Run multi-agent project audits with specialized reviewer personas for pre-launch checks, UX first impressions, task-completion smoke tests, and pedantic nitpicks on websites.
Use when a project needs multi-perspective review — pre-launch audit, post-refactor check, inherited codebase assessment, or periodic health check. Dispatches parallel expert reviewer agents with persona framing.
Use when you want to see a site through fresh eyes — how different types of people experience it for the first time. Dispatches agents with varying tech sophistication who land on the site cold and report confusion, friction, and first impressions.
Use when you want to verify a site works by having agents act as real users completing common tasks — browsing, subscribing, purchasing, searching. Each agent has a goal and clicks through the real flow using browser MCP tools.
Use when you want pedantic, nitpicky, opinionated feedback on a site or project — the kind of feedback you'd get from Hacker News commenters, typography snobs, grammar pedants, and standards purists. Finds the things that professional reviewers skip because they're "too minor."
Your project is about to ship. Instead of one reviewer catching what they catch, Review Squad dispatches a panel — security analyst, UX critic, performance specialist, pedantic nitpicker — each doing deep parallel analysis and reporting back.
/plugin marketplace add 2389-research/claude-plugins
/plugin install review-squad@2389-research
| Skill | What it does | When to use it |
|---|---|---|
review-squad:experts | Expert audit panel (SEO, a11y, security, perf, etc.) | Before launch — catch what you missed |
review-squad:normies | First-time visitors across a sophistication spectrum | When you can't tell if your site makes sense to outsiders |
review-squad:regulars | Task-oriented users verifying real flows work | Smoke test signup, checkout, search — the flows that matter |
review-squad:well-actually | Pedantic nitpickers finding what pros skip | Before posting to HN — find the nits before they do |
Expert audit before launch:
User: "Run a review-squad:experts audit on my site before we go live"
Claude: I'd suggest this panel for your site:
- Security analyst — auth flows, data handling, headers
- Performance specialist — load times, bundle size, caching
- SEO reviewer — meta tags, structured data, crawlability
- Accessibility auditor — screen readers, contrast, keyboard nav
Approve this panel, or swap anyone out?
[After approval, 4 agents dispatch in parallel]
[Each returns a focused report with specific findings]
[Consolidated into a single prioritized action list]
First impressions check:
User: "Use review-squad:normies to see if people can tell what my site is about"
Claude: I'll send these visitors to your site:
- Tech-savvy developer (comfortable with jargon)
- Non-technical manager (skims, needs clear value prop)
- Skeptical senior engineer (assumes everything is overhyped)
Each lands cold on your homepage and reports: what they think it does,
where they got confused, and whether they'd explore further.
Get roasted:
User: "Hit my site with review-squad:well-actually before I post it to HN"
Claude: Dispatching the pedants — typography snobs, grammar hawks,
standards purists, and "um actually" engineers. They'll find the
things professional reviewers skip because they're too polite.
Three of the four skills (normies, regulars, well-actually) use browser MCP tools, so you'll need a dev server running for those.
If Review Squad caught something your tests didn't, a ⭐ helps us know it's landing.
Built by 2389 · Part of the Claude Code plugin marketplace
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub 2389-research/claude-plugins --plugin review-squadMCP server for agent social media platform - enables AI agents to interact in team-based discussions
Iterative artifact refinement with investigation-first judge board - constructs problem-specific judges that read the code, understand the problem, and propose evidence-based improvements
Tiered-delegation execution where Sonnet plans a spec into sprints, a cheap Haiku agent builds and self-verifies against the gate, and a scoped Sonnet fix runs only on failure - benchmarked ~64% cheaper than Opus at equal quality.
Agentic binary reverse engineering for ELF binaries on ARM64, ARMv7, x86_64 - hypothesis-driven analysis with radare2, Ghidra, GDB, QEMU
A comprehensive MCP server that provides Claude with private journaling, semantic search, resources, and guided prompts for reflection and learning
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification