Coding Challenge Generator

A topic + difficulty range → a graded ladder of auto-checkable challenges.

Purpose

Single exercises are easy; a coherent ladder that builds a skill is hard. This skill emits a set of challenges of rising difficulty around one topic, each fully specified and testable — ready to drop into a course, a bootcamp, or interview prep. (For a single richly-scaffolded space-themed lab, use ../../coding/cosmic-code-lab.)

When it fires

• Keyword triggers: coding challenges, problem set, exercises,

challenge ladder, interview prep

• File triggers: challenges/**, problems/**
• Command triggers: /coding-challenge-generator

Inputs

Workflow

1. Decompose the topic into a rising sequence of sub-skills. ✅ Check: each

step depends on the prior.

1. Per challenge: statement, constraints, input/output spec, hidden tests

(happy + edge + error), and a reference solution that passes them.

1. Grade the ladder — assign a difficulty label; verify monotonic increase.
2. Self-verify — each solution passes its tests; each empty starter fails.

Output contract

{
  "topic": "string",
  "challenges": [{
    "title": "string",
    "difficulty": "intro | easy | medium | hard | advanced",
    "statement": "string",
    "starter_code": "string",
    "tests": "string",
    "solution": "string"
  }]
}

Tools & MCP

• Tools: Write, Bash (run tests). MCP: none required.

Quality bar

• [ ] Difficulty increases monotonically and is justified.
• [ ] Each solution passes its tests; each starter fails them.
• [ ] Statements are implementable from text alone.

Example

Input: topic "recursion", count 5 → five Python challenges from factorial to a tree traversal, each with hidden tests and a passing solution.

Built on SIP — Starlight Intelligence Protocol Substrate: starlightintelligence.org/protocol v1.1.0 Layers used: [file-contract, attestation, sovereignty] Vertical: starlight-agent-skills · portable capability layer