Agent skill

dad-joke-validator

Analyze and score jokes on the dad joke quality spectrum with multi-dimensional feedback on pun quality, groan factor, wholesomeness, and structure. Can also generate dad jokes.

Stars 25
Forks 5

Install this agent skill to your Project

npx add-skill https://github.com/leegonzales/AISkills/tree/main/DadJokeValidator/dad-joke-validator

SKILL.md

Dad Joke Validator

Analyze jokes for dad joke quality across multiple dimensions or generate new dad jokes.

When to Use

Invoke this skill when the user:

  • Asks you to analyze a joke for "dad joke" quality
  • Wants feedback on why a joke works (or doesn't)
  • Requests a dad joke be generated
  • Asks about pun quality, groan factor, or joke structure
  • Says things like "is this a dad joke?" or "rate this joke"

Core Capabilities

1. Joke Analysis

When analyzing a joke, score across these dimensions:

Pun Quality (0-10)

  • Wordplay sophistication
  • Multiple meanings exploited
  • Unexpected connections
  • Clarity of the pun (not too obscure)

Groan Factor (0-10)

  • How predictable the punchline is
  • "Obviousness" that triggers the groan
  • Clean setup leading to "of course" moment
  • Higher score = more groan-inducing (this is GOOD for dad jokes)

Wholesomeness (0-10)

  • Family-friendly (no edgy content)
  • Positive/innocent tone
  • Safe for all ages
  • Warm rather than mean-spirited

Setup/Punchline Structure (0-10)

  • Clear setup establishing context
  • Economical punchline (not too long)
  • Timing and rhythm
  • Misdirection technique

Overall Dad Joke Score (0-100)

  • Formula: (Pun Quality * 2.5) + (Groan Factor * 3) + (Wholesomeness * 3) + (Structure * 1.5)
  • 85-100: Peak dad joke territory
  • 70-84: Solid dad joke
  • 50-69: Dad joke adjacent (needs work)
  • Below 50: Not a dad joke

2. Analysis Output Format

Provide analysis in this structure:

Dad Joke Score: XX/100

Dimensional Breakdown:
- Pun Quality: X/10 - [Brief explanation]
- Groan Factor: X/10 - [Why it makes you groan]
- Wholesomeness: X/10 - [Family-friendly assessment]
- Structure: X/10 - [Setup/punchline evaluation]

Verdict: [One sentence overall assessment]

Improvement Suggestions (if score < 85):
- [Specific actionable feedback]

3. Dad Joke Generation

When asked to generate a dad joke:

  1. Select a wholesome theme (food, animals, occupations, everyday objects)
  2. Find a word with multiple meanings or homophones
  3. Build setup establishing one meaning
  4. Deliver punchline exploiting the other meaning
  5. Keep it SHORT (1-2 sentence setup, 1 sentence punchline max)

Quality Requirements:

  • Must score 85+ on your own rubric
  • Maximum 3 sentences total
  • Pun must be clear (not too clever)
  • Should trigger genuine groan

4. Anti-Patterns to Detect

Flag these as "NOT dad jokes":

  • Edgy or inappropriate content (Wholesomeness < 7)
  • Mean-spirited humor
  • Requires specialized knowledge (too obscure)
  • No clear pun or wordplay (Pun Quality < 5)
  • Too complex or long-winded
  • Sarcastic or ironic tone

Special Instructions

DO:

  • Explain WHY scores are assigned
  • Give specific examples in feedback
  • Maintain warmth and humor in analysis
  • Acknowledge when something is "so bad it's good"

DON'T:

  • Mock the joke harshly (dad jokes are supposed to be groan-worthy)
  • Score ironically (genuine assessment only)
  • Generate edgy content when creating jokes
  • Over-explain the pun (kills the joke)

Examples

See references/examples.md for 10 analyzed dad jokes across the quality spectrum.

Integration

Works standalone. Can be combined with:

  • Prose Polish (for joke wording refinement)
  • Meeting Bullshit Detector (for detecting forced humor in corporate settings)

Expand your agent's capabilities with these related and highly-rated skills.

leegonzales/AISkills

context-continuity

High-fidelity context transfer protocol for moving conversations between AI agents. Preserves decision tempo, open loops, and critical context with graceful degradation. Use when the user says "transfer," "handoff," "continue this in another chat," or needs to work around context window limits. Produces structured artifacts (Minimal ~200 words, Full ~1000 words). DO NOT trigger on simple "summarize our conversation" requests—only when transfer intent is explicit.

25 5
Explore
leegonzales/AISkills

codex-peer-review

25 5
Explore
leegonzales/AISkills

silicon-doppelganger

Build psychometrically accurate personal proxy agents for the PAIRL Conductor system. Extracts personality, decision heuristics, and values into portable schemas that enable AI agents to negotiate, filter, and act on a principal's behalf.

25 5
Explore
leegonzales/AISkills

requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements. Dispatches three independent reviewers in parallel.

25 5
Explore
leegonzales/AISkills

fabric-patterns

Run danielmiessler/fabric CLI patterns for content analysis, extraction, summarization, writing, security analysis, and more. Use when user asks to "use fabric," "run a pattern," "extract wisdom," "summarize with fabric," or when piping content through AI patterns would be more effective than inline processing. Triggers include "fabric," "pattern," "extract wisdom," "summarize this article," "analyze this threat report," or any reference to a specific fabric pattern name.

25 5
Explore
leegonzales/AISkills

moltbook-enclave

Secure, air-gapped interface for Moltbook (social network for AI agents). Isolates untrusted external content from your main agent's memory and context.

25 5
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results