CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-device

Automates interactions for Apple-platform apps (iOS, tvOS, macOS) and Android devices. Use when navigating apps, taking snapshots/screenshots, tapping, typing, scrolling, or extracting UI info across mobile, TV, and desktop targets.

69

Quality

85%

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

71%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 router skill: clear operating rules, a sequenced default flow, and excellent progressive disclosure via gated reference files. The main weakness is redundancy across sections that inflates token cost without adding information.

Suggestions

Consolidate the 'plain snapshot vs snapshot -i' rule into a single statement; it currently appears in Default operating rules, Default flow, and Decision rules.

Merge the repeated 'Load bootstrap-install.md and exploration.md before acting' instruction (intro, Default flow, Required references) into one canonical location.

Deduplicate 'Prefer @ref or selector targeting over raw coordinates', which is stated in both Default operating rules and Decision rules.

DimensionReasoningScore

Conciseness

The router is mostly lean and assumes Claude's competence, but several rules are repeated across sections — 'Use plain snapshot when...' (Default operating rules, Default flow, Decision rules), 'Prefer @ref or selector targeting' (twice), and the bootstrap+exploration load instruction (intro, Default flow, Required references) — which could be tightened into one statement.

3 / 5

Actionability

Concrete commands and decision rules (`snapshot`, `snapshot -i`, `get`/`is`/`find`, `fill` vs `type`, `back` vs `back --system`, `--delay-ms`) give mostly executable guidance with only minor gaps, appropriate for an instruction/routing skill.

4 / 5

Workflow Clarity

The numbered Default flow (open -> inspect/act -> verify -> close) gives a clear sequence with most checkpoints ('Re-snapshot after meaningful UI changes', 'verify if needed'), though a couple of validation checkpoints remain implicit rather than explicit.

4 / 5

Progressive Disclosure

A concise overview routes to one-level-deep, real reference files, each with a 'When to open this file' gate; the second-level coordinate-system.md is nested only inside exploration.md, so navigation is easy and appropriately split.

5 / 5

Total

16

/

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 description: concise, third-person, with both a clear capability statement and an explicit 'Use when' trigger clause covering concrete, natural-sounding actions. No over-claims or padding.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'navigating apps, taking snapshots/screenshots, tapping, typing, scrolling, or extracting UI info' — giving comprehensive coverage of interaction verbs rather than vague language.

5 / 5

Completeness

It explicitly states both what ('Automates interactions for Apple-platform apps ... and Android devices') and when ('Use when navigating apps, taking snapshots/screenshots, ...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural user phrases ('navigating apps', 'taking snapshots/screenshots', 'tapping', 'typing', 'scrolling') plus synonyms (snapshots/screenshots) and platform names (iOS, tvOS, macOS, Android) give comprehensive keyword coverage.

5 / 5

Distinctiveness Conflict Risk

The device-automation niche (Apple/Android apps via snapshots/taps) with distinct trigger terms is unlikely to fire for unrelated skills, giving minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
callstackincubator/agent-skills
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.