claude-code-localCall Claude Code as a non-interactive coding agent on the same machine as OpenClaw. Use when: (1) You need to delegate coding, refactoring, or bug-fixing tas...
Install via ClawdBot CLI:
clawdbot install xxuzzwz/claude-code-localGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
$ANTHROPICAudited Apr 30, 2026 · audit v1.0
Generated May 24, 2026
A software team needs to refactor legacy code to modern standards. Use Claude Code to scan the codebase, identify deprecated patterns, and apply transformations across multiple files with automated testing.
Integrate Claude Code into the CI pipeline to automatically review pull requests. It can analyze code diff, check for bugs, style issues, and suggest improvements without human intervention.
When a bug is reported, delegate to Claude Code to locate the root cause in the codebase, propose a fix, apply the changes, and run existing tests to verify correctness.
For a large project, use Claude Code's read-only mode to generate summaries, call graphs, and dependency maps. Output can be used for architecture documentation or onboarding new developers.
Claude Code can analyze existing source files and generate unit tests for uncovered code paths, improving test coverage in a project with minimal manual effort.
Organizations integrate Claude Code into their development workflow to boost developer productivity. The orchestrator agent delegates coding tasks, reducing time spent on boilerplate and refactoring.
CI/CD platform providers can offer Claude Code as an optional service for automated code review, bug detection, and test generation, charging per analysis or subscription.
Software consulting firms use Claude Code to efficiently handle maintenance contracts for multiple clients. The tool enables them to scale code fixes and reviews without hiring additional staff.
💬 Integration Tip
Ensure claude CLI is installed and configured with appropriate permissions. Start with read-only mode and short tasks to verify behavior before scaling to full edit tasks.
Scored May 24, 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.