Agent skills for OpenAI Agents SDK

Code refactoring patterns and techniques for improving code quality without changing behavior.

Use Gemini CLI as a second-opinion / large-context research assistant on the current repo.

Conducts systematic, high-quality code reviews using standardized checklists and severity-based feedback prefixes.

Augments human code review by summarizing changes, surfacing key review questions, assessing test coverage, and identifying low-risk…

Change size guidance (800 lines)

Context-aware routing to code review guidelines.

Review code changes following HMIS project standards.

6-agent parallel code review orchestration covering architecture, security, performance, testing, quality, and documentation dimensions…

General-purpose code review checklist. Use when reviewing any code change without a narrower specialization. Complements security-review…

Full review lifecycle — request reviews, handle feedback with technical rigor, and complete branch integration.

Agent skill for code-review-swarm - invoke with $agent-code-review-swarm

Test authoring guidance

Searches GitHub for existing implementations, libraries, or patterns.

Refactors and cleans up codebases to improve readability and maintainability without altering functional behavior.

Refactors and simplifies code by removing redundant abstractions, reducing complexity, and eliminating duplication in recent changes.

Detect AI-generated code patterns ("slop") in PHP/Laravel and TypeScript/React source — comment narration, generic naming, premature…

Automated detection of code smells and anti-patterns to identify refactoring opportunities

Code quality standards and style guide for reviewing pull requests

Transfer code between files with line-based precision.

Review representative Code2Skill main flows for closure / Lightweight review of whether the representative Code2Skill main processes are…

Performs deep, multi-agent codebase audits across tech stacks to uncover hidden bugs, architecture flaws, and security risks.