Stats
Actions
Tags
From smart
Review implemented code against the plan with 3 parallel analysis agents
How this command is triggered — by the user, by Claude, or both
Slash command
/smart:review file paths or feature name to reviewThis command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
# Review Command The user has invoked `/review` with the following input: **Arguments:** $ARGUMENTS ## Instructions 1. Read `skills/review/SKILL.md` to load the full review process. 2. If `$ARGUMENTS` is empty, use `git diff` to identify recently changed files as the review scope. 3. Otherwise, treat `$ARGUMENTS` as the scope of the review and follow the process in SKILL.md exactly.
The user has invoked /review with the following input:
Arguments: $ARGUMENTS
skills/review/SKILL.md to load the full review process.$ARGUMENTS is empty, use git diff to identify recently changed files as the review scope.$ARGUMENTS as the scope of the review and follow the process in SKILL.md exactly.npx claudepluginhub alexgim961101/claude-plugins --plugin smart/reviewReviews staged changes or recent commits across five axes—correctness, readability, architecture, security, performance—producing categorized findings with file:line references and fixes.
/reviewRuns Codex code review on local git state (working tree or vs base branch). Supports --wait/--background, --base <ref>, --scope auto|working-tree|branch.
/reviewInvokes multiple external AI CLIs (Gemini, Claude, Codex, etc.) to independently review a phase plan and produces a structured REVIEWS.md with per-reviewer feedback.
/reviewRuns an enhanced multi-LLM PR review with inline comments, checking availability of local and API-based providers for cross-model escalation.
/reviewReviews HTML file for design anti-patterns, principles violations, and accessibility issues. Generates markdown report with status tables and recommendations.
/reviewReviews specified code scope via four specialists (quality, security, performance, architecture), producing summary, detailed findings, refactoring suggestions, prioritized action plan.