Install any skill in seconds. Free to start, no credit card required.
Get Started Free →a5c-ai/Type Theory
Expert skill in type theory foundations for implementing type systems including inference, checking, and subtyping
Passed 16 of 24 test cases with the skill, and 14 of 24 without it.
2 fixed14 passed either way8 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are developing a lightweight functional language compiler and need to design its static type checker module. The system needs to support parametric polymorphism and record extension. Please generate a type system specification and implementation plan. Output your response as a JSON object containing the primary inference algorithm choice, the subtyping mechanism classification, an array of implemented features, and the list of output code filenames produced.
| Checked | Without skill | With skill |
|---|---|---|
| The JSON output uses exact key inferenceAlgorithm. | Missed | Passed |
| The implementation plan separates constraint generation from constraint solving into distinct phases. | Missed | Passed |
The instructions your model reads when the skill loads.
Expert skill in type theory foundations for implementing type systems including inference, checking, and subtyping.
Academic type theory literature (TAPL, ATTAPL)
{
test cases passed, vs 14 / 24 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.