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
| Input |
Required |
Notes |
topic |
yes |
Skill/concept the set trains (e.g. "recursion"). |
language |
no |
python (default) or javascript. |
count |
no |
Number of challenges, default 5. |
range |
no |
Difficulty span, default intro→advanced. |
Workflow
- Decompose the topic into a rising sequence of sub-skills. ✅ Check: each
step depends on the prior.
- Per challenge: statement, constraints, input/output spec, hidden tests
(happy + edge + error), and a reference solution that passes them.
- Grade the ladder — assign a difficulty label; verify monotonic increase.
- 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
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
1---2name: coding-challenge-generator3description: Generate a graded set of coding challenges around a topic — progressive difficulty, each with statement, constraints, hidden tests, and solution. Use when building a problem set, a challenge ladder, interview prep, or a curriculum of exercises.4---56# Coding Challenge Generator78> A topic + difficulty range → a graded ladder of auto-checkable challenges.910## Purpose1112Single exercises are easy; a *coherent ladder* that builds a skill is hard. This13skill emits a set of challenges of rising difficulty around one topic, each fully14specified and testable — ready to drop into a course, a bootcamp, or interview15prep. (For a single richly-scaffolded space-themed lab, use16[`../../coding/cosmic-code-lab`](../../coding/cosmic-code-lab).)1718## When it fires1920- Keyword triggers: `coding challenges`, `problem set`, `exercises`,21 `challenge ladder`, `interview prep`22- File triggers: `challenges/**`, `problems/**`23- Command triggers: `/coding-challenge-generator`2425## Inputs2627| Input | Required | Notes |28|-------|----------|-------|29| `topic` | yes | Skill/concept the set trains (e.g. "recursion"). |30| `language` | no | `python` (default) or `javascript`. |31| `count` | no | Number of challenges, default `5`. |32| `range` | no | Difficulty span, default `intro→advanced`. |3334## Workflow35361. **Decompose the topic** into a rising sequence of sub-skills. ✅ Check: each37 step depends on the prior.382. **Per challenge:** statement, constraints, input/output spec, hidden tests39 (happy + edge + error), and a reference solution that passes them.403. **Grade the ladder** — assign a difficulty label; verify monotonic increase.414. **Self-verify** — each solution passes its tests; each empty starter fails.4243## Output contract4445```json46{47 "topic": "string",48 "challenges": [{49 "title": "string",50 "difficulty": "intro | easy | medium | hard | advanced",51 "statement": "string",52 "starter_code": "string",53 "tests": "string",54 "solution": "string"55 }]56}57```5859## Tools & MCP6061- Tools: `Write`, `Bash` (run tests). MCP: none required.6263## Quality bar6465- [ ] Difficulty increases monotonically and is justified.66- [ ] Each solution passes its tests; each starter fails them.67- [ ] Statements are implementable from text alone.6869## Example7071Input: topic "recursion", count 5 → five Python challenges from factorial to a72tree traversal, each with hidden tests and a passing solution.7374---7576Built on SIP — Starlight Intelligence Protocol77Substrate: starlightintelligence.org/protocol v1.1.078Layers used: [file-contract, attestation, sovereignty]79Vertical: starlight-agent-skills · portable capability layer