Initial commit: antigravity-claudekit
This commit is contained in:
83
skills/ck-problem-solving/SKILL.md
Normal file
83
skills/ck-problem-solving/SKILL.md
Normal file
@@ -0,0 +1,83 @@
|
||||
---
|
||||
name: ck-problem-solving
|
||||
description: Apply systematic problem-solving techniques when stuck. Use for complexity spirals, innovation blocks, recurring patterns, assumption constraints, simplification cascades, and scale uncertainty.
|
||||
---
|
||||
|
||||
# Problem-Solving Techniques
|
||||
|
||||
Systematic approaches for different types of stuck-ness. Each technique targets a specific problem pattern.
|
||||
|
||||
## When to Use
|
||||
|
||||
- Complexity spiraling: multiple implementations, growing special cases
|
||||
- Innovation blocks: conventional solutions inadequate
|
||||
- Recurring patterns: same issue appearing across domains
|
||||
- Assumption constraints: forced into "only one way"
|
||||
- Scale uncertainty: production readiness unclear
|
||||
- General stuck-ness: unsure which approach to take
|
||||
|
||||
## Don't Use When
|
||||
|
||||
- Problem is straightforward and well-understood
|
||||
- Simply need more time or information, not a different approach
|
||||
|
||||
## Quick Dispatch
|
||||
|
||||
| Stuck Symptom | Technique |
|
||||
|---------------|-----------|
|
||||
| Same thing implemented 5+ ways, growing special cases | Simplification Cascades |
|
||||
| Conventional solutions inadequate, need breakthrough | Collision-Zone Thinking |
|
||||
| Same issue in different places, reinventing wheels | Meta-Pattern Recognition |
|
||||
| Solution feels forced, "must be done this way" | Inversion Exercise |
|
||||
| Will this work at production? Edge cases unclear? | Scale Game |
|
||||
|
||||
## Core Techniques
|
||||
|
||||
### 1. Simplification Cascades
|
||||
Find one insight eliminating multiple components. "If this is true, we don't need X, Y, Z."
|
||||
|
||||
**Key insight:** Everything is a special case of one general pattern.
|
||||
|
||||
**Red flag:** "Just need to add one more case..." (repeating forever)
|
||||
|
||||
### 2. Collision-Zone Thinking
|
||||
Force unrelated concepts together. "What if we treated X like Y?"
|
||||
|
||||
**Key insight:** Revolutionary ideas emerge from deliberate metaphor-mixing.
|
||||
|
||||
**Red flag:** "I've tried everything in this domain"
|
||||
|
||||
### 3. Meta-Pattern Recognition
|
||||
Spot patterns appearing in 3+ domains to find universal principles.
|
||||
|
||||
**Key insight:** Patterns in how patterns emerge reveal reusable abstractions.
|
||||
|
||||
**Red flag:** "This problem is unique" (probably not)
|
||||
|
||||
### 4. Inversion Exercise
|
||||
Flip core assumptions. "What if the opposite were true?"
|
||||
|
||||
**Key insight:** Valid inversions reveal context-dependence of assumed "rules."
|
||||
|
||||
**Red flag:** "There's only one way to do this"
|
||||
|
||||
### 5. Scale Game
|
||||
Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths.
|
||||
|
||||
**Key insight:** What works at one scale fails at another.
|
||||
|
||||
**Red flag:** "Should scale fine" (without testing)
|
||||
|
||||
## Application Process
|
||||
|
||||
1. Identify stuck-type — match symptom to technique above
|
||||
2. Apply technique systematically
|
||||
3. Document insights — record what worked and what failed
|
||||
4. Combine if needed — some problems need multiple techniques
|
||||
|
||||
## Powerful Combinations
|
||||
|
||||
- **Simplification + Meta-pattern** — find pattern, then simplify all instances
|
||||
- **Collision + Inversion** — force metaphor, then invert its assumptions
|
||||
- **Scale + Simplification** — extremes reveal what to eliminate
|
||||
- **Meta-pattern + Scale** — universal patterns tested at extremes
|
||||
Reference in New Issue
Block a user