CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/mobile-device-matrix-toolkit

Dispatches mobile UI test runs across a 3-tier device matrix (smoke per-PR, regression per-merge, full farm at release) to control CI cost: generates per-target Appium capability configs from a central YAML, parallelises via GitHub Actions matrix strategy, and aggregates JUnit XML into a cross-device pass/fail table. Use when the question is about which devices to run and when, not about how to configure a specific test framework (for that, use xcuitest-suite, espresso-suite, etc.).

76

Quality

96%

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

Overview
Quality
Evals
Security
Files

Quality

Content

92%

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

A highly actionable, well-sequenced dispatcher skill with executable code and a genuine validation/re-run feedback loop; the main gap is progressive disclosure, since the scripts and large device matrix live inline rather than in referenced bundle files.

Suggestions

Move gen-matrix.py and aggregate-matrix.py into a scripts/ bundle and replace the inline listings with concise summaries plus one-level-deep links (e.g., 'See scripts/gen-matrix.py'), keeping only illustrative snippets in SKILL.md.

Extract the tier_smoke/tier_regression/tier_release device lists into a references/ file (or the actual .matrix/devices.yaml) and reference it rather than reproducing all 7+7 release-tier entries inline.

Add a short 'Quick start' section at the top pointing to the per-step detail, so the overview acts as a navigation hub before the full Step 1–5 walkthrough.

DimensionReasoningScore

Conciseness

Lean body that assumes Claude's competence — no padding about what Appium or GitHub Actions is; even the combinatorial-explosion intro is a brief, motivating framing rather than explanation of known concepts.

3 / 3

Actionability

Provides fully executable, copy-paste-ready guidance: complete gen-matrix.py and aggregate-matrix.py scripts, GitHub Actions matrix YAML, and concrete farm commands (gcloud firebase test android run ..., npx browserstack-runner).

3 / 3

Workflow Clarity

Steps 1–5 are clearly sequenced, and Step 4 adds an explicit feedback loop for a batch operation — 'detect shards with a missing or empty report, re-run only those shards, then re-aggregate'.

3 / 3

Progressive Disclosure

Well-organized into clear sections, but all code (scripts/gen-matrix.py, scripts/aggregate-matrix.py) and the full device matrix are inlined in SKILL.md with no actual bundle files; the inline scripts read as content that could be split into one-level-deep reference files.

2 / 3

Total

11

/

12

Passed

Description

100%

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 with concrete capabilities, natural trigger terms, an explicit 'Use when' clause, and a clear negative boundary that distinguishes it from per-framework skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'generates per-target Appium capability configs from a central YAML, parallelises via GitHub Actions matrix strategy, and aggregates JUnit XML into a cross-device pass/fail table' — plus the 3-tier dispatch behaviour.

3 / 3

Completeness

Clearly answers both what (dispatch/generate/parallelise/aggregate) and when via an explicit 'Use when deciding which iOS / Android devices and OS versions to run tests on and at which stage' clause.

3 / 3

Trigger Term Quality

Covers natural terms a user would say — 'mobile UI test runs', 'iOS / Android devices', 'OS versions', 'smoke / regression / full farm', 'CI cost' — across the trigger clause.

3 / 3

Distinctiveness Conflict Risk

Owns a clear niche (device-matrix dispatch / cost control) and explicitly excludes framework configuration, redirecting that to 'xcuitest-suite, espresso-suite, etc.', so it is unlikely to trigger for the wrong skill.

3 / 3

Total

12

/

12

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

15

/

16

Passed

Reviewed

Table of Contents

DiscoveryImplementationValidation