No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by new-silvermoon · Agent Tool · ★ 917
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is awesome-android-agent-skills safe to install? View the security audit →
Awesome Android Agent Skills Welcome to Awesome Android Agent Skills, a repository of specialized "brains" for your AI coding assistants. This project provides a suite of Agent Skills designed to supercharge GitHub Copilot, Claude, Google Gemini, Cursor and other agentic AI tools with expert knowledge of modern Android development. What are Agent Skills? Agent Skills are a standardized way to package capabilities, instructions, and best practices for AI agents. Instead of pasting the same prompt repeatedly ("How do I implement MVVM?", "Check this for accessibility"), you install these skills into your agent's environment. When an agent detects you are working on a relevant task (e.g., "Create a verified repository"), it automatically loads the expert instructions from the corresponding file. This ensures: Consistency: The agent always follows your defined architecture. Accuracy: It uses the latest 2025 best practices (Compose, Hilt, Room). Efficiency: No need for long context-stuffing prompts. Learn more at agentskills.io. How Skills Work Together Skills reference each other and build on shared context. The file is the foundation — every AI agent
| Stars | 917 |
| Forks | 89 |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 67.5667523729117/100 |
| Open Issues | 1 |
| Last Updated | 2026-07-27 |
| Created | 2024-02-06 |
| Platforms | claude-code, gemini |
| Est. Tokens | ~9k |
These tools work well together with awesome-android-agent-skills for enhanced workflows:
Looking for a awesome-android-agent-skills alternative? If you're comparing awesome-android-agent-skills with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and
General-purpose Playwright automation for coding agents
🎭 AI 写小说：从零生成 10-50 章完整中文小说，三层问答 · 创作记忆 · 悬念钩子 · 自动校验，长篇网文连载皆宜｜开源免费，适配主流 coding agent｜AI novel writing skill
This repository contains a collection of Agent Skills developed by GudaStudio, enabling seamless collaboration
Claude Code Skill Factory — A powerful open-source toolkit for building and deploying production-ready Claude
A collection of Agent skills and Claude Code plugins for HashiCorp products.
Explore other popular agent tool tools:
awesome-android-agent-skills is A collection of standardized Agent Skills to teach GitHub Copilot, Claude, Gemini and Cursor about modern Android development (Kotlin, Jetpack Compose, etc.).. It is categorized as a Agent Tool with 917 GitHub stars.
You can find installation instructions and usage details in the awesome-android-agent-skills GitHub repository at github.com/new-silvermoon/awesome-android-agent-skills. The project has 917 stars and 89 forks, indicating an active community.
awesome-android-agent-skills is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to awesome-android-agent-skills on Agent Skills Hub include raptor, playwright-skill, chinese-novelist-skill. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: