spec-manager
01Skill Claude Code
Spec-driven project iteration workflow: L1 PRD -> L2 Design -> L3 Impl -> Agent Task, with human review gates at each layer.
Make AI programming deliverable, reviewable, and traceable: L1 PRD → L2 Design → L3 Impl → Agent Task, compatible with AI coding tools such as Claude Code, Codex, and Cursor.
This repository also configures its own agents. See what spec-manager tells them →
Skill Claude Code
Spec-driven project iteration workflow: L1 PRD -> L2 Design -> L3 Impl -> Agent Task, with human review gates at each layer.
Skill Claude Code
Spec-driven project iteration workflow — L1 PRD → L2 Design → L3 Impl → Agent Task → Deploy, with human review gates at each layer. Pure local markdown storage, no MCP, no network. Use when the user invokes /spec-manager or asks for: new feature/PRD, technical design, implementation spec, agent task, iteration plan…