adb-navigation-base

Base navigation patterns for Android device automation - gestures, waits, and UI interaction

16 stars

Best use case

adb-navigation-base is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Base navigation patterns for Android device automation - gestures, waits, and UI interaction

Teams using adb-navigation-base should expect a more consistent output, faster repeated execution, less prompt rewriting, better workflow continuity with your supporting tools.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.
  • You already have the supporting tools or dependencies needed by this skill.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/adb-navigation-base/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/cli-automation/adb-navigation-base/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/adb-navigation-base/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How adb-navigation-base Compares

Feature / Agentadb-navigation-baseStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Base navigation patterns for Android device automation - gestures, waits, and UI interaction

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

---

## Quick Reference (30 seconds)

**Base Navigation Patterns for Android Automation**

**What It Does**: Provides fundamental gesture and wait-for patterns used in all UI automation. Smart retry logic, verification, and timeout handling.

**Core Capabilities**:
- 👆 **Smart Tap**: Retry-enabled tapping with verification
- 👉 **Swipe Gesture**: Directional swiping for scrolling
- ⏱️ **Wait For**: Element/text waiting with polling

**When to Use**:
- Building reliable automation workflows
- Handling timing-sensitive UI transitions
- Creating reusable navigation patterns
- Combining with adb-screen-detection for full automation

---

## Scripts

### 1. adb-tap.py

Smart tap action with automatic retry logic.

```bash
# Basic tap
uv run .claude/skills/adb-navigation-base/scripts/adb-tap.py --x 100 --y 200

# Tap with retry (auto-retry on failure)
uv run .claude/skills/adb-navigation-base/scripts/adb-tap.py --x 100 --y 200 --retry 3

# Tap with verification
uv run .claude/skills/adb-navigation-base/scripts/adb-tap.py --x 100 --y 200 --verify-text "Next"

# Tap with both
uv run .claude/skills/adb-navigation-base/scripts/adb-tap.py \
    --x 100 --y 200 --retry 3 --verify-text "Loaded" --timeout 5
```

**Features**:
- Automatic retry on failure (configurable attempts)
- Post-tap screen verification
- Timeout protection
- Detailed logging

---

### 2. adb-swipe.py

Perform directional swipe gesture.

```bash
# Swipe up (scroll down content)
uv run .claude/skills/adb-navigation-base/scripts/adb-swipe.py --direction up --distance 300

# Swipe left (next page)
uv run .claude/skills/adb-navigation-base/scripts/adb-swipe.py --direction left --distance 500

# Swipe with verification
uv run .claude/skills/adb-navigation-base/scripts/adb-swipe.py \
    --direction down --distance 400 --verify-text "End of List"

# Custom start position
uv run .claude/skills/adb-navigation-base/scripts/adb-swipe.py \
    --direction up --distance 300 --start-x 500 --start-y 1000
```

**Directions**: up, down, left, right
**Features**:
- 4-direction swiping
- Configurable distance (pixels)
- Custom start position
- Post-swipe verification
- Momentum-aware (handles scroll inertia)

---

### 3. adb-wait-for.py

Wait for UI element or text to appear.

```bash
# Wait for text (default 10s timeout)
uv run .claude/skills/adb-navigation-base/scripts/adb-wait-for.py \
    --method text --target "Loaded"

# Wait for element by text with timeout
uv run .claude/skills/adb-navigation-base/scripts/adb-wait-for.py \
    --method text --target "Login" --timeout 5

# Wait with polling interval
uv run .claude/skills/adb-navigation-base/scripts/adb-wait-for.py \
    --method text --target "Results" --interval 0.5

# JSON output for scripting
uv run .claude/skills/adb-navigation-base/scripts/adb-wait-for.py \
    --method text --target "Ready" --json
```

**Detection Methods**: text (OCR-based)
**Features**:
- Configurable timeout (1-60s)
- Polling interval configuration
- Timeout exception handling
- Success/failure reporting
- Return element coordinates when found

---

## Usage Patterns

### Pattern 1: Basic Navigation Sequence

```bash
# 1. Tap login button
adb-tap.py --x 100 --y 200

# 2. Wait for login form
adb-wait-for.py --method text --target "Username" --timeout 5

# 3. Swipe down to see password field
adb-swipe.py --direction down --distance 200

# 4. Tap password field
adb-tap.py --x 100 --y 300
```

### Pattern 2: Reliable Action with Retry

```bash
# Tap with automatic retry (up to 3 times)
adb-tap.py --x 100 --y 200 --retry 3 --verify-text "Next Screen"
```

### Pattern 3: Scroll and Find

```bash
# 1. Start at top
# 2. Swipe up (scroll down) multiple times looking for element
for i in {1..5}; do
  adb-swipe.py --direction up --distance 300
  # Check if element appears
  if adb-wait-for.py --method text --target "Find Me" --timeout 1; then
    # Found! Tap it
    adb-tap.py --x 150 --y 400
    break
  fi
done
```

---

## Architecture

**Design Principles**:
- **Composable**: Chain together for complex workflows
- **Fault-Tolerant**: Automatic retry and timeout protection
- **Verifiable**: All actions can have post-action verification
- **Observable**: Detailed logging of all operations
- **Stateless**: No dependency on previous state

**Dependency Relationship**:
```
adb-screen-detection/ (provides capture, OCR, find-element)
         ↓
adb-navigation-base/ (uses for wait-for and verification)
         ↓
adb-workflow-orchestrator/ (coordinates these patterns)
```

