Stats
Actions
Tags
From fabrik
Conducts code reviews on git diffs using two competing subagents that inspect architecture and implementation. Surfaces consensus issues plus serious solo findings like bugs or security flaws before commits.
How this skill is triggered — by the user, by Claude, or both
Slash command
/fabrik:code-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Always start by inspecting the changes. If you're on the `main` git branch, typically the (staged) git diff. If you're on a different branch, the committed and uncommitted changes compared to the main branch.
Always start by inspecting the changes. If you're on the main git branch, typically the (staged) git diff. If you're on a different branch, the committed and uncommitted changes compared to the main branch.
Please dispatch two subagents to carefully review the code changes. Tell them that they're competing with another agent. Make sure they look at both architecture and implementation. Tell them that whoever finds more issues wins honour and glory.
Signal-to-noise ratio matters more than completeness. When reporting back to the caller:
State clearly in the report which issues had consensus and which are single-reviewer calls promoted for seriousness.
npx claudepluginhub maragudk/fabrik --plugin fabrikReviews code changes using parallel personas for correctness, testing, maintainability, and conditional areas like security, performance, APIs. Merges into P0-P3 severity reports for PR prep and iterative feedback.
Dispatches two competing reviewers to critique code diffs independently, challenge findings adversarially, and produce high-signal reports of vetted issues. Use for rigorous reviews needing second opinions before commits.
Performs multi-agent code review of current git branch against main: detects bugs via specialist agents, verifies findings, ranks severity, generates persistent report before push/merge.