browser-testing
Drive real browsers via Chrome DevTools MCP: navigate pages, capture snapshots, run responsive checks, and collect console/perf traces. Use when the user mentions: 'validate UI change in Chrome', 'capture a screenshot', 'run responsive checks', or 'collect console logs'. Trigger terms: browser testing, DevTools, console logs, screenshot, responsive testing
100
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 articulates specific capabilities (navigate, snapshot, responsive checks, console/perf traces), names the technology (Chrome DevTools MCP), and provides explicit trigger guidance with both example phrases and a trigger terms list. It is well-differentiated and would be easy for Claude to select appropriately from a large skill set.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: navigate pages, capture snapshots, run responsive checks, collect console/perf traces. Also specifies the mechanism (Chrome DevTools MCP). | 3 / 3 |
Completeness | Clearly answers both 'what' (drive real browsers via Chrome DevTools MCP with specific actions) and 'when' (explicit 'Use when...' clause with trigger phrases and a separate trigger terms list). | 3 / 3 |
Trigger Term Quality | Includes a rich set of natural trigger terms users would actually say: 'validate UI change in Chrome', 'capture a screenshot', 'run responsive checks', 'collect console logs', 'browser testing', 'DevTools', 'responsive testing'. Good coverage of common variations. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Chrome DevTools-based browser interaction, with distinct triggers like 'DevTools', 'Chrome', 'console logs', and 'responsive testing' that are unlikely to conflict with other skills such as generic testing or screenshot tools. | 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 a high-quality skill that provides comprehensive, actionable browser testing guidance using Chrome DevTools MCP. It is concise, well-structured, and includes concrete tool calls with validation checkpoints and error recovery steps. The progressive disclosure is appropriate, keeping the main workflow inline while deferring project-specific configuration to an external file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what Chrome DevTools is or how MCP works, assumes Claude's competence, and every section provides direct, actionable tool calls without unnecessary preamble. | 3 / 3 |
Actionability | Every section provides concrete, copy-paste-ready MCP tool calls with specific function signatures and parameters. The code examples are executable and cover navigation, interaction, validation, screenshots, and performance tracing. | 3 / 3 |
Workflow Clarity | The testing workflow is clearly sequenced (Setup → Initial State → Test → Console Check → Responsive), includes explicit validation checkpoints (evaluate_script assertions, console error checks), and has a feedback loop in the regression re-test workflow ('analyze, fix, repeat. Do NOT stop'). Error recovery is addressed (e.g., 'If wait_for times out: verify dev server is running'). | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-organized sections, and appropriately references external project-specific config via a single one-level-deep link to testing-config.md. Content is well-structured with logical groupings (Tools Reference, Workflow, Regression, Context Management). | 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
- monkilabs/opencastle
- Commit
f5c8508
- 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.