Code-Review plugins

Interactive browser-based PR review with AI-authored narrative explain pills, GitHub-style stacked diffs, and realtime inline comment posting via gh.

1 skill

Combined code review: multi-agent analysis (code-reviewer, git-historian, silent-failure-hunter, test-analyzer, security-reviewer) + CodeRabbit CLI. GitHub PR + GitLab MR (inline threads, /rereview follow-up).

8 skills · 3 commands · 5 agents

Guided, read-only PR review for code and infrastructure in any language: scripted preprocessing and per-ecosystem static analysis run once, a discovery agent adapts the run to the repo's stack and quality gates, parallel lens agents (security, acceptance criteria, correctness, tests, polish) read a shared brief, and an issues-only report plus color-coded Mermaid diagrams are written per run.

3 skills

UX review and evidence-backed next-work and portfolio investment decisions powered by Pendo product analytics.

6 skills · 1 MCP server

Multi-specialist code reviewer: parallel correctness, security, performance, design, and testing agents with orchestrator dispatch and verification layer

7 skills · 2 commands · 8 agents

Self-review a PR before it ships — locally, in seconds, without paying for a cloud review service. Fourteen user-invokable slash commands (pr-switch, pr-review-local, pr-review-gh, pr-fix, pr-create, tib-create, tip-create, tib-ship, convert-tib-to-linear, ts-conventions, inject-wallet, feedback, implement-feedback, setup) plus a shared pr-review-engine dispatcher. Reviews fan out a multi-agent panel against the diff (correctness, error-handling, performance, security, CI, deps, React/Next, AI-SDK, Web3, accessibility, runtime-validation, skill-authoring, ...), post inline comments to GitHub when desired (never auto-approves), and apply mechanical fixes on demand. Tuned for TS/React/Vercel codebases.

15 skills · hooks

Run the reactant static analyzer on a React or Next.js codebase, triage its findings into true positives, false positives and non-issues, then write custom semantic rule packs for the team's own invariants.

2 skills

Code Review Graph MCP: tree-sitter knowledge graph tooling for impact analysis

1 MCP server

CodeGraph MCP: tree-sitter knowledge graph with symbol search, callers/callees, and impact analysis, auto-syncing on file changes (requires Node.js + npm on PATH)

1 MCP server

Design critique: argues whether the code should exist and whether this is the way to build it.

1 skill

Self-updating GitHub review cards with focused code pointers. Preview, publish, list PRs, review across repos, and link Zenhub tickets from Claude Code.

1 skill · 6 commands · hooks

Parse a review document for actionable feedback, work through items systematically, and track resolution progress.

1 skill

Review a colleague's pull request carefully and considerately from a checkout of its branch, and report a brief, read-only assessment in chat: requirements, direction, blockers, follow-ups, and questions for the author.

1 skill

Review an implementation plan against the current repository and its explicit dependencies, reporting evidence-backed blockers, required revisions, and optional improvements before work begins. Use when asked to review a plan or assess implementation readiness.

1 skill

Comprehensive PR review plugin with specialized agents for code quality, security, test coverage, and performance analysis. Works with GitHub, Azure DevOps, Bitbucket, and any git repository.

6 skills · 1 command · 4 agents · hooks

Whole-codebase performance bottleneck detection triggered from a GitHub issue or Azure DevOps work item. Analyzes latency, CPU, memory, and I/O patterns across the repository's default branch and opens a single pull request containing focused, low-risk optimizations together with an embedded performance report. Works with GitHub and Azure DevOps.

2 skills · 1 command · 6 agents · hooks

Detection-first PR review for open source: general, security, performance, testing, API compatibility, docs, supply chain, and contributor experience.

8 skills

Android/Kotlin 코드 리뷰 전문 Agent

5 skills · 1 agent

Automated resolution of pull request review threads — classifies each unresolved comment as apply, discuss, or decline, applies actionable ones as commits, replies to the rest, and posts a structured disposition report. Works with GitHub, Azure DevOps, and any git repository.

2 skills · 1 command · 1 agent · hooks

Checks each edit an agent makes against both sides of every boundary it touches, and reports what changed when the agent stops.

1 skill · 1 command · 1 MCP server · hooks

Structure and carry out code reviews with a consistent, cost-of-change-driven framework and reviewer workflows.

4 skills

Human-gated star review: Claude (the neutral primary) fans a spec/plan/PR out to N independent secondary reviewers (in-harness fable by default — disable with MULTI_REVIEW_FABLE=off — plus cross-vendor codex/gemini), adjudicates their findings, and converges — always ending at a human approval gate.

1 skill · 1 command

AI code review that catches production-breaking bugs, business logic issues, and security vulnerabilities — directly in Claude Code.

1 skill

Rewrite a pull request's commits into a coherent release story that semantic-release can publish, without changing file contents

1 skill

Triage and analyze PR review comments — classify concerns, verify claims against actual code, evaluate trade-offs

1 skill

Interactive companion that guides you through manually reviewing someone else's pull request instead of reviewing it for you. Explains the PR's scope, breaks the change into logical components, and walks through them one at a time while you form your own judgment.

1 skill

Revisão de qualidade de código para projetos Swift/SwiftUI, com feedback didático em PDF.

1 skill

Bridge headless CLI agents (Kimi Code, Codex, ...) into Claude Code with review and planning loops.

10 skills · 4 commands · 2 agents · 1 MCP server

Comprehensive PR review workflow: execute reviews, integrate Gemini suggestions, and interactively resolve issues

6 skills · 2 commands

Four-lens code review (simplicity, functionality, security, maintainability), with fresh-context local subagents or a tribunal of external AI coding harnesses, merged into one verified, deduplicated report.

1 skill · 3 commands · 4 agents