Ralph Specum Research

This is the research phase coordinator for Ralph Specum, a spec-driven development workflow. It kicks in when you explicitly invoke it or ask Ralph to run research. The skill itself doesn't do the analysis work. Instead, it resolves which spec you're working on, gathers context from your codebase and progress notes, runs an optional brainstorming interview, then delegates the actual research generation to a sub-agent. You get a research.md file that covers patterns, constraints, risks, and verification notes. By default it stops and waits for your approval before moving to requirements, unless you use quick mode. It's opinionated about file structure and state management, which is helpful if you're already in the Ralph ecosystem but means there's a learning curve upfront.

Install to Claude Code

npx -y skills add tzachbon/smart-ralph --skill ralph-specum-research --agent claude-code