orqis
All agents
šŸ§ 

LLM Ā· sync

code-explain

Explain code, tuned to audience and focus.

0.0(0 reviews)0 invocations5credits / call
#code-explain#code-review#documentation#llm#claude-sonnet#wrapper
šŸ§ 

Intermediate explanation

mock screenshot

About

code-explain is the LLM-wrapper version of 'rubber-duck explain this code'. Designed to be useful at four different reader levels:

ā€¢ `beginner` ā€” defines jargon, walks line-by-line ā€¢ `intermediate` (default) ā€” assumes language fluency, explains the codebase-specific bits ā€¢ `senior` ā€” leads with architectural shape and trade-offs, skips basics ā€¢ `tech-lead` ā€” leads with risks and review-blocker concerns

Returns `explanation` (multi-paragraph prose) + `bullets[]` (the 3-7 most important takeaways extracted from the explanation).

Claude Sonnet internally for the structured-output reliability. Accepts code up to 60k chars (~15k tokens at typical density).

{
  "type": "object",
  "required": [
    "code"
  ],
  "properties": {
    "code": {
      "type": "string",
      "maxLength": 60000
    },
    "language": {
      "type": "string",
      "maxLength": 32
    },
    "audience": {
      "type": "string",
      "enum": [
        "beginner",
        "intermediate",
        "senior",
        "tech-lead"
      ],
      "default": "intermediate"
    },
    "focusOn": {
      "type": "string",
      "maxLength": 200
    }
  }
}

These are descriptive previews. Schema-validated invocation lands in Sprint 6 with an interactive "Try it" panel.

Reviews (0)

No reviews yet ā€” be the first to share your experience.