Agent Skills Hub

moonbit-refactoring

Refactor MoonBit code for idiomatic style: minimize public APIs, implement methods, leverage pattern matching with views, and enforce high test coverage for maintainable MoonBit projects.

analyze-project

Analyze project codebases to generate architecture documentation, coding standards, and development practices for AI onboarding.

research-review

Get deep, critical, NeurIPS/ICML-style peer reviews of your research, paper drafts, and experimental setups using external LLMs via Codex MCP.

vibe-agents

Generate AGENTS.md and AI configuration files (Cursor, Claude, Gemini, Copilot) for your project to streamline your vibe-coding workflow and maintain context across sessions.

test-generator

Automated generation of structured, production-ready pytest test suites for Python functions and classes.

commit-messages

Generate consistent, Conventional Commits-compliant messages directly from your staged git diffs.

metacognition

Enforces structured self-assessment checkpoints to validate approach, mitigate risks, and ensure quality before, during, and after task execution.

paper-writing

Full-stack automated paper writing pipeline from research narrative to polished LaTeX/PDF.

clean-code

Pragmatic AI-assisted coding standards focused on clean code, simplicity, and maintainability. Enforces best practices like SRP, DRY, and KISS to prevent over-engineering.

refactoring-patterns

Safely refactor code to improve structure and maintainability while preserving behavior through TDD cycles and automated test verification.

subagent-driven-development

Execute implementation plans using isolated subagents for each task, featuring a rigorous two-stage review process for spec compliance and code quality.

sync-docs

Synchronize project documentation with codebase changes. Detect stale docs, version mismatches, missing exports, and update the CHANGELOG automatically.