dyad:multi-pr-review
Multi-Agent PR Review
This skill spawns three independent sub-agents to review code changes from different perspectives, then validates and aggregates their findings through reasoned analysis.
Overview
- Fetch PR diff and existing comments
- Spawn 3 sub-agents with specialized personas using the Task tool
- Each agent receives files in a different randomized order to reduce ordering bias
- Correctness Expert: Bugs, edge cases, control flow, security, error handling
- Code Health Expert: Dead code, duplication, complexity, meaningful comments, abstractions
- UX Wizard: User experience, consistency, accessibility, error states, delight
- Each agent reviews and classifies issues (HIGH/MEDIUM/LOW severity)
- Validate issues using reasoned analysis (not just vote counting)
- Determine merge verdict based on confirmed issues
- Filter out issues already commented on (deduplication)
- Post findings: summary with verdict + inline comments for HIGH/MEDIUM issues
Workflow
More from dyad-sh/dyad
remember-learnings
Review the current session for errors, issues, snags, and hard-won knowledge, then update the rules/ files (or AGENTS.md if no suitable rule file exists) with actionable learnings.
32dyad:plan-to-issue
Create a plan collaboratively with the user, then convert the approved plan into a GitHub issue.
27dyad:feedback-to-issues
Turn customer feedback (usually an email) into discrete GitHub issues. Checks for duplicates, proposes new issues for approval, creates them, and drafts a reply email.
26dyad:deflake-e2e-recent-commits
Automatically gather flaky E2E tests from recent CI runs on the main branch and from recent PRs by wwwillchen/keppo-bot/dyad-assistant, then deflake them.
26dyad:pr-push
Commit any uncommitted changes, run lint checks, fix any issues, and push the current branch.
26dyad:lint
Run pre-commit checks including formatting, linting, and type-checking, and fix any errors.
26