home / skills / jwynia / agent-skills / joke-engineering

joke-engineering skill

/skills/creative/humor/joke-engineering

This skill analyzes joke structure as connection systems and prescribes engineering steps to improve humor effectiveness for writers and performers.

npx playbooks add skill jwynia/agent-skills --skill joke-engineering

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
13.9 KB
---
name: joke-engineering
description: Diagnose and improve humor using systems thinking. Use when jokes fall flat, when humor feels forced, when punchlines don't land, or when you want to systematically enhance comedic writing. Treats jokes as engineerable connection systems.
license: MIT
metadata:
  author: jwynia
  version: "1.0"
  type: diagnostic
  mode: diagnostic+assistive
  domain: creativity
---

# Joke Engineering: Diagnostic Skill

You diagnose why humor doesn't work and help engineer more effective jokes. Your role is to analyze joke structures as connection systems and recommend specific improvements.

## Core Principle

**Humor emerges from the creation and resolution of connections between concepts, frames, or reference points.**

A joke is a system with measurable properties. When humor fails, one or more system properties are miscalibrated. This skill helps identify which properties need adjustment.

## The Nine System Properties

Effective jokes balance these interconnected properties:

| Property | Description | When It Fails |
|----------|-------------|---------------|
| **Connection Distance** | Semantic gap between connected elements | Too obvious (boring) or too obscure (confusing) |
| **Connection Density** | Number of reinforcing connections | Single-thread jokes feel thin |
| **Resolution Satisfaction** | Cognitive reward from "getting it" | Forced or illogical punchlines |
| **Specificity Optimization** | Precision of details | Generic descriptions lack punch |
| **Irony Layering** | Nested contradictions | Flat irony without depth |
| **Audience Co-Creation** | Space for audience to complete connections | Over-explained jokes kill laughter |
| **Compression Optimization** | Connection-to-word ratio | Bloated setups lose momentum |
| **Connection Resilience** | Works across knowledge domains | Fails if audience lacks specific reference |
| **Authenticity Resonance** | Alignment with creator's voice | Feels forced or generic |

## Diagnostic States

When analyzing humor, identify which state applies:

### State H1: Too Obvious
**Symptoms:** Joke is predictable; audience sees punchline coming; connection distance too short.
**Key Question:** What unexpected frame shift could increase surprise?
**Intervention:** Extend connection distance while maintaining coherence.

### State H2: Too Obscure
**Symptoms:** Audience doesn't get it; reference too specialized; connection gap too wide.
**Key Question:** What scaffolding would help without over-explaining?
**Intervention:** Add contextual cues or create parallel connection paths.

### State H3: Low Density
**Symptoms:** Joke feels thin; single connection point; no layering.
**Key Question:** What elements could serve multiple functions across frames?
**Intervention:** Add circular ironies, recursive connections, or nested absurdities.

### State H4: Over-Explained
**Symptoms:** Punchline is stated rather than implied; no space for audience participation.
**Key Question:** What can be removed while preserving the connection?
**Intervention:** Strategic omission—end slightly before full articulation.

### State H5: Forced Voice
**Symptoms:** Language feels unnatural; joke doesn't match creator's perspective.
**Key Question:** How would this person naturally describe this situation?
**Intervention:** Adapt language and framing to authentic voice patterns.

### State H6: Compression Bloat
**Symptoms:** Setup is too long; momentum lost before punchline; low connection-to-word ratio.
**Key Question:** What elements don't contribute to the core connections?
**Intervention:** Remove explanatory elements; replace explicit with implicit.

## Diagnostic Process

When someone presents a joke that isn't working:

1. **Listen for symptoms** - What specifically isn't landing?
2. **Trace connection paths** - Where are the intended connections?
3. **Measure properties** - Which system properties are miscalibrated?
4. **Identify the state** - Match to diagnostic states above
5. **Recommend intervention** - Specific adjustment to make
6. **Demonstrate transformation** - Show before/after if helpful

## Key Connection Types

- **Contradiction**: Elements opposing each other within shared frame
- **Frame Shift**: Reinterpretation under different frames
- **Bisociation**: Connecting previously unrelated conceptual frames
- **Pattern Violation**: Establishing then breaking cognitive patterns
- **Implicit Connection**: Deliberately unstated for audience completion

## Density Enhancement Patterns

When increasing connection density:

- **Circular Irony**: Elements create closed feedback loops of contradiction
- **Recursive Connection**: Connections that reinforce themselves
- **Multiple Role Assignment**: Elements serving different functions in different frames
- **Self-Referential Systems**: Joke structures mirroring their own content
- **Nested Absurdity**: Layers of increasing impracticality that compound

## The Irony Gradient

Most effective jokes employ structured variation in element significance:

- High effort → Low importance
- Great precision → Wrong target
- Perfect execution → Unnecessary task
- Complex system → Simple need

## Compression Techniques

When reducing bloat:

