coding-agent-loopsRun long-lived AI coding agents (Codex, Claude Code) in persistent tmux sessions with Ralph retry loops and completion hooks. Use when running multi-step cod...
Install via ClawdBot CLI:
clawdbot install luke-deltadesk/coding-agent-loopsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Mar 20, 2026
Developers use this skill to implement complex features from a Product Requirements Document (PRD) with automated retry loops. It ensures the AI agent persists through failures, handles multi-step coding tasks like building APIs or adding validation, and notifies upon completion via hooks, ideal for agile software teams.
Teams automate bug fixes by running AI coding agents in persistent tmux sessions with retry mechanisms. This scenario handles authentication bugs or one-file changes, allowing agents to survive restarts and retry on failures, reducing manual intervention in DevOps workflows.
Organizations run parallel AI agents on separate tasks, such as code reviews or test generation, using the parallel mode. This speeds up development cycles by handling multiple PRDs simultaneously, with completion hooks ensuring timely notifications for quality assurance teams.
Product managers and engineers automate multi-step coding workflows based on PRD checklists. The skill validates task completion via markdown, ensuring all items are checked before signaling success, streamlining project management in tech startups.
DevOps engineers integrate this skill into CI/CD pipelines to run AI agents for automated code changes. It uses persistent sessions to handle API rate limits and retries, ensuring reliable deployments and notifications in cloud-based environments.
Offer this skill as part of a SaaS platform for AI-powered coding automation, charging monthly fees based on usage tiers. Revenue comes from enterprises and developers seeking to reduce manual coding efforts and improve productivity through persistent agent loops.
Provide consulting services to help companies integrate this skill into their existing workflows, offering customization and support. Revenue is generated through project-based fees and ongoing maintenance contracts for businesses adopting AI coding agents.
Release a freemium version of the skill with basic functionality, monetizing advanced features like parallel processing or enhanced completion hooks. Revenue streams include upgrades and add-ons for teams needing higher scalability and reliability.
💬 Integration Tip
Ensure tmux is installed and configured with a stable socket path to avoid session loss, and always include the completion hook for real-time notifications in your automation scripts.
Scored Apr 19, 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.