Automate parallel AI-driven reviews of Git diffs/PRs for code quality (bugs, compliance, git history), UI/UX design (Playwright testing, responsive, WCAG AA accessibility), and security (OWASP-aligned vulnerabilities) with confidence scores. Verify false positives via codebase tracing and post reports or GitHub comments.
npx claudepluginhub joaquimscosta/arkhe-claude-plugins --plugin reviewComprehensive UI/UX design review with automated browser testing via Playwright CLI. Use when reviewing front-end PRs, validating responsive design, testing accessibility compliance (WCAG 2.1 AA), or verifying visual consistency across viewports.
False positive verifier for code and security review reports. Use after generating a code-review or security-review report to independently verify findings against the actual codebase through deep tracing, framework-aware analysis, and web research. Reduces noise by confirming real issues and dismissing false positives.
Single-pass code reviewer for delegation by other workflows. Use when another agent or workflow needs to spawn a focused code review as a subtask. For full multi-agent orchestrated reviews, use /review:code-review instead.
Multi-agent code review using the Pragmatic Quality framework. Orchestrates parallel review agents (CLAUDE.md compliance, bug scanning, git history, security) with independent confidence scoring to produce high-signal findings. Use when user runs /code-review, /review:code-review, requests a "code review", "review my changes", "PR review", or mentions "review diff", "review branch".
Comprehensive UI/UX design review with live environment testing, responsive validation, accessibility compliance (WCAG 2.1 AA), and visual consistency analysis using Playwright. Use when user runs /design-review, /review:design-review, requests a "design review", "UI review", "UX audit", or mentions "review the design", "check accessibility", "responsive testing".
Security-focused code review identifying high-confidence exploitable vulnerabilities with two-axis severity/confidence scoring, OWASP 2025 alignment, per-finding Haiku verification, and false positive filtering. Optional GitHub PR posting. Use when user runs /security-review, /review:security-review, requests a "security review", "security audit", "vulnerability scan", or mentions "find vulnerabilities", "check for exploits".
Verify code-review or security-review findings for false positives using deep codebase tracing, framework-aware analysis, and web research. Produces a .verified.md report alongside the original. Use when a review report has been generated and needs independent verification, or when user runs /verify-findings, mentions "verify review", "check false positives", or "validate findings".
5つの専門エージェント(backend-reviewer, frontend-reviewer, test-reviewer, security-reviewer, ux-reviewer)がチームでコードレビューするスキル。
Perform a comprehensive code review of recent changes
Comprehensive code review with architecture, security, and PR enhancement
Quality control and workflow orchestration utilities
Reflective code review toolkit with structured analysis, blast radius analysis, domain expertise, and intelligent review orchestration
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Supercharge Claude Code with 109 specialized components — from deep reasoning and autonomous dev loops to
DDD architecture, design system enforcement, and git workflow automation. 22 agents, 32 commands, 55 skills across 13 modular plugins.
| Plugin | Description | Key Components | Docs |
|---|---|---|---|
| 🧠 Core | 6-phase SDLC pipeline with multi-agent orchestration and deep research. | deep-think-partner, deep-researcher, /develop, /research | View |
| 🤖 AI | AI engineering toolkit for production LLM apps, RAG, and prompt optimization. | ai-engineer, prompt-engineer, lyra, /improve-agent | View |
| 📝 Doc | Documentation generation with diagrams, ADRs, RFCs, and Johnny.Decimal management. | rfc-critic, adr-critic, doc-coauthoring, /diagram, /rfc | View |
| 🔍 Review | Code quality, security, and design reviews with pragmatic standards. | pragmatic-code-review, design-review, false-positive-verifier | View |
| 🧵 Stitch | Atomic UI prompt authoring and MCP-powered Google Stitch screen generation. | /prompt, /stitch-generate, generating-stitch-screens | View |
| 🔀 Git | Workflow automation with smart commits, PRs, changelogs, and Dependabot triage. | /commit, /create-pr, /changelog, dependabot-review | View |
| 📐 Design Intent | Visual React prototyping from Figma/mockups with persistent pattern memory. | design-intent-specialist, /design-intent, /save-patterns | View |
| 💻 Lang | Production-grade language-specific skills (Bash/Shell). | scripting-bash, POSIX compliance, ShellCheck | View |
| 🎭 Playwright | Browser automation via Playwright CLI for testing and screenshots. | playwright-cli, /playwright-setup | View |
| 🍃 Spring Boot | DDD with Spring Boot 4, Modulith 2.0, Security 7, and OpenTelemetry. | 10 skills: DDD, data, web-api, modulith, security, observability, testing, flyway | View |
| 🔄 Ralph | Autonomous development loop with fresh context, task sets, and memory system. | ralph-agent, /ralph, /create-prd, Hat-lite system | View |
| 🗺️ Roadmap | Product management, roadmap analysis, and solution architecture. | product-manager, system-architect, roadmap-analyst | View |
| 🔧 Devtools | Developer tooling: SOPS encryption, Claude Code environment setup, quality stack. | sops-setup, code-env-setup, quality-stack | View |
Option A: Install directly from GitHub (recommended)
/plugin marketplace add joaquimscosta/arkhe-claude-plugins
Option B: Clone and install locally
git clone https://github.com/joaquimscosta/arkhe-claude-plugins.git
/plugin marketplace add ./arkhe-claude-plugins
You can install all plugins at once:
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim