skills.rest
lmorchard
lmorchardCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

claude_code

Delegate coding tasks to Claude Code for repository edits and tests.

9|1|Updated Mar 14, 2026
Search Tags:#automation#refactor#coding#code-review#tests#code-editing
One-click install
npx skills add https://github.com/lmorchard/decafclaw --skill claude-code-lmorchard
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude_code
Source: https://github.com/lmorchard/decafclaw/tree/main/src/decafclaw/skills/claude_code
Command: npx skills add https://github.com/lmorchard/decafclaw --skill claude-code-lmorchard

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Delegates coding tasks to Claude Code as a subagent to read, modify, and test code within a repository, enabling end-to-end development workflows without micromanagement.

Core Features & Use Cases

  • End-to-end coding delegation: read, modify, run tests, iterate, and converge on a passing solution.
  • Context-preserving edits: maintain project structure, dependencies, and test expectations while applying changes.
  • Real-world use cases: fix bugs, add features, refactor code, write tests, or perform code reviews in a repository.

Quick Start

Describe the feature to implement and let Claude Code read, modify the codebase, run tests, and iterate until all tests pass.

Frequently Asked Questions about claude_code

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

FAQPage Schema
How do I delegate coding tasks to an AI agent for end-to-end bug fixes?▼

You can delegate bug fixes by describing the issue, allowing the agent to read the codebase, apply modifications, run tests, and iterate until all tests pass. This handles the entire development loop without micromanagement.

Can I automate code refactoring and test generation in my repository?▼

Yes, you can automate code refactoring and test generation. The agent modifies the codebase while maintaining project structure and dependencies, iterating through end-to-end development loops to converge on a passing solution.

What is the best way to perform automated code reviews on software projects?▼

The best way to perform automated code reviews is to delegate them to the agent, which reads and analyzes the repository code to provide structured results. This enables comprehensive development workflows without micromanagement.

Does the coding agent handle permission checks and cost budgeting automatically?▼

Yes, the agent handles permission checks and cost budgeting automatically while processing coding tasks. It captures diffs and provides structured results via its SessionLogger, ensuring safe and tracked repository modifications.

How do I add new features to a codebase without micromanaging the implementation?▼

To add new features without micromanaging, describe the desired functionality to the agent. It will autonomously read, modify, and test the code within your repository, converging on a passing solution end-to-end.

Related Skills

Explore More Software Engineering Skills→
lestrratlestrrat
2

claude-docs-init

Generate repository docs and CLAUDE.md for Claude Code navigation.

Community
Advanced
CornjebusCornjebus
1

github-code-review

Coordinate multi-agent code reviews for GitHub pull requests.

Community
Advanced
evanfang0054evanfang0054

requesting-code-review

Automate code review requests with detailed context for reviewers.

Community
Advanced
kkestellkkestell
1

kwork

Execute repository implementation plans with code changes, tests, and reviews.

Community
Advanced