OpenParable
Skip to content
← Back to skills

Type Theory

Development

Type Theory is an Agent Skill for development published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Expert skill in type theory foundations for implementing type systems including inference, checking, and subtyping

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/a5c-ai/babysitter/blob/HEAD/library/specializations/programming-languages/skills/type-theory/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/type-theory, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Type Theory Skill

Overview

Expert skill in type theory foundations for implementing type systems including inference, checking, and subtyping.

Capabilities

  • Implement Hindley-Milner type inference with Algorithm W
  • Implement constraint-based type inference with unification
  • Design and implement bidirectional type checking
  • Implement structural and nominal subtyping
  • Handle variance (covariant, contravariant, invariant)
  • Implement row polymorphism and record types
  • Design flow-sensitive type narrowing
  • Implement type error message generation

Target Processes

  • type-system-implementation.js
  • semantic-analysis.js
  • generics-polymorphism.js
  • effect-system-design.js

Dependencies

Academic type theory literature (TAPL, ATTAPL)

Usage Guidelines

  1. Algorithm Selection: Choose between HM inference and bidirectional checking based on language features
  2. Constraint Generation: Separate constraint generation from solving for cleaner implementation
  3. Error Localization: Track constraint origins for accurate error location
  4. Variance: Document variance rules explicitly for all generic positions
  5. Gradual Typing: Consider gradual typing for mixed typed/untyped codebases

Output Schema

{
  "type": "object",
  "properties": {
    "inferenceAlgorithm": {
      "type": "string",
      "enum": ["hindley-milner", "bidirectional", "constraint-based", "flow-sensitive"]
    },
    "subtypingKind": {
      "type": "string",
      "enum": ["structural", "nominal", "mixed"]
    },
    "features": {
      "type": "array",
      "items": { "type": "string" }
    },
    "generatedFiles": {
      "type": "array",
      "items": { "type": "string" }
    }
  }
}