pr-auditUse when the user wants a local review of a GitHub pull request based on its diff, risks, quality, performance, tests, and security implications.
Install via ClawdBot CLI:
clawdbot install wimi321/pr-auditGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated May 6, 2026
A developer needs a thorough review of a PR that introduces a new feature. The agent analyzes the diff for correctness, potential bugs, and adherence to coding standards, providing actionable feedback before merging.
When a PR touches sensitive areas like authentication or data handling, the agent prioritizes security vulnerabilities, checks for unsafe patterns, and recommends fixes to prevent exploits.
A PR that modifies database queries or algorithms is reviewed for performance impact. The agent identifies inefficient code, suggests optimizations, and flags potential regressions.
Junior developers submit PRs that require guidance. The agent provides constructive, specific feedback on code quality and best practices, accelerating learning without overwhelming the reviewer.
Teams pay a monthly fee to integrate the agent into their CI/CD pipeline, enabling automated reviews for unlimited PRs. Pricing tiers based on team size and review depth.
Individual developers or small teams pay per PR review, ideal for intermittent usage. Each review costs a fixed amount, with discounts for bulk reviews.
Large companies license the agent for internal use, with custom workflows and compliance checks. Includes dedicated support and SLA guarantees.
💬 Integration Tip
Integrate as a GitHub Actions step to automatically trigger reviews on PR creation or updates.
Scored May 6, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.