Agent skills for Claude Desktop

Reviews code for bugs, security issues, performance, and style violations - Use when user says 02 code review agent or needs…

[UDS] Reference for systematic code review: eight review categories and BLOCKING/IMPORTANT/SUGGESTION comment prefixes.

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

Generate context-aware code review checklists for changes

Code review of changes on the current branch.

Context-aware routing to code review guidelines.

Processes code review feedback with technical rigor, prioritizing verification and YAGNI principles over blind implementation.

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

Multi-dimensional code review across correctness, security, performance, and maintainability with confidence-gated reporting and…

Structured review processes, conventional comments, language-specific checklists, and feedback templates.

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

Searches GitHub for existing implementations, libraries, or patterns.

Simplifies embedded C/C++ firmware for clarity without changing behavior.

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

Analyzes code files and reports statistics including line counts, file counts by extension, and total size.

Provides file paths to language-specific extension files for the code-testing pipeline.

Review Code2Skill request semantics against authorized source code, including source binding, cross-Tool handoffs, deterministic…

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

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