CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/appium-testing

Use for any question or task about Appium mobile UI tests, even a quick fix, including tests that break after an Appium upgrade and suites that pass on Android but fail on iOS: one suite for iOS and Android (native or React Native) with XCUITest, UiAutomator2 and Espresso drivers, capabilities, clients in JS, Python, Java, Ruby or .NET, simulators, emulators and device farms.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

Quality

Content

78%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.

Excellent operational content: executable code at every step, expert-level traps (idle-timeout setting vs capability, reset semantics, migration breaking changes), and clear sequencing with verification. The main gap is structural — everything lives in one long file with no progressive disclosure to reference files, and one date-stamped version claim sits outside the migration section.

Suggestions

Move the capabilities catalog and the Appium 2→3 migration table into a references/ file (e.g. references/migration.md), keeping SKILL.md as an overview with well-signaled one-level-deep pointers.

Relocate the date-stamped version claim ("3.9.0 on npm, 3 Nov 2026") into the migration/upgrade section so time-sensitive details don't stale the main workflow, per the conciseness guideline.

Add an explicit failure-recovery loop for the run step (e.g., 'if the session fails to start, run appium driver doctor and check driver versions'), which would raise workflow clarity to anchor 5.

DimensionReasoningScore

Conciseness

Dense and non-obvious throughout — no basic-concept padding; every section carries Appium-specific knowledge ("waitForIdleTimeout is a setting, not a capability", scoped insecure flags, reset semantics). Not anchor 5 because time-sensitive version data ("Appium 3 is current (3.9.0 on npm, 3 Nov 2026)") sits in the main install flow instead of the migration/deprecated section, and the ~350-line body could be trimmed slightly.

4 / 5

Actionability

Fully executable, copy-paste-ready guidance at every step: install/doctor commands, server flags, a complete WebdriverIO test, a capabilities table, concrete selector examples per platform, a CI matrix YAML, and a raw-HTTP W3C Python script. Matches anchor 5; the only placeholder (`...iosCaps`) is an acceptable config excerpt.

5 / 5

Workflow Clarity

Steps 1–7 are clearly sequenced (install → server → author → capabilities → selectors → run → CI) with an explicit validation checkpoint (`appium driver doctor` / "0 required fixes needed") and a failure→fix anti-patterns table plus an explicit upgrade order. Not anchor 5: there is no true validate→fix→retry feedback loop within the workflow itself (e.g., what to check when a session fails to start), and per-step checkpoints are implicit.

4 / 5

Progressive Disclosure

A single ~350-line SKILL.md with no bundle files: the capabilities catalog, the Appium 2→3 migration table, and the anti-patterns table are all inlined where they could live in separate reference files. Sections are well-organized and external links are clearly listed one level deep in a References section (better than anchor 2's wall of text), but content that should be split out is inline, matching anchor 3; the under-50-line simple-skill exception does not apply.

3 / 5

Total

16

/

20

Passed

Description

95%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: explicit trigger guidance including edge-case phrasings users actually say (broken-after-upgrade, Android-passes-iOS-fails), third-person voice, and a concrete enumeration of the toolchain scope. Its only weakness is that it enumerates technologies more than distinct actions.

DimensionReasoningScore

Specificity

Enumerates concrete, verifiable artifacts — "XCUITest, UiAutomator2 and Espresso drivers, capabilities, clients in JS, Python, Java, Ruby or .NET, simulators, emulators and device farms" — with only minor gaps. Falls short of anchor 5 because it lists specific technologies and scope rather than multiple distinct concrete actions (the verbs are mostly implied by "any question or task about").

4 / 5

Completeness

Explicitly answers both: when ("Use for any question or task about Appium mobile UI tests, even a quick fix, including...") and what ("one suite for iOS and Android (native or React Native) with XCUITest, UiAutomator2 and Espresso drivers, capabilities, clients..."). The when-clause is explicit with concrete trigger phrases, matching anchor 5 rather than anchor 4's merely-adequate 'when'.

5 / 5

Trigger Term Quality

Covers natural phrasings a user would actually say: "Appium mobile UI tests", "even a quick fix", "tests that break after an Appium upgrade", "suites that pass on Android but fail on iOS", "React Native", "simulators, emulators and device farms" — including failure-scenario triggers, not just topic keywords. Matches anchor 5's comprehensive natural-term coverage; barely any common variant is missing.

5 / 5

Distinctiveness Conflict Risk

"Appium" plus named drivers (XCUITest, UiAutomator2, Espresso) carve out a clear niche with distinct triggers and minimal conflict risk against adjacent skills (detox, xcuitest-suite, espresso-suite) — those are different tools a user would name explicitly. Matches anchor 5.

5 / 5

Total

19

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

On this page