CtrlK
BlogDocsLog inGet started
Tessl Logo

android-emulator

Verify and debug native, React Native, Expo, or Flutter apps on an Android Emulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an Android virtual device.

76

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

90%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, actionable body with executable commands and a sensible workflow including error recovery. It could benefit from explicit section headers and a validation checkpoint to fully maximize clarity and navigation.

Suggestions

Add ## section headers (e.g., '## Setup', '## Driving an app', '## Specialized tasks') to improve navigation and progressive disclosure.

Insert an explicit validation checkpoint after opening the app (e.g., confirm the interactive snapshot loaded before proceeding) to strengthen the workflow's feedback loop.

Consider splitting the help-topic catalog into a short reference table so the main flow reads as a clean quick-start path.

DimensionReasoningScore

Conciseness

Lean and efficient with no padding or explanation of concepts Claude already knows; every line (install boundary, open command, help routing) earns its place.

5 / 5

Actionability

Provides copy-paste-ready commands ('npm install -g agent-device@latest', 'agent-device open <id> --platform android --foreground', version-matched help topics) covering the common driving cases.

5 / 5

Workflow Clarity

Clear sequence (install boundary -> open -> follow snapshot/hints -> escalate to help) with an error-recovery loop (unavailable -> ask user), but lacks an explicit validate-then-proceed checkpoint.

4 / 5

Progressive Disclosure

Compact single-page skill with no bundle files and logically ordered prose, but it lacks explicit ## section headers that would aid navigation; minor organization gap.

4 / 5

Total

18

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that concretely states capabilities and triggers with synonym coverage and minimal conflict risk. Both the 'what' and 'when' are explicitly and specifically answered.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow') across named frameworks, giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' ('Verify and debug ... apps on an Android Emulator with agent-device') and 'when' ('Use when an agent needs to ...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers natural user phrases (tap, type, scroll, validate a code change, reproduce a workflow) plus synonyms (Android Emulator / Android virtual device) and framework variants (native, React Native, Expo, Flutter).

5 / 5

Distinctiveness Conflict Risk

Clear niche tied to a specific tool (agent-device) and platform (Android Emulator) with distinct framework triggers, minimizing overlap with other skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
callstack/agent-device
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.