Explore skills

Patterns and techniques for analyzing brownfield codebases. Use when onboarding to unfamiliar code, preparing for refactoring, conducting architecture reviews, or identifying technical debt.

Detect project stack from package manifests (package.json, pyproject.toml, go.mod, Cargo.toml, pubspec.yaml, CMakeLists.txt). Auto-identify frameworks, test tools, and build systems for onboarding.

The MapReduce skill enables parallel task execution across multiple AI providers or agent instances, followed by intelligent consolidation of results. This produces higher-quality outputs by levera...

Orchestrate tasks across multiple AI providers (Claude, OpenAI, Gemini, Cursor, OpenCode, Ollama). Use when delegating tasks to specialized providers, routing based on capabilities, or implementing fallback strategies.

Invoke external AI CLIs via native Task agents (Claude, Codex, Gemini, Cursor). Primary mode for multi-provider orchestration with fork-terminal fallback for auth.

Skills for orchestrating tasks across multiple AI providers and execution environments. Parent skill category containing native-invoke and related delegation patterns.

Domain vocabulary and entity relationships for {project}. Ensures consistent terminology and model understanding.

Research workflow patterns specific to {project}. Covers research agent coordination, source management, and synthesis strategies.

Custom test patterns and fixtures for {project}. Covers E2E, integration, and specialized testing requirements.

Multi-source parallel research with confidence-based synthesis.

Detect common security vulnerabilities in code. Covers OWASP patterns, SQL injection, bare excepts, shell injection. Framework-agnostic.

Spawn an AI coding agent in a new terminal (Claude, Codex, Gemini, Cursor, OpenCode, Copilot). Defaults to Claude Code if unspecified.