android/skills

Android skills is a repository of AI-optimized modular instructions designed to help agents understand and execute Android development patterns that follow...

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 33 minutes ago
Added to GitGenius on September 1st, 2026
Created on March 16th, 2026
Open Issues & Pull Requests: 33 (+0)
GitHub issues: Enabled
Number of forks: 475
Total Stargazers: 7,228 (+0)
Total Subscribers: 84 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 2.1 days
Mean response time: 6.2 days
90th percentile: 22.0 days
Tracked items: 129

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Only 20% of issues opened in the past year have been closed. Three people close 91% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 32
New in 7 days: 13
Closed in 7 days: 16
Avg open age: 74 days
Stale 30+ days: 20
Stale 90+ days: 12

Recent activity

Opened in 7 days: 13
Closed in 7 days: 16
Comments in 7 days: 3
Events in 7 days: 36

Top labels

  • enhancement (60)
  • bug (55)
  • new skill request (2)

Most active issues this week

Detailed Description

Android skills is a repository of AI-optimized modular instructions designed to help agents understand and execute Android development patterns that follow best practices from developer.android.com.

The repository addresses the problem that large language models underperform on certain Android development use cases and workflows. It solves this by providing markdown-based skill files that follow an open standard for agent skills, grounding LLMs with specialized domain knowledge and step-by-step instructions for Android-specific tasks. Skills are installed via Android CLI into agent directories and activate automatically when an agent receives a related task prompt.

Developers should adopt this tool if they use AI agents for Android development and want those agents to follow official Android best practices. The skills are particularly valuable for workflows where LLMs typically struggle, rather than well-established areas where they already perform well. Installation is straightforward through Android CLI, with options to install individual skills or all available skills, and to target specific agents or projects. The tool integrates with multiple agents including Gemini and Antigravity, and works within Android Studio.

The project maintains a focused scope by deliberately avoiding areas where LLMs are already proficient, concentrating instead on high-value use cases identified through evaluation. Public contributions are not accepted, with feedback and requests handled through GitHub issues. The repository includes a disclaimer that AI can make mistakes, requiring users to verify results independently.