MCP App StoreMCP App Store
from icpc-problem-creator.skill28
Creates complete, locally-testable ICPC-style problem workspaces: statement, generators, validators, checkers, solutions, and wrong-solution suites driven by co
This skill coordinates creating or completing an ICPC-style problem workspace. It guides a main agent to define the problem architecture, produce a clear statement, author generators, validators, checkers/interactors, reference solutions, and compile a suite of targeted wrong solutions and test cases so the repository's scripts/run-all-tests.ps1 can validate the problem end-to-end. It describes a parallel workflow where the main agent delegates validator, solution/tutorial, and wrong-solution generation to sub-agents and integrates their outputs.
Use this skill when you need to turn a problem idea into a full, verifiable contest workspace (local OJ), or to repair/integrate missing pieces of an existing problem (statement, config.json, generators, checkers, solutions, tests). Ideal for authors preparing contest problems and for maintainers validating that a workspace runs under the project's test flow.
Best used with agents that can run shell commands, edit files, and spawn sub-agents (e.g., agents supporting execute, edit, agent orchestration).
ICPC Problem Creator is a skill for generating complete ICPC-style competitive programming problem workspaces including statements, generators, validators, checkers, solutions, and wrong-solution suites. The SKILL.md is exceptionally detailed and well-structured, written primarily in Chinese. It uses a main-agent + 3 sub-agent parallel architecture. All 4 bundled scripts are PowerShell (.ps1), which could not be run in the audit environment (Linux, no pwsh). No security concerns found — no hardcoded credentials, no network calls, no destructive commands, no exfiltration. Scripts are clean build/test tooling for competitive programming. The skill is niche (ICPC problem authoring) limiting its audience.
powershellWell-crafted domain-specific skill. Security is clean — no issues detected. Architecture is strong with clear separation of concerns, frontmatter, sub-skills, and config-driven workflow. Code quality is high with proper error handling, validation, and structured output. Main limitations: niche audience (ICPC/competitive programming problem setters), PowerShell dependency, and Chinese-language documentation. Scripts are build/test automation tools, not security risks.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
Readwise Reader Document Management
Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Junshi — Research Advisor
Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
ezBookkeeping API Tools
Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi
Feishu Voice Sender
Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.