Claude MarketplacesSubmit

Pokeclaw Android Ai Agent

aradotso/trending-skills

This is a complete on-device Android agent built around Gemma 4 and LiteRT-LM with real tool calling. It reads your screen as a UI tree, decides what to tap or type, executes the action through Android Accessibility Services, checks the result, and loops until done. No cloud calls required for local mode. The repo includes full tool definitions for tap, swipe, text input, app launching, screen reading, and messaging automation, plus the orchestrator and dispatcher. It's genuinely useful if you want to study how structured output from a local LLM can drive accessibility APIs, or if you're building auto-reply bots or task automation that stays entirely on the phone. The architecture is clean and the setup instructions are thorough.

skills.sh installs: 404
GitHub stars: 25
last updated: Jun 3, 2026

Install

$ npx -y skills add aradotso/trending-skills --skill pokeclaw-android-ai-agent --agent claude-code

Installs into .claude/skills of the current project.

Files

PokeClaw Android AI Agent

Skill by ara.so — Daily 2026 Skills collection.

PokeClaw is an open-source Android app that runs Gemma 4 entirely on-device via LiteRT-LM with native tool calling. The LLM reads the screen as a UI tree, selects tools (tap, swipe, type, open app, send message, etc.), executes them through Android Accessibility Services, observes the result, and loops until the task is complete — no cloud, no API key required for local mode.

Architecture Overview

User prompt
    │
    ▼
TaskOrchestrator          ← manages task lifecycle & session history
    │
    ▼
LLMEngine (LiteRT-LM)     ← Gemma 4 on-device, tool-call aware
    │  tool_calls[]
    ▼
ToolDispatcher            ← routes to concrete tool implementations
    │
    ├── AccessibilityTool  ← tap / swipe / long_press / input_text
    ├── AppLaunchTool      ← open_app
    ├── ScreenReaderTool   ← get_screen_info / take_screenshot
    ├── MessagingTool      ← send_message / auto_reply
    └── FinishTool         ← finish (signals task done)
         │
         ▼
    Android Accessibility Service / UI Automator

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly

Agent CaffeineSponsoredClose your lid, come back to finished work

SnugSponsoredThe clipboard manager for the AI era Promote your product hereReach 125k+ visitors monthly

WaxSponsoredBlock anything with supervision, without erasing your iPhone Promote your product hereReach 125k+ visitors monthly

knobsSponsoredSee your site on any phone, any day, in any language

Details

Repository: github.com/aradotso/trending-skills
Categories: AI & Agent Building, Mobile Development
First seen: Jun 3, 2026

Recommended

More AI & Agent Building

1

ln-310-multi-agent-validatorlevnikolaevich/claude-code-skillsUse when validating Stories, plans, or tasks through the evaluation platform with mandatory research, parallel evidence lanes, sequential merge, and bounded ref221skills.sh installs

2

openai-prompt-engineerjamesrochabrun/skillsGenerate and improve prompts using best practices for OpenAI GPT-5 and other LLMs. Apply advanced techniques like chain-of-thought, few-shot prompting, and prog207skills.sh installs

3

llm-fine-tuning-guideqodex-ai/ai-agent-skillsMaster fine-tuning of large language models for specific domains and tasks. Covers data preparation, training techniques, optimization strategies, and evaluatio194skills.sh installs

4

langchainhoodini/ai-agents-skillsBuild LLM applications with LangChain and LangGraph. Use when creating RAG pipelines, agent workflows, chains, or complex LLM orchestration. Triggers on LangCha169skills.sh installs

5

alicloud-ai-chatbot-testcinience/alicloud-skillsSmoke test for alicloud-ai-chatbot. Validate minimal authentication, API reachability, and one read-only query path.161skills.sh installs

6

agent-framework-azure-ai-pysickn33/antigravity-awesome-skillsagent framework azure ai py145skills.sh installs