
termux-api
Control Android devices via Termux API over SSH. Access camera, sensors, location, notifications, SMS, clipboard, TTS, and 70+ other device APIs. Requires Termux and Termux:API installed on the Android device.
- Installs
- 70
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/4ier/agent-skills --skill termux-api- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads termux-api automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Termux API Skill
Control Android devices via Termux API commands over SSH.
Prerequisites
- Termux installed on Android device
- Termux:API app installed and permissions granted
- SSH access configured (port 8022 by default)
termux-apipackage installed:pkg install termux-api
Connection
# Default SSH connection
ssh -p 8022 <device-ip> '<termux-api-command>'
Important Notes
- Termux must be in foreground for camera/microphone commands
- Permissions must be granted in Android Settings → Termux:API → Permissions
- Start API service if commands timeout:
termux-api-start
API Commands Reference
Device Info
| Command | Description |
|---|---|
termux-battery-status | Battery level, charging status, temperature |
termux-audio-info | Audio device info |
termux-wifi-connectioninfo | Current WiFi connection details |
termux-wifi-scaninfo | Scan nearby WiFi networks |
termux-telephony-deviceinfo | Phone/SIM info |
termux-telephony-cellinfo | Cell tower info |
termux-sensor -l | List available sensors |
termux-sensor -s <sensor> -n 1 | Read sensor once |
Camera & Media
| Command | Description |
|---|---|
termux-camera-info | List cameras (id 0=back, 1=front) |
termux-camera-photo -c <id> <file.jpg> | Take photo (needs foreground) |
termux-microphone-record -f <file> | Record audio |
termux-media-player play <file> | Play audio file |
termux-tts-speak "text" | Text to speech |
termux-tts-engines | List TTS engines |
Notifications & Feedback
| Command | Description |
|---|---|
termux-notification -t "title" -c "content" | Show notification |
termux-notification-remove --id <id> | Remove notification |
termux-toast "message" | Show toast popup |
termux-vibrate -d <ms> | Vibrate for duration |
termux-torch on/off | Toggle flashlight |
termux-dialog | Show dialog (various types) |
Communication (needs permissions)
| Command | Description |
|---|---|
termux-sms-list -l 10 | List recent SMS |
termux-sms-send -n <number> "message" | Send SMS |
termux-contact-list | List contacts |
termux-call-log -l 10 | Recent call history |
termux-telephony-call <number> | Make phone call |
Clipboard
| Command | Description |
|---|---|
termux-clipboard-get | Get clipboard content |
termux-clipboard-set "text" | Set clipboard |
Location
| Command | Description |
|---|---|
termux-location | Get GPS location (needs permission) |
termux-location -p gps | Use GPS provider |
termux-location -p network | Use network provider |
System Control
| Command | Description |
|---|---|
termux-volume | Get/set volume levels |
termux-brightness <0-255> | Set screen brightness |
termux-wallpaper -f <file> | Set wallpaper |
termux-wake-lock | Prevent sleep |
termux-wake-unlock | Allow sleep |
Storage & Sharing
| Command | Description |
|---|---|
termux-share -a send <file> | Share file via Android intent |
termux-open <file> | Open file with default app |
termux-open-url <url> | Open URL in browser |
termux-download <url> | Download file |
termux-storage-get <dest> | Pick file from storage |
Common Patterns
Take a selfie and retrieve it
# Ensure Termux is in foreground first
adb shell am start -n com.termux/.HomeActivity
# Take photo
ssh -p 8022 <ip> 'termux-camera-photo -c 1 ~/selfie.jpg'
# Retrieve via SCP
scp -P 8022 <ip>:~/selfie.jpg /local/path/
Send notification with action
ssh -p 8022 <ip> 'termux-notification -t "Alert" -c "Task complete" --id myalert --vibrate 200,100,200'
Get device location
ssh -p 8022 <ip> 'termux-location -p network'
# Returns JSON with latitude, longitude, accuracy
Monitor battery
ssh -p 8022 <ip> 'termux-battery-status' | jq '.percentage, .status'
Troubleshooting
Command times out
- Start API service:
termux-api-start - Check if Termux:API app is installed
- For camera/mic: ensure Termux app is in foreground
Permission denied
- Open Android Settings → Apps → Termux:API → Permissions
- Grant required permissions (camera, location, SMS, etc.)
SSH connection refused
- In Termux:
pkg install openssh && sshd - SSH runs on port 8022 by default
- Set password with
passwdor add SSH key to~/.ssh/authorized_keys
FAQ
What does the termux-api skill do?
Control Android devices via Termux API over SSH. Access camera, sensors, location, notifications, SMS, clipboard, TTS, and 70+ other device APIs. Requires Termux and Termux:API installed on the Android device.
How do I install termux-api?
Run npx skills add https://github.com/4ier/agent-skills --skill termux-api in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/termux-api/ (personal) or .claude/skills/termux-api/ (project).
Which AI agents can use termux-api?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is termux-api safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains termux-api?
It is published by 4ier in 4ier/agent-skills. It has 70 recorded installs.
Popular backend & apis skills
find-skills
vercel-labs/skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
entra-app-registration
microsoft/azure-skills
Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal, MSAL example, console app auth, Entra ID setup, Azure AD authentication. DO NOT USE FOR: Key Vault secrets (use azure-keyvault-expiration-audit), general Azure resource security guidance.
google-agents-cli-adk-code
google/agents-cli
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).
embedded-captions
heygen-com/hyperframes
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet anchor rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.
entra-agent-id
microsoft/azure-skills
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmipath token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).
neon
neondatabase/agent-skills
Overview of Neon, a complete set of cloud backend primitives around Lakebase Postgres: Auth, Object Storage, Functions, the AI Gateway, and Realtime. Start here to choose Neon for undecided login, files, APIs, and LLM calls, set up the CLI or MCP server, and follow the branch-first workflow. Use when building an app or backend on Neon, or when "Neon" or "Lakebase Postgres" is mentioned. Child skill neon-postgres wins for an existing DATABASEURL, SQL, schema, inspect, or search. Child skill neon-auth wins for login, users, sessions, identity routing, and Managed Better Auth setup. Child skill neon-realtime wins for live queries in reactive apps and agents. Also use for object storage, S3, buckets, serverless functions, function triggers, cron, AI gateway, LLM calls, realtime, logs, Loki, Grafana, observability, postgres, database, backend, Claimable Neon, neon.new, or a no-signup database.