This skill helps an AI agent take one issue and turn it into working code. The agent writes a failing test first, then makes it pass, and finally cleans up the code. Each step is saved as a separate commit. The agent also closes the issue automatically.
Anyone who wants a task done from start to finish can use it. The agent picks an issue, implements it, runs tests, and completes the work. Everything is done in the correct order so the code is reliable.
The skill works with tracked issues or ad-hoc tasks. It follows a strict test-first discipline. This means every change is backed by a proper test. The result is code that works and a closed issue.
Global
mkdir -p ~/.claude/skills/implementProject
mkdir -p .claude/skills/implementSource Repository
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Skill Creatoranthropics/skills
Create, test, and improve AI agent skills with easy step-by-step guidance
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly
Openclaw Secure Linux Cloudxixu-me/skills
Secure self-hosting of OpenClaw with private control and SSH tunneling