Name: agent-device
Rating: 64 (1 reviews)
Author: Expensify

agent-device

Drive iOS and Android devices for the Expensify App - testing, debugging, performance profiling, bug reproduction, and feature verification. Use when the developer needs to interact with the mobile app on a device.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/agent-device/SKILL.md

Quality

Content

80%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 well-sequenced, highly actionable bring-up workflow with strong validation checkpoints and feedback loops. The major weakness is progressive disclosure: the skill cites flows/ and scripts/ paths that are absent from the bundle, so the referenced detailed material is unreachable.

Suggestions

Ship the referenced bundle: add a flows/README.md (and the flows/macros/ helpers and .ad snippets it describes) and a scripts/is-hybrid-app.sh, or remove the references and inline the essential guidance.

Verify 'Canonical skill references' and the bundled CLI skills dir pointer resolve at load time; document what to do if the npm-global path is absent rather than only checking it in pre-flight.

Tighten the 'Interaction safety' section by consolidating the repeated overlay/snapshot rationale into a single concise checklist.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, command-driven, and assumes competence, but the 'Interaction safety' section is somewhat padded with repeated overlay/snapshot rationale; a few explanatory sentences could be trimmed without losing clarity.	4 / 5
Actionability	Provides concrete, copy-paste-ready commands at every step (e.g. 'agent-device open <bundle-id> --platform <p> --device "<name>"', 'agent-device snapshot -i') with specific flags and bundle IDs, covering the common bring-up cases.	5 / 5
Workflow Clarity	The Bring-up flow is a clearly numbered 9-step sequence with explicit STOP/validation checkpoints (pre-flight FAIL gates, dev-build check, Metro failure handling, sanity snapshot, overlay dismissal feedback loop), including error-recovery guidance.	5 / 5
Progressive Disclosure	The body repeatedly points to flows/README.md and scripts/is-hybrid-app.sh, but no flows/ or scripts/ bundle directories exist in the skill; references resolve to nothing, leaving navigation broken and detail unsplit rather than well-disclosed.	2 / 5
	Total	16 / 20 Passed

Description

76%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 specific, third-person description that clearly answers both what and when with concrete actions and a distinct device-automation niche. Trigger phrase coverage is good but could add common synonyms (simulator/emulator) to reach the top anchor.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('testing, debugging, performance profiling, bug reproduction, and feature verification') plus the target (iOS and Android devices), with only a minor gap around what 'interact' concretely entails.	4 / 5
Completeness	Answers 'what' (drive iOS/Android devices for testing/debugging/profiling) and 'when' ('Use when the developer needs to interact with the mobile app on a device'); the 'when' clause is explicit but somewhat generic, not a 3 (what present, when missing) nor a 5 (concrete multi-trigger phrases).	4 / 5
Trigger Term Quality	Includes natural user-facing terms ('mobile app', 'on a device', 'testing', 'debugging') and an explicit 'Use when the developer needs to interact with the mobile app on a device' trigger, but lacks synonyms like 'simulator', 'emulator', or device-specific phrasing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Expensify App on iOS/Android devices) with distinct triggers unlikely to collide with generic skills; the Expensify + device scoping sharply reduces conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

81%

Warnings & errors only

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

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: Expensify/App
Path: .claude/skills/agent-device/SKILL.md
Commit: 0498f1e

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.