nccuoj

Solve competitive programming problems on NCCUOJ (https://nccuoj.ebg.tw). Use when: solving OJ problems, reading problem statements, writing solutions in C/C++/Python, submitting code, checking submission results.

3,891 stars

Best use case

nccuoj is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Solve competitive programming problems on NCCUOJ (https://nccuoj.ebg.tw). Use when: solving OJ problems, reading problem statements, writing solutions in C/C++/Python, submitting code, checking submission results.

Teams using nccuoj should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/nccuoj/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/andyjjrt/nccuoj/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/nccuoj/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How nccuoj Compares

Feature / AgentnccuojStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Solve competitive programming problems on NCCUOJ (https://nccuoj.ebg.tw). Use when: solving OJ problems, reading problem statements, writing solutions in C/C++/Python, submitting code, checking submission results.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# NCCUOJ Problem Solving

Solve competitive programming problems on [NCCUOJ](https://nccuoj.ebg.tw), a QDU-based Online Judge for NCCU CS.

## When to Use

- Read a problem statement from NCCUOJ
- Write a solution for a specific problem
- Submit code and check results
- Debug a wrong answer or time limit exceeded
- Solve contest problems

## Directory Structure

All generated files are organized under `.nccuoj/` at the workspace root:

```
.nccuoj/
├── cookies.txt                                  # Session cookies (auto-managed)
└── solution/
    ├── public/<problem_id>/                      # Public problem solutions
    │   ├── problem.md                            # Problem statement
    │   └── solution.cpp / solution.py / ...      # Solution code
    └── contest/<contest_id>/<problem_id>/        # Contest problem solutions
        ├── problem.md
        └── solution.cpp / solution.py / ...
```

**When writing solution code, always place files in the correct directory.** The scripts' `--save` flag and `get_solution_dir()` helper handle directory creation automatically.

## CSRF Token (Important)

All NCCUOJ API requests require a CSRF token. The provided scripts handle this automatically (via `GET /api/profile` on init). If making manual requests, see [./references/api.md](./references/api.md) for details.

## Scripts

Use these scripts to interact with NCCUOJ. They handle CSRF tokens and session management automatically.

| Script | Purpose |
|--------|--------|
| [get_problem.py](./scripts/get_problem.py) | Fetch problem statement as Markdown (supports `--username`/`--password`, `--contest`, `--raw`) |
| [submit.py](./scripts/submit.py) | Submit code (requires `--username` / `--password` CLI args) |
| [check_result.py](./scripts/check_result.py) | Check submission result, with optional `--poll` |

All scripts use only Python stdlib (no pip install needed).

Scripts are located in this skill's `./scripts/` directory. In the examples below, `$SCRIPTS` refers to the absolute path of that directory. Resolve it relative to this SKILL.md file before running commands.

## Mode A: Public Problem Solving

### 1. Fetch the Problem

Run [get_problem.py](./scripts/get_problem.py) to fetch the problem. **If the problem requires login (e.g. returns "Please login first"), ask the user for their credentials and pass `--username`/`--password`.**

```bash
# Public (no login)
python $SCRIPTS/get_problem.py <problem_id>

# With login
python $SCRIPTS/get_problem.py <problem_id> --username <username> --password <password>
```

Or if given a URL like `https://nccuoj.ebg.tw/problem/1001`, extract `1001` and pass it as the argument.

The output is **formatted Markdown** containing: title, metadata (internal ID, difficulty, time/memory limit, tags), description, input/output format, sample test cases, hint, allowed languages, and statistics. All URL-encoded HTML fields are automatically decoded and converted to Markdown.

Use `--raw` to get the original JSON instead.

### 2. Analyze the Problem

- Identify input/output format from `input_description` and `output_description`
- Study sample cases from `samples`
- Determine constraints (time/memory limits)
- Identify the algorithm or data structure needed

### 3. Write the Solution

Write the solution file in the correct directory:
- **Public**: `.nccuoj/solution/public/<problem_id>/solution.cpp` (or `.py`, `.java`, etc.)
- **Contest**: `.nccuoj/solution/contest/<contest_id>/<problem_id>/solution.cpp`

The supported languages are:

| Language   | API Name      | Notes         |
|------------|---------------|---------------|
| C          | `C`           | GCC, C17      |
| C++        | `C++`         | GCC, C++20    |
| Python     | `Python3`     | Python 3.12   |
| Java       | `Java`        | Temurin 21    |
| Go         | `Golang`      | Go 1.22       |
| JavaScript | `JavaScript`  | Node.js 20    |

**Default to C++ unless the user specifies otherwise.**

#### C/C++ Template

```cpp
#include <bits/stdc++.h>
using namespace std;

int main() {
    ios::sync_with_stdio(false);
    cin.tie(nullptr);
    // solution
    return 0;
}
```

#### Python Template

```python
import sys
input = sys.stdin.readline

def solve():
    # solution
    pass

solve()
```

### 4. Test Locally

Before submitting, verify the solution against the sample cases. Run the code with each sample input and compare to expected output.

### 5. Submit (Optional)

**Before submitting, if the user has not provided their NCCUOJ username and password, ask them for it.** Then pass the credentials directly as CLI arguments.

```bash
# Submit (problem_id is the internal numeric ID from the problem JSON's "id" field)
python $SCRIPTS/submit.py <problem_internal_id> "C++" .nccuoj/solution/public/<problem_id>/solution.cpp --username <username> --password <password>

# Check result (with --poll to wait for judging)
python $SCRIPTS/check_result.py <submission_id> --username <username> --password <password> --poll
```

Result codes: `-2` (Compile Error), `-1` (Wrong Answer), `0` (Accepted), `1` (Time Limit Exceeded), `2` (Memory Limit Exceeded), `3` (Runtime Error), `4` (System Error), `6` (Pending), `7` (Judging), `8` (Partial Accepted).

### 6. Debug if Needed

If the submission is not Accepted:

- **Wrong Answer**: Re-examine edge cases, off-by-one errors, output format
- **Time Limit Exceeded**: Optimize algorithm complexity, reduce I/O overhead
- **Runtime Error**: Check array bounds, division by zero, stack overflow
- **Compile Error**: Check the error info in submission response
- **Memory Limit Exceeded**: Reduce data structure size, avoid unnecessary copies

## Mode B: Contest Problem Solving

Contest mode mirrors public mode but all API calls require the `contest_id` parameter.

### 1. Fetch Contest Problem

Run [get_problem.py](./scripts/get_problem.py) with `--contest`. **Contest problems always require login.**

```bash
python $SCRIPTS/get_problem.py <problem_id> --contest <contest_id> --username <username> --password <password>
```

The response format is the same as public problems.

### 2–4. Analyze, Write, Test

Same as Mode A steps 2–4.

### 5. Submit to Contest

**Before submitting, if the user has not provided their NCCUOJ username and password, ask them for it.**

```bash
python $SCRIPTS/submit.py <problem_internal_id> "C++" .nccuoj/solution/contest/<contest_id>/<problem_id>/solution.cpp --username <username> --password <password> --contest <contest_id>

# Check result
python $SCRIPTS/check_result.py <submission_id> --username <username> --password <password> --poll
```

### 7. Debug if Needed

Same as Mode A step 6. Note: contest submissions **cannot be shared** while the contest is underway.

## API Reference

See [./references/api.md](./references/api.md) for full API endpoint documentation.

Related Skills

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation