performance-testing
Create and review E2E performance tests that measure real user flows on real devices with TimerHelper and PerformanceTracker. Use when creating, editing, or reviewing performance tests, when the user mentions perf tests, timing measurements, performance thresholds, or files in tests/performance/.
100
100%
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 a strong skill description that clearly communicates its purpose, lists specific tools and actions, and provides explicit trigger guidance. It uses proper third-person voice, includes a well-structured 'Use when...' clause with natural trigger terms, and is distinctive enough to avoid conflicts with other testing-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Create and review E2E performance tests', 'measure real user flows on real devices', and names specific tools 'TimerHelper and PerformanceTracker'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (create and review E2E performance tests measuring real user flows with specific tools) and 'when' (explicit 'Use when...' clause covering creating, editing, reviewing performance tests, plus specific trigger terms and file paths). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'perf tests', 'timing measurements', 'performance thresholds', 'tests/performance/', 'performance tests', 'E2E'. Good coverage of both formal and informal variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: E2E performance testing with specific tools (TimerHelper, PerformanceTracker), specific file path (tests/performance/), and specific domain (real device performance measurement). Unlikely to conflict with general testing or unit test skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that is concise, highly actionable, and well-structured. It provides a complete executable template, clear rules with rationale, specific threshold ranges, and thorough guidance for both creating and modifying tests. The progressive disclosure is well-handled with the reference.md link and organized key references section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient throughout. It assumes Claude's competence with testing frameworks, avoids explaining what E2E testing is or how libraries work, and every section delivers actionable information without padding. The tables, checklists, and code template are all dense with useful information. | 3 / 3 |
Actionability | Provides a fully executable quick template with real imports and patterns, concrete forbidden patterns, specific threshold ranges, exact file paths, and a detailed code review checklist. The guidance is copy-paste ready and leaves no ambiguity about what to do. | 3 / 3 |
Workflow Clarity | The core rules establish a clear sequence (actions outside measure, assertions inside), the template demonstrates the exact workflow order, and the modification section includes explicit validation steps (run 3+ times for baselines, grep for usages, re-run affected tests). The code review checklist serves as a validation checkpoint for modifications. | 3 / 3 |
Progressive Disclosure | Opens with a clear pointer to the full reference guide, keeps the SKILL.md as a focused overview with essential rules and a quick template, and ends with well-organized key references linking to specific files. References are one level deep and clearly signaled. | 3 / 3 |
Total | 12 / 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
bee9b14
- 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.