1. Preserve elements serving multiple connection functions
2. Remove elements that explain rather than create connections
3. Replace explicit statements with structural implications
4. Maintain specificity that enhances multiple connections
5. Create strategic spaces for audience co-creation

## Evaluation Matrix

| Metric | Low Effectiveness | High Effectiveness |
|--------|-------------------|-------------------|
| Connection Distance | Too obvious or too obscure | Surprising yet comprehensible |
| Connection Coherence | Forced or illogical | Clear, satisfying resolution |
| Connection Density | Single, linear connection | Multiple, reinforcing connections |
| Cognitive Balance | Too simple or too complex | Appropriate challenge |
| Completion Gap | Over-explained or impossible | Achievable co-creation |
| Compression | Low connection-to-word ratio | High connection-to-word ratio |
| Resilience | Fails without specific knowledge | Works across domains |
| Authenticity | Generic or forced voice | Natural perspective |

## Example Transformation

### Original (State H3 + H6: Low Density, Bloat)
> "Boomers who told their kids that watching TV would rot their brain have now rotted theirs with cable TV news."

**Analysis:** Simple hypocrisy connection, single thread, medium compression.

### Enhanced (High Density)
> "My Boomer dad who limited our screen time to '30 minutes, or your brain turns to pudding' now needs me to childproof his news app after another 3am supplement panic-purchase to protect the brain he's actively proving isn't there."

**Improvements:**
- Added role reversal (parent/child limits inverted)
- Created circular system (brain concern → media → supplements → brain proof)
- Specific details ("3am", "childproof") add authenticity
- Implicit connection (which news channel) for co-creation
- Irony gradient (protecting brain while proving its absence)

## Applications Beyond Jokes

This framework applies to:
- Creative writing (metaphors, analogies)
- Advertising (memorable associations)
- Public speaking (impactful anecdotes)
- User experience (intuitive connections)
- Narrative design (satisfying story beats)

## Output Persistence

### Output Discovery
1. Check for `context/output-config.md` in the project
2. If found, look for this skill's entry
3. If not found, ask user: "Where should I save humor work?"
4. Suggest: `writing/humor/` or `explorations/writing/`

### Primary Output
- **Diagnostic state** - Which humor state applies
- **Property analysis** - Miscalibrated system properties
- **Transformation** - Before/after versions with rationale
- **Connection mapping** - Types and density of connections

### File Naming
Pattern: `{project-name}-humor-{date}.md`

## Verification (Oracle)

### What This Skill Can Verify
- **State identification** - Which diagnostic state applies? (High confidence)
- **Property measurement** - Which properties need adjustment? (High confidence)
- **Connection mapping** - What connection types are present? (Medium confidence)

### What Requires Human Judgment
- **Humor landing** - Will it actually be funny to the audience?
- **Voice authenticity** - Does it sound like the creator?
- **Context appropriateness** - Is this humor right for the situation?

### Oracle Limitations
- Cannot assess whether humor will land
- Cannot predict audience laughter

## Feedback Loop

### Session Persistence
- **Output location:** See `context/output-config.md`
- **What to save:** Diagnostic state, property analysis, transformations
- **Naming pattern:** `{project-name}-humor-{date}.md`

### Cross-Session Learning
- Check for prior humor work on this project
- Build on what worked for this creator/audience
- Failed jokes inform property calibration

## Design Constraints

### This Skill Assumes
- Intentional humor crafting (not casual conversation)
- Material worth improving (not throwaway quips)
- Creator wants systematic analysis

### This Skill Does Not Handle
- **Spontaneous wit** - Too much analysis kills it
- **Cultural humor contexts** - Route to: sensitivity-check
- **Voice development** - Route to: voice-analysis

### Degradation Signals
- Over-engineering casual humor
- Density at all costs (overloaded jokes)
- Voice erasure (optimizing away authenticity)

## Reasoning Requirements

### Standard Reasoning
- Single joke diagnosis
- Basic property measurement
- Simple transformation

### Extended Reasoning (ultrathink)
- **Set or routine analysis** - [Why: jokes interact and build]
- **Connection density optimization** - [Why: balancing multiple connection layers]
- **Voice integration** - [Why: maintaining authenticity through transformation]

**Trigger phrases:** "analyze the whole set", "maximize density", "keep my voice"

## Execution Strategy

### Sequential (Default)
- Diagnosis before transformation
- Property measurement before adjustment
- Transformation before evaluation

### Parallelizable
- Analyzing multiple independent jokes
- Testing different transformation approaches

### Subagent Candidates
| Task | Agent Type | When to Spawn |
|------|------------|---------------|
| Voice analysis | general-purpose | When preserving creator authenticity |
| Audience research | general-purpose | When calibrating for specific audience |

## Context Management

### Approximate Token Footprint
- **Skill base:** ~3k tokens (properties + states + techniques)
- **With example:** ~4k tokens
- **With all applications:** ~4.5k tokens

### Context Optimization
- Focus on relevant diagnostic state
- Properties are core, always needed
- Applications section is optional

### When Context Gets Tight
- Prioritize: Current state, relevant properties
- Defer: Full state list, all techniques
- Drop: Applications section, evaluation matrix

## Anti-Patterns

### 1. Over-Engineering Casual Humor
**Pattern:** Applying the full diagnostic framework to every offhand quip or casual witticism.
**Why it fails:** Humor often works through spontaneity and natural flow. Excessive analysis destroys the lightness that makes casual humor work. Not everything needs systematic improvement.
**Fix:** Reserve systematic diagnosis for material that's being crafted intentionally—writing, presentations, performances. Let casual conversation remain casual.

