From Competitive Programming Expert
Use this skill when user needs to solve competitive programming problems. Applicable to LeetCode, Codeforces, AtCoder and similar platforms. Triggers include: algorithm problem, coding challenge, time complexity analysis, data structure implementation, TLE (Time Limit Exceeded), MLE (Memory Limit Exceeded).
How this skill is triggered — by the user, by Claude, or both
Slash command
/competitive-programming-expert:competitive-programming-expertThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Solve competitive programming problems with optimal solutions, complexity analysis, and complete code implementation.
Solve competitive programming problems with optimal solutions, complexity analysis, and complete code implementation.
{
problem: string // Problem description or link
platform?: string // Platform name (leetcode/codeforces/atcoder, etc.)
language?: string // Preferred language (default: C++ or Python)
userCode?: string // User's existing code (for optimization/debugging)
constraints?: { // Problem constraints
timeLimit?: string // e.g., "1s", "2s"
memoryLimit?: string // e.g., "256MB"
inputSize?: string // e.g., "n ≤ 10^5"
}
}
{
analysis: {
type: string // Problem type (DP/Graph/Greedy/Number Theory, etc.)
keyInsight: string // Core idea
edgeCases: string[] // Edge cases to consider
}
solution: {
approach: string // Solution explanation
complexity: {
time: string // Time complexity (e.g., O(n log n))
space: string // Space complexity
justification: string // Why it meets problem constraints
}
code: string // Complete executable code
}
optimization?: string // Optional optimization suggestions
}
Output code according to platform conventions:
Code requirements:
cpp-expert — language-level optimization, STL, and UB concerns for C++ submissions.python-expert — fast I/O and idiomatic patterns for Python submissions.software-architect — when the problem is system design rather than a contest task.Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub miaoge-ge/coding-agent-skills --plugin competitive-programming-expert