Multi-Agent Review Run a panel of independent reviewers on a spec or plan before execution starts. Two model tiers (fast + standard) review each of three topics in parallel. When the tiers disagree, a single reasoning-tier juror adjudicates. The verdict gates whether the next workflow step proceeds. Concrete model IDs come from the plugin manifest (Step 3); the tier names below are variables, not model names. When to invoke Command Fire after Proceeds to /multi-agent-review spec spec is written and committed writing-plans /multi-agent-review plan plan is written and committed subagent-driven-development Invocation syntax /multi-agent-review [mode] [path?] [--fast] Show more Installs 949 Repository riekelt/multi-a…t-review GitHub Stars 100 First Seen 6 days ago Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Fail
multi-agent-review
安装
npx skills add https://github.com/riekelt/multi-agent-review --skill multi-agent-review