← ClaudeAtlas

code-reviewlisted

Multi-agent code review with learning feedback loop — reviews PRs using parallel specialized agents (style, logic, security) with confidence scoring and false-positive reduction
sliamh11/Deus · ★ 38 · Code & Development · score 83
Install: claude install-skill sliamh11/Deus
# Multi-Agent Code Review Run a multi-agent code review on the current branch's PR. Three specialized agents (style, logic, security) review in parallel, findings are confidence-scored, and dismissed findings feed back into the evolution system as negative examples for future reviews. ## Prerequisites - **Git** — must be in a git repository - **GitHub CLI** — `gh` authenticated - Current branch must have an open PR ## Instructions When the user asks for a code review or triggers this skill: ### Step 1: Validate environment ```bash git rev-parse --is-inside-work-tree # Must be in a repo gh auth status # Must be authenticated ``` Get the current branch and find the open PR: ```bash BRANCH=$(git branch --show-current) gh pr list --head "$BRANCH" --state open --json number,title,baseRefName ``` If no PR exists, ask the user if they want to create one first. Do NOT proceed without a PR. ### Step 2: Check eligibility Skip review if: - PR is a draft (`gh pr view <number> --json isDraft`) - PR has zero code changes (only docs/config) - This exact commit SHA was already reviewed (check `resources/review-history.log` if it exists) ### Step 3: Gather context Collect all inputs the review agents will need: ```bash # Get the unified diff gh pr diff <number> # Get file list and stats gh pr view <number> --json files,additions,deletions # Get PR description for intent context gh pr view <number> --json body ``` Also load: 1. **CLAUDE.md files** from