A curated public collection of reusable Agent Skills and Claude Code agents for software development workflows.
Agent
Orchestrates dual-pipeline code review with parallel Opus and Codex reviewers, synthesis, and interactive fix delegation. Use when performing code review, reviewing changes, or checking code quality. Context: User wants to review uncommitted changes user: "Review my dirty files" assistant: "I'll use the code-reviewer…
Agent
Use when analyzing Claude Code conversation history, finding past sessions by topic, tracing how implementations evolved across conversations, or understanding session patterns. PROACTIVE for session archaeology and conversation forensics.
Agent
Use PROACTIVELY when bugs are reported or unexpected behavior occurs. Systematically investigates issues by combining git history analysis, code tracing, and root cause identification. Trigger when users mention "bug", "broken", "not working", "regression", or describe unexpected behavior.
Agent
MUST USE when searching git history to understand code evolution, find feature introductions, trace bug origins, or discover implementation patterns. Use PROACTIVELY for git log analysis, commit searches, blame investigations, and code archaeology.
Agent
MUST USE when implementing a single scoped task from an approved plan, spec, or ticket. Implements exactly that task, drives its own review loop with a reviewer subagent until the review is clean, verifies the result against the project's checks, and reports back. Does not touch work belonging to other tasks. Use…
Agent
Research and investigation specialist for both online sources and local codebases. MUST USE for researching documentation, APIs, best practices online AND deep-diving into local code. Use PROACTIVELY when you need comprehensive information from multiple sources, technology research, or cross-referencing…
Agent
Use PROACTIVELY for expert UI/UX analysis and recommendations. Trigger when implementing new UI components, designing features, completing forms, or when users report usability concerns. Offers UX guidance before implementation.
Agent
Performs Xcode builds and reports results. Handles project detection, build execution, error parsing, and returns a structured build report. Optionally installs, launches, and streams logs from the built app on a simulator or physical device.
Agent
Runs Xcode apps on simulators, physical devices, or macOS. Determines if a rebuild is needed, delegates builds to xcode-builder, then installs, launches, and optionally streams console logs. Use when asked to "run my app", "launch on device", "test on simulator", "run on Mac", or "stream logs".