icpc-problem-creator

Generate a complete ICPC problem workspace with statement, solutions, checker, validator, and config.json.

42|1|Updated Apr 28, 2026
One-click install
npx skills add https://github.com/Lumine2024/ICPC-Problem-Creator.skill --skill icpc-problem-creator
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: icpc-problem-creator
Source: https://github.com/Lumine2024/ICPC-Problem-Creator.skill/tree/main
Command: npx skills add https://github.com/Lumine2024/ICPC-Problem-Creator.skill --skill icpc-problem-creator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps ICPC problem setters transform a raw problem idea into a complete, iterative, locally verifiable problem workspace with consistent documentation, reference solutions, wrong solutions, and an automated test workflow.

Core Features & Use Cases

  • Workspace bootstrapping for both standard and interactive problems, including config.json-driven generation and judging.
  • End-to-end local verification loop: build, generate tests, validate inputs, judge solutions with checker/interactor, and validate wrong solutions against expected verdicts.
  • Parallelized agent collaboration model: main agent sets architecture and delegates judge/validator, solutions/tutorial, and wrong solutions + generator.

Quick Start

Tell the agent: "Create a new standard ICPC problem workspace named 'my-problem' and generate a complete runnable config.json workflow for local testing."

Frequently Asked Questions about icpc-problem-creator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a locally testable ICPC problem workspace from an idea?

ICPC problem authoring requires generating solutions, a checker or interactor, a validator, and a generator to build a complete locally verifiable workspace. This ensures repeatable local generation and judging for both standard and interactive problems.

How do I ensure deterministic test case generation for ICPC problem judging?

Deterministic test case generation is ensured by driving the generator with argv parameters like type and seed. This allows the local validation workflow to consistently reproduce test cases across multiple runs.

What is the best way to validate wrong solutions against expected verdicts in competitive programming?

Validating wrong solutions requires a local verification loop that runs generated wrong solutions through a checker or interactor and compares the output against expected verdicts using a config.json-driven test script.

Can I use a config.json workflow to automate interactive ICPC problem judging locally?

Yes, interactive ICPC problem judging can be automated locally using a config.json file that drives scripts like run-all-tests.ps1 to compile, generate tests, and validate solutions end-to-end with an interactor.

What components do I need for a complete ICPC problem authoring setup?

A complete ICPC problem authoring setup requires a problem statement, reference solutions, wrong solutions, a checker or interactor, a validator, a generator, and a config.json file to orchestrate the local test workflow.

Why does my local ICPC problem validation fail to compile solutions consistently?

Local ICPC problem validation fails when config.json does not properly drive scripts like run-all-tests.ps1 to compile and validate end-to-end. Ensuring deterministic generator cases via argv type and seed maintains consistency.