From architect-toolkit
Lead effective architecture reviews. Manage discussions, surface disagreements, build consensus, document decisions. Use when conducting reviews or running architecture forums.
How this skill is triggered — by the user, by Claude, or both
Slash command
/architect-toolkit:architecture-review-facilitationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Lead productive architecture reviews that surface concerns, build consensus, and document decisions.
Lead productive architecture reviews that surface concerns, build consensus, and document decisions.
You are facilitating architecture reviews. Create safe environment for questioning. Surface disagreements productively. Drive to decision. Read architecture proposal, review requirements, participant background.
Based on facilitation and decision-making research:
Prepare:
Start: "We're here to review [architecture]. Goal is solid decision, not agreement. All perspectives welcome."
Present: Proposer presents problem, solution, trade-offs. 15-20 minutes. No interruptions yet.
Clarify: "What questions help you understand the proposal?" Not criticism, genuine questions.
Evaluate: "What are strengths? What concerns do you have?" Go around table; every voice heard.
Resolve: Address concerns. "That's a real risk. How do we mitigate it?" Adjust design or document risk as accepted.
Decide: "Based on discussion, I'm approving this with conditions: [list]. We'll revisit risk [X] in 2 weeks."
Document: Approved, conditions, open risks, next steps. Send within 24 hours.
npx claudepluginhub sethdford/claude-skills --plugin architect-toolkitOrchestrates parallel reviews from all architecture specialist subagents, aggregates into consolidated report for full multi-perspective assessments.
Advises on architectural decisions by asking questions, surfacing trade-offs, and presenting options without executing. Use when designing features, choosing approaches, or refactoring.
Convenes parallel role-specialized agents (principal engineer, platform, integration, test, QA, security) to debate cross-domain technical decisions or audit codebases in real time. The invoking Claude acts as CEO, routing peer DMs and producing a one-page decision log.