When to Use1516| Skill | Use case |17|-------|----------|18| lateral-thinking | Escape a dominant pattern when stuck |19| analogical-thinking | Transfer structural solutions across domains |20| **bisociative-creativity** | Deliverable is an idea (not a diagnosis or decision) |2122---2324## Phase 1 — Frame Selection (Divergent)2526Quality of output depends on **distance** of the colliding frames. Close frames = incremental ideas. Distant frames = surprising ones.2728**Step 1: Name the seed domain.** State the topic/brief.2930**Step 2: Generate 5–7 distant frames** with no obvious connection to the seed:3132| Generator | Method |33|-----------|--------|34| **Sensory world** | Physical material, texture, natural process (mycelium, tidal erosion, fermentation) |35| **Historical era** | Non-obvious period (Venetian glassmaking, Rosetta Stone decipherment) |36| **Art form** | Discipline far from seed (Butoh dance, mosaic restoration, jazz comping) |37| **Everyday ritual** | Mundane activity (packing a suitcase, mise en place, tuning a guitar) |38| **Unrelated industry** | Zero surface overlap (perfumery, air traffic control, wine terroir) |39| **Emotional state** | Specific feeling (the moment before a sneeze, homesickness, flow) |40| **Constraint injection** | Arbitrary rule from another domain ("what if context expired like fresh produce?") |4142**Frame rules:**43- If the connection is immediately visible, the frame is too close44- ≥2 frames should feel absurd or uncomfortable45- Reject dead metaphors (orchestra conductor for leadership; journey for change)4647---4849## Phase 2 — Collision5051For each frame, force collision via structural interrogation. Ask in order:52531. **Core mechanic** — How does this frame work, physically or conceptually?542. **Tensions/trade-offs** — What does it balance? What can go wrong?553. **Bisociation point** — Where does its structure intersect the seed's structure?564. **Idea produced** — Concrete concept, not abstract connection.5758**Critical: no judgment in Phase 2.** Premature convergence is the #1 killer.5960**Example — seed: "name for visual knowledge mapping tool", frame: fermentation:**61- Mechanic: transformation over time; raw inputs become new through controlled conditions62- Tensions: speed vs. depth; control vs. wild cultures63- Bisociation: knowledge isn't organized — it *develops*64- Ideas: "Kultur", "Starter", tagline "Let your ideas develop"6566---6768## Phase 3 — Harvest (Convergent)6970Triage every idea:7172| Bucket | Criteria | Action |73|--------|----------|--------|74| Live spark | Surprising AND structurally sound | Develop immediately |75| Kernel | Idea impractical, but useful concept buried inside | Extract, restate, find better vehicle |76| Dead end | Forced, generic, or only works if you squint | Discard |7778**For each live spark:** state in one sentence; explain the collision; give 2–3 variations; pick strongest expression.7980**For each kernel:** extract the usable concept; combine with another kernel/spark; collide with a *different* Phase 1 frame.8182---8384## Output Format8586### Creative Brief87Restate seed + kind of ideas needed.8889### Frame Selection90List 5–7 frames + one-line distance justification each.9192### Collisions93For each: Frame × Seed | Core mechanic | Bisociation point | Ideas produced.9495### Live Sparks963–5 strongest. Each: idea (one sentence), why it works, 2–3 variations, strongest expression.9798### Kernels Worth Saving99Extracted concepts for later/combination.100101---102103## Oblique Strategy Injections104105Use when the collision phase feels mechanical:106107- *"What if the opposite of this idea were the idea?"*108- *"What would make someone laugh about this?"*109- *"What would this be if it were a sound? A smell? A temperature?"*110- *"What's the version that would get you fired?"*111- *"What's the version a 6-year-old would invent?"*112- *"Honor thy error as a hidden intention."*113- *"What would this look like in 1926? In 2126?"*114- *"Remove the most important element. What's left?"*115116---117118## Anti-Patterns119120| Anti-pattern | Symptom | Fix |121|-------------|---------|-----|122| Mode-seeking | Ideas sound like generic "creative AI" | Increase frame distance; add constraint injection |123| Dead metaphor | Tired comparisons (journey, tapestry, compass) | Reject any frame already a cliché for the seed |124| Premature convergence | Filtering during Phase 2 | No judgment until Phase 3 |125| Surface bisociation | Wordplay, not structural | "Does this work if I remove the pun?" |126| Quantity collapse | Stopping at 3 ideas | Set a quota (min 15 raw ideas) |127| Comfort zone frames | All frames adjacent to seed | Mandate ≥2 from sensory/emotional/everyday |128129---130131## Recombination Protocol132133After initial harvest, cross-pollinate:1341351. Take top 3 live sparks1362. Ask: *"What if Spark A and Spark B were the same idea?"*1373. Force the combination — don't ask if it makes sense yet1384. Best idea often comes from second-order collision (two bisociations bisociating)139140---141142## Calibration by Task143144| Task | Frame distance | Collision depth | Output style |145|------|---------------|-----------------|-------------|146| Naming | Maximum — absurd frames welcome | Sound, rhythm, double meaning | Short, punchy, memorable |147| Concepts | High — cross-industry | Mechanics + UX | Functional + emotional hook |148| Writing angles | Medium-high — surprising but graspable | Narrative tension + audience surprise | Thesis + opening line |149| Visual concepts | Maximum — synesthetic frames | Sensory overlap + spatial metaphor | Image description + mood |150| Strategy/positioning | Medium — credible but differentiated | Competitive contrast + audience psychology | One-line positioning + why defensible |151152---153154## Thinking Triggers155156- *"What two things never combined would produce this?"*157- *"What frame would make an expert in [seed] uncomfortable?"*158- *"What's the version that doesn't exist yet because no one connected these two worlds?"*159- *"If I couldn't use any word associated with [seed], how would I describe this?"*160- *"What would someone from [random profession] find interesting about this?"*161162---163164## Example Applications165166- **Open-source context standard name** → cartography × mycology × textile weaving × astronomical navigation × culinary mise en place → 15+ candidates167- **Fresh angle for conference talk** → thesis × sommelier service × ER triage × darkroom photography × archaeological stratigraphy → metaphor reframes the audience168- **Team offsite ideas** → "team alignment" × improv × foraging × radio astronomy × bread baking → activities that embody the goal, not discuss it169- **Marketing angles** → value prop × magician's misdirection × geological sedimentation × DJ mixing × sourdough → angle competitors can't copy
andurilcode