openclaw-coding-agent-playbookDelegate coding tasks to Codex, Claude Code, Pi, or OpenCode from bash with safe launch modes, background monitoring, and repo-isolated review workflows.
Install via ClawdBot CLI:
clawdbot install danielsinewe/openclaw-coding-agent-playbookGrade 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/user/repo.gitAudited Apr 16, 2026 · audit v1.0
Generated Apr 27, 2026
Use the skill to automatically review pull requests in a temporary directory, ensuring code quality and consistency without affecting the main project workspace.
Delegate building new features like a dark mode toggle or API error handling to an agent running in background mode, freeing the developer to focus on other tasks.
Refactor a legacy codebase by spawning a coding agent in a focused working directory, preventing unintended modifications to unrelated files and minimizing risks.
Simultaneously review multiple pull requests by spawning multiple agent instances in parallel, each in its own temporary git worktree, drastically reducing review time.
Quickly test ideas or build prototypes by running Codex in a temporary git repository, avoiding setup overhead and keeping experiments isolated.
Offer coding agents as a subscription service where developers pay a monthly fee for access to automated PR reviews, feature building, and refactoring capabilities.
Provide a basic free tier limited to simple one-shot tasks, with premium features like background agents, parallel reviews, and priority support available via paid plans.
License the skill package to enterprises for use within their own secure infrastructure, with customization and dedicated support included.
💬 Integration Tip
Ensure the required CLIs (claude, codex, opencode, pi) are installed and configured. Use background mode with PTY (except for Claude Code) for long-running tasks, and always isolate PR reviews in temp directories.
Scored Jul 8, 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.