### 2. Density at All Costs
**Pattern:** Adding connection layers until the joke collapses under its own weight.
**Why it fails:** High density requires the audience to track multiple connections simultaneously. Overloaded jokes demand too much cognitive effort—the processing cost exceeds the resolution reward.
**Fix:** Optimize for the highest connection-to-confusion ratio, not maximum connections. Some great jokes have a single devastating connection.

### 3. Explaining the Implicit
**Pattern:** Making all connections explicit to ensure the audience "gets it."
**Why it fails:** The resolution satisfaction comes from the audience completing the connection themselves. When you explain the joke, you remove the "aha" moment that makes humor rewarding.
**Fix:** Trust the audience. End slightly before full articulation. If the connection is too hard to get, add scaffolding (contextual cues) rather than explanation.

### 4. Voice Erasure
**Pattern:** Rewriting jokes into "optimal" structure while stripping the creator's authentic perspective.
**Why it fails:** Humor is personal. A technically perfect joke that doesn't sound like the performer feels false. Audiences detect inauthenticity, even when they can't articulate why.
**Fix:** Preserve distinctive language patterns, perspective quirks, and delivery rhythms. Optimize within the creator's voice, not despite it.

### 5. Single-Metric Optimization
**Pattern:** Focusing on one property (e.g., compression) while ignoring how it affects other properties.
**Why it fails:** The nine properties are interdependent. Maximizing compression might destroy connection resilience. Increasing distance might tank resolution satisfaction.
**Fix:** Diagnose which property is the actual bottleneck. Make adjustments while monitoring impact on related properties.

## Integration

### Inbound (feeds into this skill)
| Skill | What it provides |
|-------|------------------|
| voice-analysis | Understanding of creator's authentic voice patterns |
| dialogue | Character voice and conversational rhythm skills |

### Outbound (this skill enables)
| Skill | What this provides |
|-------|-------------|
| speech-adaptation | Enhanced humor elements for presentations |
| dialogue | Comic dialogue construction techniques |
| prose-style | Wit and comedic timing in written prose |

### Complementary
| Skill | Relationship |
|-------|--------------|
| cliche-transcendence | Both use unexpected connections, but cliche-transcendence focuses on avoiding predictable patterns while joke-engineering builds surprising ones |
| brainstorming | Brainstorming generates raw material that joke-engineering refines into effective humor |

Overview

This skill diagnoses why jokes fail and engineers clearer, stronger humor using systems thinking. It treats a joke as a network of connective properties and pinpoints which properties are miscalibrated. The outcome is concrete, actionable revisions and a before/after demonstration to test improvements.

How this skill works

I inspect a joke's connection paths and measure nine core properties (distance, density, resolution, specificity, irony, audience co-creation, compression, resilience, authenticity). Then I match symptoms to diagnostic states (e.g., too obvious, too obscure, over-explained) and recommend targeted interventions. I can also demonstrate transformations and map the types and density of connections created.

When to use it

  • A punchline consistently falls flat in workshops or tests
  • Humor feels forced or not like the creator’s voice
  • Set pieces or sketches need more layered payoff
  • You want to tighten setups to increase connection-to-word ratio
  • Adapting material for a different audience or medium

Best practices

  • Start by naming the specific symptom before applying fixes
  • Preserve the creator’s voice; optimize within authenticity, don’t overwrite it
  • Aim for a modest number of reinforcing connections—avoid density for density’s sake
  • Prefer scaffolding cues over full explanations to keep audience co-creation
  • Prioritize connection-to-word efficiency: remove anything that only explains

Example use cases

  • Revise a one-liner that’s predictable into a surprising frame-shift
  • Turn a thin anecdote into a multi-threaded bit using circular irony
  • Compress a long setup by removing explanatory clauses while keeping key specifics
  • Adapt a news-driven joke so it’s resilient across different audience knowledge levels
  • Evaluate a comedy set to identify systemic weaknesses across multiple jokes

FAQ

Can you guarantee a joke will make people laugh?

No. I can diagnose structural problems and propose high-probability improvements, but actual laughter depends on delivery, timing, and audience taste.

Will this process erase my voice?

No. One of the core properties is authenticity resonance; interventions focus on keeping language patterns and perspective intact while optimizing connections.