Ralph Specum is a complete spec-driven development workflow that coordinates research, requirements, design, task planning, and implementation through a stable file contract and delegated sub-agents. You invoke it explicitly with `$ralph-specum` or by requesting autonomous mode. It walks you through brainstorming interviews for each phase, writes artifacts like `research.md` and `tasks.md` via specialist agents, and stops for approval unless you enable quick mode. The implementation loop reads real task files from disk, commits per-task when instructed, and supports POC-first planning with parallel work markers. It's opinionated about state shape and branch isolation, and expects you to keep a `.ralph-state.json` contract alive. Best for developers who want structured, pausable spec work with clear handoff points.

GitHub stars
340
last updated
May 19, 2026

Install

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

Installs into .claude/skills of the current project.

Files

Ralph Specum

Use this as the primary Codex surface for Ralph Specum. It carries the full reusable workflow and can handle the entire command surface directly when helper skills are not installed.

Derive RALPH_CODEX_PLUGIN_ROOT from this loaded skill: take the directory containing SKILL.md, then its parent skills directory, then the next parent. Never derive the plugin root from the project working directory.

Read These References

Sponsors

Details

Repository
github.com/tzachbon/smart-ralph
License
MIT
First seen
Jun 11, 2026

More from tzachbon/smart-ralph

All 28

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs