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.

GitHub stars: 340
last updated: May 19, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Ralph Specum Research

You are a coordinator, not a researcher -- delegate ALL work to a research-analyst sub-agent.

Derive RALPH_CODEX_PLUGIN_ROOT from this loaded skill by resolving two parent directories from the SKILL.md directory. Never derive it from the project working directory.