claude-code

Execute Claude Code CLI commands and capture output for summarization.

18|3|Updated Mar 28, 2026
One-click install
npx skills add https://github.com/ondrej-svec/heart-of-gold-toolkit --skill claude-code-ondrej-svec
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-code
Source: https://github.com/ondrej-svec/heart-of-gold-toolkit/tree/main/plugins/guide/skills/claude-code
Command: npx skills add https://github.com/ondrej-svec/heart-of-gold-toolkit --skill claude-code-ondrej-svec

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, and includes scripts (resource) components.

What problem does it solve?

Use this skill to run Claude Code directly, capture Claude's actual output, and summarize it back to the user.

Core Features & Use Cases

  • Run Claude Code directly via CLI and capture outputs
  • Summarize Claude's responses for clear, concise results
  • Support for common workflows like code analysis, debugging, and refactoring across repositories

Quick Start

Prompt Claude Code to run a command and return a concise summary of the output.

Frequently Asked Questions about claude-code

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run Claude Code commands and capture the exact output for summarization?

To run Claude Code commands and capture output for summarization, this Skill executes CLI tasks via the run-claude-code.sh wrapper to manage prompts, model settings, and permission modes, returning concise summaries of Claude's actual execution results.

Can I use Claude Code for code analysis and debugging across multiple repositories?

Yes, you can use Claude Code for code analysis and debugging across repositories. The Skill executes CLI tasks to capture actual outputs, supporting workflows like refactoring and debugging sessions directly from your command line interface.

Do I need Python to execute Claude Code workflows from the CLI?

Yes, you need Python3 installed to execute Claude Code workflows via this Skill. It relies on Python3 as a dependency to run the scripts that manage prompt execution, permission modes, and output formatting.

What is the best way to summarize Claude Code CLI execution results?

The best way to summarize Claude Code CLI execution results is by using the run-claude-code.sh wrapper to handle prompt management and model configuration, which captures and formats Claude's actual response into a concise summary.

Does this method support configuring permission modes for Claude Code tasks?

Yes, this method supports configuring permission modes for Claude Code tasks. The run-claude-code.sh wrapper explicitly manages permission settings alongside prompts and model selection to ensure controlled command execution and result formatting.