e2e-test
Add and fix Detox E2E tests (smoke and regression) for MetaMask Mobile using withFixtures, Page Objects, and tests/framework. Use when creating a new spec, fixing a failing E2E test, adding page objects and selectors, or adding MetaMetrics analytics expectations (analyticsExpectations).
88
85%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that clearly defines its scope (Detox E2E testing for MetaMask Mobile), lists specific concrete actions, includes an explicit 'Use when' clause with multiple trigger scenarios, and uses domain-specific terminology that makes it highly distinguishable. It uses proper third-person voice and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: add and fix Detox E2E tests, create specs, fix failing tests, add page objects and selectors, add MetaMetrics analytics expectations. Also names specific tools/patterns: withFixtures, Page Objects, tests/framework. | 3 / 3 |
Completeness | Clearly answers both 'what' (add and fix Detox E2E tests using specific patterns) and 'when' (explicit 'Use when' clause covering creating specs, fixing failing tests, adding page objects/selectors, and adding analytics expectations). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'Detox', 'E2E test', 'smoke', 'regression', 'spec', 'failing E2E test', 'page objects', 'selectors', 'analyticsExpectations', 'MetaMetrics', 'MetaMask Mobile'. These cover a wide range of terms a developer would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Detox E2E tests specifically for MetaMask Mobile, with named patterns (withFixtures, Page Objects) and domain-specific terms (analyticsExpectations, MetaMetrics). Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured orchestration skill that excels at progressive disclosure and workflow clarity, serving as an effective routing document to detailed references. Its main weakness is that actionability depends entirely on the referenced files (none provided in the bundle), so the skill itself lacks executable examples or templates. There is some redundancy between the decision tree and the reference table that could be consolidated.
Suggestions
Add at least one minimal executable code example in the SKILL.md itself (e.g., a skeleton withFixtures spec) so the skill has standalone actionability even before opening references.
Consolidate the decision tree and the reference table into a single navigation structure to reduce redundancy and improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but has some redundancy — the decision tree and the reference table at the bottom convey largely the same information. The 'What This Skill Does' section also partially restates the workflow overview. However, it avoids explaining concepts Claude already knows and the golden rules are tight. | 2 / 3 |
Actionability | The golden rules provide concrete, specific constraints (e.g., 'no element(by.id()) in spec files', 'always use withFixtures'), and the decision tree gives clear routing. However, the skill itself contains no executable code examples, templates, or copy-paste-ready patterns — all concrete guidance is deferred to reference files which are not provided in the bundle. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Steps 0-5) with explicit validation checkpoints (Step 3: lint/tsc before running, Step 5: iterate until green). The decision tree provides clear branching logic for different task types. The feedback loop (fix → lint → run → iterate) is explicitly stated for this type of iterative development task. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure: the SKILL.md serves as a concise overview with golden rules and workflow, then clearly signals one-level-deep references via both a decision tree and a well-organized table. Each reference is clearly labeled with when to open it, and the instruction to not read references until directed is explicit. | 3 / 3 |
Total | 10 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- MetaMask/metamask-mobile
- Commit
dedb5dd
- 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.