pun-decomposition

Decompose surface forms into multiple valid parses within an ACSet schema.

60|13|Updated Dec 22, 2025
One-click install
npx skills add https://github.com/plurigrid/asi --skill pun-decomposition
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pun-decomposition
Source: https://github.com/plurigrid/asi/tree/main/skills/pun-decomposition
Command: npx skills add https://github.com/plurigrid/asi --skill pun-decomposition

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

A pun expands a surface form into multiple valid interpretations, each with its own decomposition, highlighting ambiguity and alternative parses.

Core Features & Use Cases

  • Gestalt-aware decompositions: evaluates multiple plausible parses.
  • ACSet schema for puns: defines surface, parses, meanings, and biases.
  • Inductive bias as prior: models how context favors certain parses.

Quick Start

Explore multiple parses for a given surface, then compare their decompositions.

Frequently Asked Questions about pun-decomposition

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I decompose text into multiple valid interpretations?

Decomposition breaks a surface form into multiple valid parses, each revealing different interpretations. This Skill evaluates gestalt-aware decompositions using an ACSet schema to track surfaces, parses, morphemes, and meanings, enabling you to explore alternative linguistic structures within a single text.

What is a pun and how does it relate to natural language understanding?

A pun expands one surface form into multiple valid interpretations, each with its own decomposition. Understanding puns strengthens natural language processing by modeling ambiguity and alternative parses—core challenges in text interpretation workflows where context and inductive bias shape which parse is favored.

How do inductive bias and context affect parse selection?

Inductive bias acts as a prior that models how context favors certain parses over others. This Skill implements multi-parse validation with bias control, letting you observe how prior assumptions influence which decomposition is selected from multiple valid alternatives.

Can I use this for linguistic humor analysis?

Yes. This Skill applies directly to linguistic humor analysis by decomposing puns into their constituent parses and meanings. It models how ambiguity and alternative decompositions create the cognitive misdirection that drives humor recognition.

What data structures does this use to represent decompositions?

Decompositions are represented within an ACSet schema containing surfaces, parses, morphemes, and meanings. Each meaning includes text, trit values, and bias parameters, enabling triad-aware context modeling and schema-aware validation of alternative interpretations.

When should I use multi-parse validation instead of single-parse analysis?

Use multi-parse validation when ambiguity is meaningful—in humor analysis, gestalt perception tasks, or schema-aware interpretation where alternative decompositions coexist validly. Single-parse approaches miss this structural richness; multi-parse modeling reveals how surface forms support competing valid interpretations.