CtrlK
BlogDocsLog inGet started
Tessl Logo

argent-test-ui-flow

Autonomously test an app UI (iOS or Android) by running interact-screenshot-verify loops using argent MCP tools. Use when testing a UI flow, verifying login works, testing navigation, or running an end-to-end UI test scenario.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

81%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-structured, actionable skill body with a clear workflow, concrete examples, and explicit recovery/verification feedback loops. It loses a little on conciseness and actionability due to minor trims and pseudo-call representations, and progressive disclosure is appropriately single-file but above the simple-skill line.

Suggestions

Tighten the platform-agnostic setup table and Tips section to remove any non-essential tokens and push conciseness toward the lean 5 anchor.

Where possible, replace the pseudo-call example representations (e.g. 'gesture-tap { x: 0.5, y: 0.4 }') with the exact argent MCP tool invocation syntax so examples are copy-paste executable.

Consider moving the longer Examples or Recovery Pattern into a reference file to demonstrate clearer progressive disclosure for the >50-line body.

DimensionReasoningScore

Conciseness

Mostly lean and efficient, using tables and tight code blocks without explaining concepts Claude already knows (e.g. what a screenshot or gesture is). A few sections (platform-agnostic setup table, Tips) could be trimmed slightly, keeping it just below the lean 5 anchor.

4 / 5

Actionability

Concrete tool names and example calls with coordinates ('gesture-tap { x: 0.5, y: 0.4 }', 'adb -s <serial> reverse tcp:8081 tcp:8081') give mostly executable guidance. It is a 4 rather than 5 because the example calls are representations of MCP tool invocations rather than copy-paste-ready real syntax.

4 / 5

Workflow Clarity

A clear numbered Workflow (baseline screenshot, find target, interact, verify, repeat) with an explicit verification step and a dedicated Recovery Pattern section providing feedback loops ('If tap misses target: re-run discovery, retry once', 'If tap fails twice: stop, re-discover, report').

5 / 5

Progressive Disclosure

Well-organized single-file structure (Platform-agnostic, Workflow, Template, Examples, Recovery, Tips, Related Skills) with clearly signaled one-level-deep cross-skill references in a table. It is a 4 rather than 5 because all content is inline with no bundle files, and the ~110-line body is slightly above the simple-skill threshold.

4 / 5

Total

17

/

20

Passed

Description

91%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 description that clearly states both what the skill does and when to use it, with natural, varied trigger phrases. Minor overlap risk with sibling argent device-interaction skills keeps distinctiveness just below the top anchor.

DimensionReasoningScore

Specificity

Names the domain ('test an app UI (iOS or Android)') and several concrete actions ('interact-screenshot-verify loops', 'using argent MCP tools'), with minor gaps in the full action set. It lists several specific actions but not the comprehensive coverage of a 5.

4 / 5

Completeness

Explicitly answers both 'what' ('Autonomously test an app UI ... by running interact-screenshot-verify loops using argent MCP tools') and 'when' ('Use when testing a UI flow, verifying login works, testing navigation, or running an end-to-end UI test scenario') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger phrases a user would say are comprehensive: 'testing a UI flow', 'verifying login works', 'testing navigation', 'running an end-to-end UI test scenario', covering the main scenarios and synonyms. Not a 4 because the natural phrasing covers the relevant use cases thoroughly.

5 / 5

Distinctiveness Conflict Risk

Clear niche (argent MCP UI testing via interact-screenshot-verify) with distinct triggers, but 'testing a UI flow' has minor overlap risk with the related argent-device-interact skill. Not a 5 because of that small overlap with closely related device-interaction skills.

4 / 5

Total

18

/

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
Uniswap/interface
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.