skills/android__skills
1
0
Fork 0
mirror of https://github.com/android/skills.git synced 2026-09-14 20:07:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README (#28)

Browse Source 
* Update README

* Apply suggestion from @gemini-code-assist[bot]

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* Apply suggestion from @gemini-code-assist[bot]

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

---------

Co-authored-by: Jose Alcérreca <JoseAlcerreca@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Simona
2026-04-27 16:57:45 +01:00
committed by GitHub
parent 04d6e21f53
commit 640c9e3d0d
1 changed files with 11 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+11 -5
View File
@@ -1,12 +1,18 @@
## Android skills
Android skills are a dedicated repository of AI-optimised, modular instructions and resources, to
help LLMs better understand and execute specific patterns that follow the best practices and
guidance on Android development from [developer.android.com](https://developer.android.com).
**Android skills** are a dedicated repository of **AI-optimized, modular instructions** and
resources, to help LLMs better understand and execute specific patterns that follow the best
practices and guidance on Android development
from [developer.android.com](https://developer.android.com).
Android skills follow the [open-standard agent skills](https://agentskills.io/home) - markdown
files (SKILL.md) that provide a technical specification of a task, and ground LLMs with information
on specialized domains and workflows.
files (SKILL.md) that provide a technical specification of a task, and **ground LLMs** with
information on specialized domains and workflows.
Our Android skill development focuses on **use cases and workflows where evaluations show LLMs
underperform**.
We aren't prioritizing well-established areas where LLMs are already proficient, such
as basic Jetpack Compose best practices.
To learn more, read the official documentation: