skills.rest
eddielueng
eddieluengCOMMUNITY
Explore all skills by this author →
GitHub

claude-code

Orchestrate Anthropic's Claude Code CLI for coding, refactoring, and PR-review tasks.

1|Updated Apr 14, 2026
Search Tags:#automation#claude-code#code-review#structured-output#code-refactoring#coding-agent#tmux-orchestration
One-click install
npx skills add https://github.com/eddielueng/hermes-agent-zh --skill claude-code-eddielueng
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude-code
Source: https://github.com/eddielueng/hermes-agent-zh/tree/main/skills/autonomous-ai-agents/claude-code
Command: npx skills add https://github.com/eddielueng/hermes-agent-zh --skill claude-code-eddielueng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of slow, error-prone coding work by letting you delegate implementation, refactoring, and review tasks to Claude Code’s autonomous CLI workflow instead of writing everything by hand.

Core Features & Use Cases

  • One-shot coding in Print Mode (-p): Run non-interactive tasks that return results immediately for automation and repeatable changes.
  • Interactive multi-turn coding via PTY/tmux: Keep a live REPL session for iterative refactor → review → fix → test cycles.
  • Structured/streamed outputs and session control: Produce JSON/streaming results, resume sessions by ID, and manage cost/turn limits for reliable orchestration.

Quick Start

Ask the assistant to run Claude Code in print mode to refactor a specific module with a bounded number of turns and explicit file access permissions.

Frequently Asked Questions about claude-code

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

FAQPage Schema
How do I automate code refactoring using a CLI coding agent?▼

Automate code refactoring by running Claude Code in non-interactive print mode (-p), which executes tasks immediately and returns results for repeatable, automated changes within your project directory.

Can I run an interactive coding session for iterative bug fixing?▼

Yes, you can run an interactive coding session by orchestrating Claude Code through a tmux or PTY connection, maintaining a live REPL for iterative refactor, review, fix, and test cycles.

How does structured output work when orchestrating a coding agent for CI workflows?▼

Structured output works by enabling JSON or stream-JSON modes in Claude Code, producing machine-readable results that allow automated CI-style workflows to reliably parse and handle coding agent responses.

What is the best way to control costs when delegating coding tasks to an autonomous agent?▼

Control autonomous agent costs by configuring explicit max-turns and budget limits before delegating coding tasks, ensuring the CLI agent stops after reaching defined resource boundaries during execution.

Do I need tmux to delegate PR review tasks to Claude Code?▼

You do not need tmux for one-shot PR review tasks; non-interactive print mode handles them directly. Tmux is only required for interactive multi-turn coding sessions that require live dialogue handling.

Can I resume an interrupted coding agent session by ID?▼

Yes, you can resume an interrupted coding agent session by referencing its unique session ID, allowing you to continue iterative code review and development workflows without losing previous context.

Related Skills

Explore More Software Engineering Skills→
whd4whd4

setup-gbrain

Install the gbrain CLI and initialize a local PG Lite or Supabase brain on macOS.

Community
Advanced
flutterflutter
178.3k

dart-log-failure-parser

Parse Dart and Flutter test logs to detect and summarize failure patterns.

Official
Intermediate
26mitch2626mitch26

land-and-deploy

Merge pull requests, deploy changes, and verify production health via CI/CD pipelines.

Community
Advanced
RDCrystalLabRDCrystalLab

tmux-fork

Launch parallel terminal sessions by creating tmux windows for commands and AI coding agents.

Official
Intermediate