Google's Addy Osmani Releases agent-skills to Standardize AI Coding Agent Workflows

Addy Osmani, an Engineering Director at Google, has released a new open-source repository called agent-skills on GitHub. This project addresses the inconsistency of AI-generated code by packaging the workflows, quality gates, and best practices of senior software engineers into a standard set of skills for AI coding agents to follow. The framework provides seven slash commands mapped to the software development lifecycle, allowing AI agents to systematically activate specific skills based on the context. Instead of relying on fragile and ad-hoc prompts, developers can now embed standardized engineering practices directly into their agents' execution loops to maintain high code quality. As the project gains traction on GitHub Trending, it offers a foundational layer for deploying AI coding assistants in real-world, enterprise-level environments. Teams looking to adopt agent-skills should review the repository documentation to understand the environmental requirements and tool dependencies for each command.
Related tools
Recommended tools for this topic
These picks prioritize high-intent tools relevant to this topic. Some links may include partner or affiliate tracking.
Strong fit for AI, backend, and frontend readers looking for an AI-first coding workflow.
View CursorNatural next step for readers evaluating LLM adoption, APIs, and production inference.
Explore APIA strong fit for readers comparing Claude-class models, safety, and long-context workflows.
View AnthropicComparison
| Aspect | Before / Alternative | After / This |
|---|---|---|
| Workflow consistency | Highly variable, dependent on prompt quality and manual intervention | Standardized via seven predefined slash commands mapped to the lifecycle |
| Quality gates | Manual review or custom, disconnected CI pipelines | Built-in automated checks executed directly by the agent |
| Execution model | Ad-hoc execution driven by natural language prompts | Structured skill execution based on senior engineering practices |
Action Checklist
- Review the agent-skills repository on GitHub Analyze how the seven slash commands map to your team's existing development workflow
- Verify environment dependencies Ensure your target runtime environment has the necessary toolsets required by the skills
- Integrate commands into your AI agent pipeline Configure your custom AI agents or IDE extensions to trigger these standardized skill packages
Source: GitHub Trending
This page summarizes the original source. Check the source for full details.


