$ loading_
Simulate a multi-agent engineering team to review code for quality and risks.
This skill appears to be an open-source, prompt-only code review skill with no required secrets and no declared remote endpoints, indicating low overall risk. Because only a brief description is available and no README or maintenance details are provided, the assessment relies mainly on the available metadata and users should still inspect the repository before use.
The material states that no keys or environment variables are required. No API tokens, account credentials, or other sensitive authentication secrets are requested, so credential exposure and misuse risk is low.
No remote endpoints are declared, and the system flags it as prompt-only. Based on the available material, there is no evidence that user code or data is sent to third-party services.
As a prompt-only skill, the material does not indicate that it launches local processes, executes scripts, or requests additional system capabilities; based on the available facts, it does not appear to have code execution privileges.
The material does not claim file read/write, repository modification, or access to sensitive local directories. If it is only a prompt-based skill, its data exposure is typically limited to context explicitly provided by the user, with no signs of overbroad access.
The source is an open GitHub repository under Apache-2.0, publicly auditable, with some community adoption (229 stars), all of which are positive factors that lower risk. The main caveats are the missing README and unknown maintenance status, which limit transparency and ongoing maintenance visibility.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "open-code-review" yet — see the docs or source repo.
Simulate a code review team made up of a senior backend engineer, QA engineer, and architect to review the following PR diff. Provide feedback from each role, then summarize issues sorted by severity. Focus on readability, edge cases, performance, security, and maintainability. End with a merge recommendation. Code: <paste diff>
A structured code review with multi-role feedback, prioritized issues, and a merge recommendation.
Here is a recently refactored core module. Simulate a code review discussion to identify behavioral change risks, hidden bugs, compatibility issues, and testing gaps. Also specify the most important unit and integration tests to add. Code: <paste code>
A review report focused on refactoring risks, including issue analysis and recommended test coverage.
Using the perspectives of a security engineer, SRE, and senior developer, perform a joint review of this server-side code. Focus on input validation, authorization, error handling, log leakage, resource cleanup, concurrency safety, and recovery from failures. Provide concrete fixes. Code: <paste code>
A joint security and reliability review listing risks and actionable remediation suggestions.
Run multi-model reviews for code changes, PRs, and risky edits.
Review code, suggest refactors, and generate tests with AI assistance.
Review code with line-level feedback on security and quality issues.
Review code deeply across correctness, tests, security, performance, and product quality.
Review repositories in natural language for security, performance, and code quality issues
Review contract code with multi-agent AI and get verdict-driven quality insights.