27 Android skills for AI agents (Claude Code, Codex, Cursor). Fixes Supabase auth, Hilt errors, design inconsistency, kapt→ksp, missing UiState states. Reduced my token bills 5×. FitGenZ AI shipped in 18 days.
<p align="center"> <a href="https://github.com/piyushverma0/android-agent-skills/stargazers"> <img src="https://img.shields.io/github/stars/piyushverma0/android-agent-skills?style=flat-square&color=22c55e" alt="Stars"/> </a> <img src="https://img.shields.io/badge/skills-27-3b82f6?style=flat-square" alt="27 skills"/> <img src="https://img.shields.io/badge/rules-180%2B-f59e0b?style=flat-square" alt="180+ rules"/> <img src="https://img.shields.io/badge/bills_reduced-5×-ef4444?style=flat-square" alt="5x less bills"/> <img src="https://img.shields.io/badge/Kotlin-2.0%2B-7F52FF?style=flat-square&logo=kotlin" alt="Kotlin 2.0+"/> <img src="https://img.shields.io/badge/license-MIT-8b5cf6?style=flat-square" alt="MIT"/> </p>I was getting 5× token bills every month building Android apps with AI agents.
Same errors. Same Supabase crashes. Same broken screens.
I fixed it by writing these 27 skills.
Now my bills dropped 5×. FitGenZ AI shipped in 18 days.
I'm Piyush. I build Android apps solo using AI agents — Claude Code, Codex, Cursor, Antigravity.
My first serious Android project was Sarkari Khozo — an app that helps Indians find government schemes, exam notifications, and jobs. The idea was solid. The execution was a nightmare.
Every AI session started the same way. I'd describe what I wanted. The agent would start building. And within 20 minutes, I was correcting the same mistakes I'd corrected the session before.
Here's exactly what was happening to my token budget:
Problem 1: Every screen looked different from the last one
The agent had no memory of how I built screen 1 when it started screen 2. Different spacing on every card. fontSize = 18.sp here, fontSize = 20.sp there. Color(0xFF1A1A2E) in one file, Color(0xFF161622)
Mine your Claude Code and Codex logs into a local you.md agent profile.
Local-first AI coding agent for VS Code & Cursor. Ollama, LM Studio & your inference fleet. Cursor-grade agent UX — offline, private, zero token cost.
A self-improving skill for AI coding agents (Claude Code, Cursor, AGENTS.md): recognize a hard-won golden path in a session and harvest it into a reusable skill/rule for next time.
Second brain for Forward Deployed Engineers. Engagement memory + 35 skills across 6 domains, all behind one @fde... Works with any AI coding agent.
Game-development Agent Skills for AI coding agents: install once and a master router loads the right skill for your engine and task. 66 original, version-pinned skills (plus a master router) in the portable SKILL.md format that runs across Claude Code, Cursor, Codex, Copilot, Gemini CLI and more, for Godot, Unity, Unreal, web and beyond.
Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — write less code, less prose, and denser agent-to-agent handoffs (−53%, lossless in benchmarks) with no loss of quality. Works with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, Windsurf, Cline & Kiro.
Workflows from the Neura Market marketplace related to this Cursor resource