Architect Refine Critique

ntcoding/architect-refine-critique

Three-phase design review. Chain architect → refiner → critique subagents. Triggers on: 'design review', 'architecture review', '/arc', system design proposals, significant refactoring decisions, new service or module design.

6k tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

331

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/NTCoding/claude-skillz --skill architect-refine-critique

The instruction itself

3 sections, as written by the author

Architect-Refine-Critique

Chain three subagents sequentially from the main conversation.

Usage

/arc [name] [target]

Execution

Use the architect subagent to create the initial design for [target] with name=[name],

then use the refiner subagent to improve the design with name=[name],

then use the 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.

How to use it

Copy the folder

Take ntcoding/architect-refine-critique from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.