Slash Command

/arc

Chains Architect, Refine, and Critique subagents for three-phase design review of [target] named [name]. Instructs to run /arc-review [name] next.

design

code-quality

npx claudepluginhub ntcoding/claude-skillz --plugin architect-refine-critique

Prompt Preview

# 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 ...

Command Content

Other plugins with /arc

/review-design

169

Reviews design documents using Product Manager, Architect, Designer, Security Design, and CTO agents. Produces approval verdict, agent feedback, blockers, suggestions, and next steps.

metaswarm

/technical_review

Invokes multiple specialized agents to review a plan's technical approach and architecture in parallel, focusing on Rails expertise and code simplicity.

compound-engineering

/evaluate

125

Reviews project architecture in background via subagent while capturing session learnings, producing architecture report and knowledge artifacts.

spectre

/arch

Performs MVP-focused architecture review for solo developers by executing /archreview with all provided arguments.

claude-commands

/architecture-review

faos-cto

Stats

Parent Repo Stars276

Parent Repo Forks38

Last CommitJan 19, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

# 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 ...

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.