openclaw-code-review-skill对 Pull Request 或代码 Diff 进行结构化审查，使用多 Agent 并行审查 + 置信度评分过滤误报。触发：/code-review、审查 PR、代码审查
Install via ClawdBot CLI:
clawdbot install cdapic/openclaw-code-review-skillGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/owner/repo/blob/<full-shaAudited Apr 16, 2026 · audit v1.0
Generated May 11, 2026
Maintainers of open source repositories can use this skill to automatically review incoming pull requests for compliance with project guidelines, bugs, and security issues. The skill filters low-confidence alerts, reducing maintainer burden while ensuring high-quality contributions.
Integrate the skill into a continuous integration (CI) pipeline to automatically block pull requests that fail structured code review checks (e.g., CLAUDE.md compliance, critical bugs, security risks). This enforces coding standards without slowing down developers.
A solo developer can submit their local code diffs to the skill for immediate feedback before committing. The structured review catches mistakes and logic errors, acting like a second pair of eyes without needing a human reviewer.
In industries like finance or healthcare, development teams must audit code changes for compliance. This skill provides traceable review documents with confidence scores, supporting audit trails and regulatory requirements.
Offer the skill as a paid add-on for existing DevOps platforms (e.g., GitHub, GitLab) on a monthly per-repository or per-user fee. Generate recurring revenue from teams that need automated structured code reviews.
License the skill for enterprise self-hosting, allowing organizations to run code reviews within their own infrastructure for compliance. Revenue comes from annual licensing and optional support contracts.
Provide the basic skill for free (limited to small PRs or basic checks) and charge for advanced features like custom rules, higher confidence thresholds, or integration with proprietary tools. Attract users with free tier, upsell premium.
💬 Integration Tip
Set up the skill to trigger automatically via webhook on new PRs, and configure your CLAUDE.md in the repository root to define project-specific rules for compliance checks.
Scored May 11, 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.