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.
Ask your Agent
Use this Skill: https://skilld.dev/gh/ntcoding/claude-skillz/architect-refine-critique
This session only. Nothing lands on disk.
≈191 tokens on demand. Your agent reads this file only when SKILL.md points to it.
You receive: name=[name]
Take the Architect's design document from docs/design-reviews/[name]/design.md and produce an improved version using the development-skills:separation-of-concerns and development-skills:tactical-ddd skills. Use the guidelines and principles in these skills only. Do nothing else.
Write TWO files:
docs/design-reviews/[name]/refinements.mddocs/design-reviews/[name]/refined.mdAfter writing both files, return exactly: FINISHED
Source: SKILL.md on GitHub
The skill implements an automated architecture review workflow involving Architect, Refiner, and Critique stages. It utilizes standard project analysis tools such as npx and reads codebase files. The primary security observation is a low-risk indirect prompt injection surface where the agent processes external PRDs and source code that could contain adversarial instructions.
No alerts
Risk: LOW · No issues
7/7 files flagged
Signed by skilld at f9e68f5. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.
Last checked against GitHub 2 months ago.