Clawmobile Capabilities

Organization

ClawMobile

clawmobile-capabilities

Capability-stage map for the ClawMobile Termux runtime.

Overview

Publisher	ClawMobile
Repository	`ClawMobile`
Skill name	`clawmobile-capabilities`
Stars	147
Forks	28
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by ClawMobile on GitHub. Read the source before you install it.

Installation

Install the Clawmobile Capabilities AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/ClawMobile/ClawMobile/tree/main/installer/workspace-seed-lite/skills/clawmobile-capabilities
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/ClawMobile/ClawMobile/tree/main/installer/workspace-seed-lite/skills/clawmobile-capabilities

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/ClawMobile/ClawMobile.git /tmp/ClawMobile
mkdir -p .claude/skills
cp -r /tmp/ClawMobile/installer/workspace-seed-lite/skills/clawmobile-capabilities .claude/skills/clawmobile-capabilities

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Clawmobile Capabilities in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Clawmobile Capabilities on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Clawmobile Capabilities is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

ClawMobile Termux Runtime Capabilities

Use this skill to map common phone actions to the currently available runtime capabilities. Call android_health when the current permission stage is unknown.

Stages

Stage	Capability shape
`termux`	OpenClaw, local shell, files, network, CLI tools, and OCR on existing image files when `local_ocr=true`
`termux_api`	Termux plus local phone APIs such as toast, notification, clipboard, battery, and TTS
`adb_shell`	Termux plus Android UI observation/input and `adb shell` commands

Do not use ADB-required tools unless android_health.capabilities.ui_input, ui_observe, screenshot, or android_shell says that capability is true. Do not use OCR tools unless android_health.capabilities.ocr or local_ocr is true. Use OCR without a path only when screen_ocr is true.

Navigation

Capability	Tool
Go home	`adb_keyevent HOME` when `ui_input=true`
Go back	`adb_keyevent BACK` when `ui_input=true`
Recent apps	`adb_keyevent RECENTS` when `ui_input=true`
Press enter	`adb_keyevent ENTER` when `ui_input=true`

Observation

Capability	Tool
List connected devices	`adb_devices`
Check runtime capabilities	`android_health`
Discover UI keywords compactly	`android_ui_dump` when `ui_observe=true`; returns a local `dump_id` and keyword index, not raw XML by default
Query UI nodes compactly	`android_ui_query` when `ui_observe=true`; it fresh-dumps and caches UI XML when no `dumpId` is provided
Dump raw UI hierarchy	`adb_ui_dump_xml` or `android_ui_dump rawXml=true` when raw XML is genuinely needed
Take screenshot	`adb_screenshot` or `android_screenshot` when `screenshot=true`
OCR existing image file	`android_ocr_dump`, `android_match_text_queries`, or `android_resolve_text_queries` with `path` when `ocr=true` or `local_ocr=true`
OCR current phone screen	OCR tools without `path` when `screen_ocr=true`

App / System Commands

Capability	Tool
Local Termux command	`android_shell backend="termux" cmd="..."`
Open app by package	`android_shell backend="adb" cmd="monkey -p <package> -c android.intent.category.LAUNCHER 1"` when `android_shell=true`
Open Android settings	`android_shell backend="adb" cmd="am start -a android.settings.SETTINGS"` when `android_shell=true`
Open Wi-Fi settings	`android_shell backend="adb" cmd="am start -a android.settings.WIFI_SETTINGS"` when `android_shell=true`
List IMEs	`android_shell backend="adb" cmd="ime list -s"` when `android_shell=true`
Set IME	`android_shell backend="adb" cmd="ime set <IME_ID>"` when `android_shell=true`

Touch / Text

Capability	Tool
Tap coordinate	`adb_tap` or `android_tap` when `ui_input=true`
Swipe coordinate path	`adb_swipe` or `android_swipe` when `ui_input=true`
Type into focused field	`adb_type` or `android_type` when `ui_input=true`
Run generated-skill fast path	`clawmobile_skill_run_fast_path` when a generated skill provides an eligible fast path; it loads the skill and calls `clawmobile_batch_execute` internally
Run raw deterministic batch	`clawmobile_batch_execute` when explicit batch steps are already available and required ADB/OCR capabilities are available

Generated skills are app/task knowledge first. Use their app model, applicability rules, anchors, verification hints, and prior execution evidence to reduce repeated probing during normal agent runs. Use a fast path only when its required inputs and app-state assumptions match.

Observe before coordinate actions unless the coordinates are explicitly provided by the user, a previous tool result, or a reliable generated-skill anchor. For UI XML, call android_ui_query directly when the target is known. Use android_ui_dump first only when you need a complete keyword index or plan to run several related queries on the same screen; then reuse its dumpId. Use nodeId and detail="full" only when you need to inspect one candidate. For generated skills, prefer entry/final checkpoint verification over fresh screenshots after every low-risk coordinate action.

Demonstration Learning

Capability	Tool
Record a fresh touch trace	`clawmobile_record_start` then `clawmobile_record_stop` when ADB/shell-level event and screenshot access are available
Parse existing recording	`clawmobile_record_parse`
Prepare trace summary	`clawmobile_trace_prepare_summary`
Save candidate	`clawmobile_trace_save_skill_candidate`
Promote generated skill	`clawmobile_skill_candidate_promote`
Refresh generalized skill	`clawmobile_skill_generalize`
Read generated skill status	`clawmobile_skill_status`
Execute generated skill fast path	`clawmobile_skill_run_fast_path`

Use the clawmobile-trace-induction skill for the full record-to-generated skill workflow.

Frequently asked questions

What does the Clawmobile Capabilities AI skill do?

Capability-stage map for the ClawMobile Termux runtime.

Why use Clawmobile Capabilities on TypingMind?

Because you install it once and use it with any model. Clawmobile Capabilities is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Clawmobile Capabilities in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ClawMobile/ClawMobile/tree/main/installer/workspace-seed-lite/skills/clawmobile-capabilities. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Clawmobile Capabilities?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Clawmobile Capabilities?

As many as you like. As long as a model supports skills, you can use Clawmobile Capabilities with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Clawmobile Capabilities AI skill free?

Yes. It is published on GitHub by ClawMobile under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Pptx Author

NousResearch

OrganizationPopular

Build PowerPoint decks headless with python-pptx.

Pokemon Player

Play Pokemon via headless emulator + RAM reads.

Docx

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document',…

Openclaw Docker E2e Authoring

openclaw

OrganizationPopular

Author OpenClaw Docker E2E and live provider Docker lanes.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

ClawMobile Termux Runtime Capabilities

Stages

Navigation

Observation

App / System Commands

Touch / Text

Demonstration Learning

Frequently asked questions

Related AI Skills

Set up your own AI workspace now