claude-handoffWrites a structured handoff package when local agent determines cloud Claude Code is needed. This is the ONLY path from local pipeline to cloud — the agent n...
Install via ClawdBot CLI:
clawdbot install stephenlthorn/claude-handoffGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated May 20, 2026
When a local agent cannot handle iOS-specific SwiftData migration to CloudKit due to stale training data, it prepares a detailed handoff package for Claude Code to implement the migration safely.
After multiple failed build attempts, the local agent documents the remaining errors, attempted fixes, and context for Claude Code to resolve stubborn compilation issues.
When the local agent's self-critique yields low confidence after maximum passes, it hands off to Claude Code for a fresh perspective and more reliable solution.
Developers can explicitly request 'hand this to Claude' when they prefer Claude Code's capabilities for a specific task, maintaining full control over quota usage.
Automatically escalates when an iOS .swift file is in scope, as the local agent is not trained on iOS frameworks, ensuring quality by routing to Claude Code.
Users never auto-invoke Claude Code; they review handoff packages and decide whether to spend Max plan quota. This prevents accidental quota burn and builds trust.
Offered as a premium feature in coding assistants, allowing seamless handoff between lightweight local agents and powerful cloud models for complex tasks.
Integrated into CI/CD pipelines to handle build failures or complex migrations with human approval, reducing developer frustration and downtime.
💬 Integration Tip
Integrate into your local agent's decision loop by checking escalation triggers (hard gates, build failures, low confidence) and writing the handoff package before user notification.
Scored May 20, 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.