Browse Skills

PR Review batches open pull requests in order of complexity, checks merge readiness (conflicts, CLA, reviews), reads diffs, and asks for explicit approval before merging. It also posts comments on blocked PRs.

PR Triage audits open pull requests, flags risks, and helps choose which PRs need deeper review. It can draft and post review comments, with language handling for French or English.

Repo Recap generates a structured Markdown summary of a repository's open pull requests, issues, and recent releases, ready to share with a team. Use it to quickly get an executive overview of project activity and risk areas.

RTK TDD enforces a Red-Green-Refactor test-driven development workflow for Rust projects, auto-triggering on implementation, testing, refactoring, and bug fixing tasks. It provides Rust-idiomatic testing patterns using anyhow/thiserror, cfg(test), and Arrange-Act-Assert.

RTK Triage orchestrates issue and PR triage, then cross-references the data to detect overlapping PRs, security gaps, P0 bugs without PRs, and internal conflicts, saving a report to claudedocs.

Rust Design Patterns documents idiomatic Rust patterns (Newtype, Builder, State Machine, Trait Object, RAII, Strategy, Extension Trait) for RTK's CLI filter modules. Use when designing new modules or refactoring existing filter code.

Security Guardian performs comprehensive security analysis for RTK CLI, focusing on command injection, shell escaping, hook security, and malicious input handling. Use it before release or after security-sensitive code changes.

Ship automates the complete release cycle for RTK: build verification, version bump, changelog update, git tag, and push to trigger CI/CD. Use it before tagging a new version to ensure quality checks pass and releases are safe.

TDD Rust guides Red-Green-Refactor development of RTK filters in Rust, using real command fixtures, token savings assertions, and insta snapshot tests. Use it when implementing new filter commands to enforce quality and output stability.

Agent Builder provides a framework for designing and building AI agents for any domain, from customer service to research and operations. Use it when asked to create an agent, build an assistant, or understand agentic patterns.

Code Review performs thorough code reviews covering security, performance, and maintainability. Use it when asked to review code, check for bugs, or audit a codebase.

MCP Builder guides development of Model Context Protocol servers that give Claude new tools, resources, and external service integrations. Use it to create MCP servers in Python or TypeScript and register them with Claude.