ask-claude
Delegate a task to Claude Code CLI and immediately report the result back in chat. Supports persistent sessions with full context memory. Safe execution: no data exfiltration, no external calls, file operations confined to workspace. Use when the user asks to run Claude, delegate a coding task, continue a previous Claude session, or any task benefiting from Claude Code's tools (file editing, code analysis, bash, etc.).
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/0xmanel/ask-claudeWhat This Skill Does
The ask-claude skill is a powerful integration that brings the capabilities of the Claude Code CLI directly into your OpenClaw workflow. It enables you to delegate complex coding tasks—such as file refactoring, deep codebase analysis, or executing bash commands—to Claude, with results returned seamlessly into your current chat context. The skill leverages persistent session management, meaning Claude remembers previous edits, file scans, and project context as long as you work within the same directory. By using the run-claude.sh wrapper, the tool maintains strict adherence to your specified workspace, ensuring that file operations are confined entirely to the directories you choose. It is designed to act as an autonomous agent that understands your project structure, allowing for complex multi-step development cycles without manual intervention for every single step.
Installation
To integrate this skill into your environment, use the OpenClaw management CLI. Run the following command in your terminal:
clawhub install openclaw/skills/skills/0xmanel/ask-claude
Ensure you have the Claude Code CLI installed in your system environment, as the skill acts as a bridge for that executable. Verify your workspace paths before the first execution to ensure proper file system access.
Use Cases
This skill is perfect for developers who need to perform bulk code refactoring, resolve complex build errors, or analyze legacy codebases. It is particularly effective for 'pair programming' scenarios where you need an AI to explore a directory, identify bugs, and implement fixes while maintaining state across multiple turns. It is also excellent for automating routine shell-based tasks that require contextual awareness of local files.
Example Prompts
- "Ask Claude to look at the current directory and refactor all function components to use arrow functions, then update the tests accordingly."
- "Continue the work we were doing on the authentication module; can you fix the TypeScript errors you found in the last session?"
- "Start a new session in the /workdir/frontend project and identify any unused dependencies in the package.json file."
Tips & Limitations
Always prioritize the use of the synchronous shell tool; background execution is discouraged as it may interrupt the flow of the Claude Code CLI. Remember that sessions are tied to your workdir, so if you switch projects, ensure you start a fresh session to avoid context leakage. While highly efficient, this tool requires local CLI permissions to operate on your files, so ensure your target directories do not contain sensitive secrets or private keys that shouldn't be parsed by the agent.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-0xmanel-ask-claude": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution