Agent skills for OpenAI Agents SDK

ALWAYS USE whenever asked to write, add, or generate unit tests for existing code, including one helper, function, class, or missing…

Execute codeagent-wrapper for multi-backend AI code tasks.

Techniques for analyzing existing codebases to reverse-engineer requirements and understand business logic.

Analyzes codebase using adaptive parallel Explore subagents based on task complexity.

Use PROACTIVELY when auditing code quality, running security scans, assessing technical debt, reviewing code for production readiness…

Generates comprehensive documentation explaining how a codebase works, including architecture, key components, data flow, and development…

Multi-angle codebase exploration spawning 3-5 parallel agents for code structure, data flow, architecture patterns, and health assessment.

Explore codebases with CodeGraph: symbols, calls, impact.

Scan source code and report agent-readiness metrics with actionable recommendations

Designs reverse-engineered, milestone-driven learning plans to master, debug, and modify complex Python and Go codebases efficiently.

Use when asked to audit a codebase, find DRY/YAGNI/complexity issues repo-wide, or perform periodic code quality review

Designs a target codebase structure from a shared domain and use-case model, assigning semantic ownership and choosing capability…

Evaluates a proposed or implemented codebase structure without changing it: semantic ownership, module and port boundaries, dependency…

Use Codeclew for bounded compiler- or syntax-backed code context, safe changes, multi-repository analysis, freshness checks, recovery, and…

Automates the management and evolution of autonomous AI agents on the BNB Chain using DNA-driven decision engines.

Code quality skill that provides auto-linting, formatting, and code fixes through a unified CLI interface.

Regenerate and verify game package TypeScript from .randsum.json specs

Automate Codeinterpreter tasks via Rube MCP (Composio).

Map codebase structure with parallel analysis — produces 7 documents about architecture, concerns, and conventions

This guide helps AI agents efficiently create codemods with optimal performance and consistency Quick Reference: Scaffold, Create…

CodeQL is a static analysis framework that queries code as a database.