Manages AI Agent Skills by searching, creating, and organizing multi-file skills for Claude Code.

Manages AI prompts by searching, saving, and improving them using the prompts.chat library.

Analyzes code comments for accuracy, completeness, and long-term maintainability to prevent technical debt.

Analyzes type designs for invariant strength, encapsulation quality, and enforcement effectiveness.

Audits code for silent failures, inadequate error handling, and poor fallback behavior in pull requests.

Simplifies recently modified code while preserving functionality and applying project-specific standards.

Reviews and improves Claude Code skills for effectiveness, reliability, and best practices.

Verifies TypeScript Agent SDK applications for correct configuration, SDK usage patterns, and deployment readiness.

Analyzes conversation transcripts to identify problematic coding behaviors and generates hook rules to prevent them.

Designs feature architectures by analyzing codebase patterns and providing comprehensive implementation blueprints with specific files, components, and build sequences.

Analyzes pull request test coverage to identify critical gaps and ensure adequate testing of new functionality.

Verifies Python Agent SDK applications for correct configuration, SDK best practices, and deployment readiness.

Traces execution paths through codebases to map feature implementations across architecture layers and dependencies.

Reviews code against project guidelines, detects bugs, and suggests fixes with confidence scoring.

Reviews code for bugs, security vulnerabilities, and guideline violations, reporting only high-confidence issues with actionable fixes.

Validates Claude Code plugin structure, configuration, and components for correctness and security.

Creates high-performance AI agent configurations from user requirements with expert persona design.

Fetches library documentation from Context7 and provides concise answers with code examples.

Reviews completed code against original plans and standards for quality assurance.

Enforces test-driven development by writing comprehensive tests before implementing code.

Removes dead code and duplicates using knip, depcheck, and ts-prune analysis tools.

Reviews Go code for security, concurrency, and idiomatic best practices using static analysis and git diff.

Scans code for security vulnerabilities and provides remediation guidance for OWASP Top 10 issues.

Optimizes PostgreSQL databases for performance, security, and schema design using Supabase best practices.

Creates comprehensive implementation plans for complex features and refactoring tasks.

Reviews Python code for security, type hints, PEP 8 compliance, and Pythonic best practices.

Generates codemaps and updates documentation from codebase analysis.

Reviews code for security vulnerabilities, quality issues, and performance problems with actionable fixes.

Generates, maintains, and runs end-to-end browser tests using Vercel Agent Browser and Playwright with artifact management.

Designs scalable system architectures, evaluates technical trade-offs, and recommends patterns for maintainable software.

Fixes TypeScript and build errors with minimal diffs to get builds passing quickly.

Resolves Go compilation errors, vet warnings, and linter issues with minimal, targeted code changes.

Analyzes logs and codebases to identify error patterns, correlate issues, and determine root causes.

Refactors legacy codebases and migrates outdated frameworks using safe, incremental modernization techniques.

Analyzes code directories to create comprehensive C4 code-level documentation with function signatures and dependencies.

Synthesizes code-level documentation into logical C4 components with interfaces and diagrams.