# Three-phase design review (Architect → Refine → Critique)

> Use the architect-refine-critique:architect subagent to create the initial design for [target] with name=[name], then use the architect-refine-critique:refiner subagent to improve the design with name=[name], then use…

- Skill: `tools-only/three-phase-design-review-architect-refine-critique` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add tools-only/three-phase-design-review-architect-refine-critique`
- Raw SKILL.md: https://api.skillmd.com/api/skills/tools-only/three-phase-design-review-architect-refine-critique/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: tools-only (https://skillmd.com/u/tools-only)
- Updated: 2026-09-29
- Page: https://skillmd.com/skills/tools-only/three-phase-design-review-architect-refine-critique

---


# Architect-Refine-Critique

Chain three subagents sequentially from the main conversation.

## Usage

`/arc [name] [target]`

## Execution

Use the architect-refine-critique:architect subagent to create the initial design for [target] with name=[name],
then use the architect-refine-critique:refiner subagent to improve the design with name=[name],
then use the architect-refine-critique:critique subagent to challenge the design with name=[name].

After all three complete, tell the user: "Run `/arc-review [name]` to discuss findings."

Do not analyze. Do not summarize. Do not add value. Just chain and hand off.