Explain deterministic architecture governance reports for repository changes without implementing architecture rules in the Agent adapter.
Scanned 9/28/2026
Install to Claude Code
Skills Directorynpx -y skills add CoaseEdge/repo-governance --skill architecture-review --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Architecture Review?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/coaseedge-architecture-review)More formats (shields.io, HTML) on the badges page.
---
name: architecture-review
description: Explain deterministic architecture governance reports for repository changes without implementing architecture rules in the Agent adapter.
---
# Architecture Review
1. Run `repo-governance check --json` in the repository and preserve its schema version.
2. Read [references/playbook.md](references/playbook.md); in the source repository, use `playbooks/architecture-review.md`.
3. Explain only `architectureFindings`, `architectureGraph`, `architectureDriftFindings`, and `architectureDrift` according to the Playbook.
4. Separate deterministic conclusions and evidence from optional suggested actions, and state the capability boundary.
Do not add findings, change severity, recalculate dependency rules or health scores, resolve skipped evidence, or modify architecture files. A skipped report is not evidence of a healthy architecture.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
