Lumine2024

Lumine2024 / ICPC-Problem-Creator.skill

Public

使用AI Agent创造ICPC风格的题目

14
0
100% credibility
Found May 01, 2026 at 14 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
C++
AI Summary

A set of templates for building and testing programming contest problems, including data generators, solutions, and verifiers for both standard and interactive types.

How It Works

1
🔍 Discover Problem Templates

You find a kit of ready-made examples to help create coding contest challenges for events like ICPC.

2
Choose Challenge Style
📝
Standard Style

Perfect for straightforward problems with clear inputs and outputs.

💬
Interactive Style

Great for dynamic problems that interact step by step.

3
✏️ Tailor to Your Idea

Tweak the samples and rules to match the exact challenge you have in mind.

4
⚡ Create Test Cases

Easily generate a full set of tests to cover all possibilities for your problem.

5
🧪 Check Solutions

Try out correct answers and common mistakes to confirm everything judges fairly.

🎉 Contest Problem Ready

Your complete, tested challenge is all set to use in class or competition.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 14 to 14 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is ICPC-Problem-Creator.skill?

This C++-based creator.skill uses AI agents to generate full ICPC-style programming problems, complete with test data generators, correct and wrong sample solutions, input validators, and even interactors for interactive challenges. It spits out ready-to-test workspaces you can locally compile, generate data for, and judge via a simple PowerShell runner and config.json setup. No more hand-crafting boilerplate for contest problems—plug in your idea and get a verifiable package fast.

Why is it gaining traction?

It stands out by bundling everything needed for ICPC problem validation in one reproducible package, including deliberate wrong-answer cases to catch edge failures and Python helpers for interactive testing. Developers dig the seed-based random generation for consistent test suites and the zero-commit policy for generated data, keeping repos clean. The hook? Turns vague problem ideas into judge-ready assets in minutes, skipping the usual setup drudgery.

Who should use this?

ICPC regional organizers cranking out fresh problems under deadlines, university profs building custom programming assignments, or training camp leads needing quick interactive challenges. Ideal for anyone running C++ contests who hates repetitive generator tweaking or interactor debugging.

Verdict

With just 14 stars and a 1.0% credibility score, it's raw and unproven—docs are template-focused with minimal examples, and test coverage relies on your own runs. Worth a spin for prototyping ICPC problems if you're handy with testlib, but stabilize it first before production contests.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.