Multi-model peer review layer using local LLMs via Ollama to catch errors in cloud model output. Fan-out critiques to 2-3 local models, aggregate flags, synthesize consensus. Use when: validating trade analyses, reviewing agent output quality, testing local model accuracy, checking any high-stakes Claude output before publishing or acting on it. Don't use when: simple fact-checking (just search the web), tasks that don't benefit from multi-model consensus, time-critical decisions where 60s latency is unacceptable, reviewing trivial or low-stakes content. Negative examples: - "Check if this date is correct" β No. Just web search it. - "Review my grocery list" β No. Not worth multi-model inference. - "I need this answer in 5 seconds" β No. Peer review adds 30-60s latency. Edge cases: - Short text (<50 words) β Models may not find meaningful issues. Consider skipping. - Highly technical domain β Local models may lack domain knowledge. Weight flags lower. - Creative writing β Factual r
Data sourced from ClawHub. View on ClawSkills
What Peer Review can do for your AI workflow
Multi-model peer review layer directly from your Claude conversation
Works across Claude, Cursor, OpenClaw β install once, use everywhere
One-command installation β no complex setup required
Combine with other skills to build powerful multi-step AI workflows
Try these prompts with your AI agent after installing Peer Review
Help me get started with Peer Review
Explains what Peer Review does, walks through the setup, and runs a quick demo based on your current project
Use Peer Review to multi-model peer review layer using local LLMs via Ollama to catch ...
Invokes Peer Review with the right parameters and returns the result directly in the conversation
What can I do with Peer Review in my design & creative workflow?
Lists the top use cases for Peer Review, with example commands for each scenario
Guides & tutorials for AI skills
The 7 AI Skills Every Software Developer Should Have Installed in 2026
After testing dozens of developer-focused AI skills, these are the seven that have proven genuinely useful across different tech stacks and workflows β not just impressive demos, but tools that hold up under daily use.
MCP Skills vs Native Claude Tools: What's the Difference and When to Use Each
Claude comes with built-in capabilities, but MCP skills extend it in ways the base model can't. Here's a clear breakdown of what each type of tool is good for, with real examples of when to reach for a skill versus relying on Claude's native abilities.
Peer Review extends your AI assistant with the ability to multi-model peer review layer using local LLMs via Ollama to catch errors in cloud model output. Fan-out critiques to 2-3 local models, aggregate flags, synthesize consensus. Use when: validating trade analyses, reviewing agent output quality, testing local model accuracy, checking any high-stakes Claude output before publishing or acting on it. Don't use when: simple fact-checking (just search the web), tasks that don't benefit from multi-model consensus, time-critical decisions where 60s latency is unacceptable, reviewing trivial or low-stakes content. Negative examples: - "Check if this date is correct" β No. Just web search it. - "Review my grocery list" β No. Not worth multi-model inference. - "I need this answer in 5 seconds" β No. Peer review adds 30-60s latency. Edge cases: - Short text (<50 words) β Models may not find meaningful issues. Consider skipping. - Highly technical domain β Local models may lack domain knowledge. Weight flags lower. - Creative writing β Factual r. Rather than leaving your conversation to handle this manually, you can ask your Claude agent directly β and it will take care of the task end-to-end, using Peer Review as its underlying capability.
Peer Review works across Claude, Cursor, OpenClaw through the Model Context Protocol (MCP) β an open standard that lets AI clients share tools and skills without lock-in. Because MCP is platform-agnostic by design, you install Peer Review once and it becomes available across all your AI clients. Whether you're working in Claude for focused sessions or Cursor for integrated workflows, the skill behaves consistently.
Peer Review installs like any other MCP skill: drop the folder into `~/.claude/skills/peer-review/` for global access, or `.claude/skills/peer-review/` to keep it scoped to one project. After a quick restart of Claude, you can trigger it explicitly with `/peer-review`, or let the AI decide when it's the right tool for your request.
Peer Review has 907 installs and is part of the growing Design & Creative skill ecosystem on DiscoverAISkills. Like all skills on DiscoverAISkills, it is free to install and use. The broader AI skills ecosystem continues to expand as developers contribute new capabilities across categories like developer tools, data analysis, writing, automation, and more.
Place the skill folder at ~/.claude/skills/peer-review/ for personal use (all projects), or .claude/skills/peer-review/ for project-specific use. Restart your AI client, then invoke with /peer-review or let the AI discover it automatically.
Peer Review supports Claude, Cursor, OpenClaw. It integrates seamlessly with these AI platforms to extend their capabilities.
Peer Review is free to install. Check the repository for licensing information.
Multi-model peer review layer using local LLMs via Ollama to catch errors in cloud model output. Fan-out critiques to 2-3 local models, aggregate flags, synthesize consensus. Use when: validating trade analyses, reviewing agent output quality, testing local model accuracy, checking any high-stakes Claude output before publishing or acting on it. Don't use when: simple fact-checking (just search the web), tasks that don't benefit from multi-model consensus, time-critical decisions where 60s latency is unacceptable, reviewing trivial or low-stakes content. Negative examples: - "Check if this date is correct" β No. Just web search it. - "Review my grocery list" β No. Not worth multi-model inference. - "I need this answer in 5 seconds" β No. Peer review adds 30-60s latency. Edge cases: - Short text (<50 words) β Models may not find meaningful issues. Consider skipping. - Highly technical domain β Local models may lack domain knowledge. Weight flags lower. - Creative writing β Factual r
Review Summarizer
Scrape, analyze, and summarize product reviews from multiple platforms (Amazon, Google, Yelp, TripAdvisor). Extract key insights, sentiment analysis, pros/cons, and recommendations. Use when researching products for arbitrage, creating affiliate content, or making purchasing decisions.
Peer Reviewer
AI-powered academic paper reviewer. Uses a multi-agent system (Deconstructor, Devil's Advocate, Judge) to analyze papers for logical flaws, contradictions, and empirical validity.
Review Skills on Clawdtm
Review and rate Claude Code skills. See what humans and AI agents recommend.
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install peer-reviewOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install peer-reviewβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/peer-review/π‘Extract and place the folder at the path above, then restart your agent.
Category
π¨Design & CreativeAutomate my design & creative tasks using Peer Review
Identifies repetitive steps in your workflow and sets up Peer Review to handle them automatically
Peer Review is categorized under Design & Creative. These skills help AI agents perform specialized tasks in this domain.