---

## Integration Points

**Used By**:
- `adb-workflow-orchestrator` - Workflow step execution
- `adb-magisk` - Magisk Manager navigation
- `adb-karrot` - Karrot app automation

**Dependency On**:
- `adb-screen-detection` - Screen capture and OCR
- System: `adb` command-line tool

---

## Error Handling

### Retry Logic

```
Attempt 1: Try action
  ├─ Success → Return
  └─ Failure → Wait, Try again

Attempt 2: Try action
  ├─ Success → Return
  └─ Failure → Wait, Try again

Attempt 3: Try action
  ├─ Success → Return
  └─ Failure → Return error
```

### Timeout Handling

- Polls every N seconds (configurable)
- Returns TIMEOUT error if deadline exceeded
- Allows caller to handle timeout gracefully

---

## Workflows

This skill includes TOON-based workflow definitions for automation.

### What is TOON?
TOON (Task-Oriented Orchestration Notation) is a structured workflow definition language that pairs with Markdown documentation. Each workflow consists of:
- **[name].toon** - Orchestration logic and execution steps
- **[name].md** - Complete documentation and usage guide

This TOON+MD pairing approach is inspired by the BMAD METHOD pattern, adapted to use TOON instead of YAML for better orchestration support.

### Available Workflows

Workflow files are located in `workflow/` directory:

**Example Workflows (adb-navigation-base):**
- `workflow/tap-and-wait.toon` - Tap element and wait for result
- `workflow/scroll-and-find.toon` - Scroll to find element
- `workflow/gesture-sequence.toon` - Complex gesture combinations

### Running a Workflow

Execute any workflow using the ADB workflow orchestrator:

```bash
uv run .claude/skills/adb-workflow-orchestrator/scripts/adb-run-workflow.py \
  --workflow .claude/skills/adb-navigation-base/workflow/tap-and-wait.toon \
  --param device="127.0.0.1:5555"
```

### Workflow Documentation

Each workflow includes comprehensive documentation in the corresponding `.md` file:
- Purpose and use case
- Prerequisites and requirements
- Available parameters
- Execution phases and steps
- Success criteria
- Error handling and recovery
- Example commands

See the `workflow/` directory for complete TOON file definitions and documentation.

### Creating New Workflows

To create custom workflows for this skill:
1. Create a new `.toon` file in the `workflow/` directory
2. Define phases, steps, and parameters using TOON v4.0 syntax
3. Create corresponding `.md` file with comprehensive documentation
4. Test with the workflow orchestrator

For more information, refer to the TOON specification and the workflow orchestrator documentation.

---

**Version**: 1.0.0
**Status**: ✅ Foundation Tier
**Scripts**: 3
**Last Updated**: 2025-12-01
**Tier**: 2 (Foundation)

Related Skills

docker-database

16
from diegosouzapw/awesome-omni-skill

Configure database containers with security, persistence, and health checks

deep-codebase-analysis

16
from diegosouzapw/awesome-omni-skill

Agent capable of reading and analyzing the entire source code of a software project to gain a thorough understanding of architecture, communication, design patterns, and business flows. Use when exploring new systems, maintenance, or refactoring.

Database Sync

16
from diegosouzapw/awesome-omni-skill

Automate database synchronization, replication, migration, and cross-platform data integration

database-skill

16
from diegosouzapw/awesome-omni-skill

Design and manage relational databases including table creation, migrations, and schema design. Use for database modeling and maintenance.

database-architect

16
from diegosouzapw/awesome-omni-skill

Database design and optimization specialist. Schema design, query optimization, indexing strategies, data modeling, and migration planning for relational and NoSQL databases.

Codebase context

16
from diegosouzapw/awesome-omni-skill

Create a lightweight codebase_context.md that anchors the idea in the existing repo (modules, constraints, extension points). Generic framework prompt.

bio-basecalling

16
from diegosouzapw/awesome-omni-skill

Convert raw Nanopore signal data (FAST5/POD5) to nucleotide sequences using Dorado basecaller. Covers model selection, GPU acceleration, modified base detection, and quality filtering. Use when processing raw Nanopore data before alignment. Note: Guppy is deprecated; use Dorado for all new analyses.

arch-database

16
from diegosouzapw/awesome-omni-skill

DB architecture: relational vs document vs graph vs vector, schema design, indexing, replication, sharding

acsets-algebraic-databases

16
from diegosouzapw/awesome-omni-skill

ACSets (Attributed C-Sets): Algebraic databases as in-memory data structures. Category-theoretic formalism for relational databases generalizing graphs and data frames.

account-based-marketing-agent

16
from diegosouzapw/awesome-omni-skill

AI агент для ABM. Используй для автоматизации ABM кампаний и персонализации outreach.

u08983-ethical-dilemma-navigation-for-multilingual-translation-services

16
from diegosouzapw/awesome-omni-skill

Operate the "Ethical Dilemma Navigation for multilingual translation services" capability in production for multilingual translation services workflows. Use when mission execution explicitly requires this capability and outcomes must be reproducible, policy-gated, and handoff-ready.

basecamp-automation

16
from diegosouzapw/awesome-omni-skill

Automate Basecamp project management, to-dos, messages, people, and to-do list organization via Rube MCP (Composio). Always search tools first for current schemas.