lens-inspect
Use the Lens built-in browser to inspect a running web application. Trigger when the request involves previewing a page, taking screenshots, reading DOM, checking console errors, picking elements to locate source code, or comparing rendered output to a design spec.
86
82%
Does it follow best practices?
Impact
90%
1.57xAverage score across 3 eval scenarios
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 identifies the tool (Lens built-in browser), its purpose (inspecting running web applications), and provides an explicit trigger clause with six specific use cases. The description is concise, uses third-person voice, and includes natural trigger terms that users would actually say.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: previewing a page, taking screenshots, reading DOM, checking console errors, picking elements to locate source code, and comparing rendered output to a design spec. | 3 / 3 |
Completeness | Clearly answers both 'what' (use the Lens built-in browser to inspect a running web application) and 'when' (explicit trigger clause listing six specific scenarios). The 'Trigger when...' clause serves the same function as 'Use when...'. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'screenshots', 'console errors', 'DOM', 'design spec', 'previewing a page', 'source code'. These cover a good range of terms a user would naturally use when needing browser inspection capabilities. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to a specific tool ('Lens built-in browser') for inspecting running web applications. The combination of browser inspection, DOM reading, console errors, and design spec comparison creates a distinct niche unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid reference skill that provides actionable tool names, clear element picker output descriptions, and a useful Figma comparison workflow. Its main weaknesses are some unnecessary explanatory content (the 'What is Lens?' section), missing validation checkpoints in workflows, and all content being packed into a single file rather than using progressive disclosure for advanced topics like source code mapping and design comparison.
Suggestions
Remove or drastically shorten the 'What is Lens?' section — Claude doesn't need to know it uses Electron's WebContentsView or that it's in the right rail panel.
Add explicit validation steps to the Figma workflow (e.g., 'Verify screenshot is not blank before comparing') and to the element picker flow (e.g., 'If no selector is returned, the element may be in a shadow DOM').
Consider splitting source code mapping configuration and the Figma design comparison workflow into separate referenced files to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'What is Lens?' section explains concepts that could be inferred from context. The tool table and tips are efficient, but some descriptions (e.g., explaining what ring-buffered means, explaining Electron's WebContentsView) add tokens without value for Claude. | 2 / 3 |
Actionability | Provides a complete MCP tool reference table with specific tool names and purposes, concrete CSS selector-based interactions, specific settings paths, and a step-by-step Figma comparison workflow. The element picker output format is clearly specified with exact data fields returned. | 3 / 3 |
Workflow Clarity | The Figma design comparison workflow has a clear loop with numbered steps, but lacks explicit validation checkpoints (e.g., verifying screenshot succeeded, checking navigate completed). The 'Opening Lens' steps are clear but simple. The source code mapping section describes configuration but doesn't sequence the actual workflow of using it for debugging. | 2 / 3 |
Progressive Disclosure | Content is reasonably well-organized with clear sections and a useful table, but everything is in a single monolithic file with no references to supporting documents. The source code mapping and Figma workflow sections could be split into separate files. No bundle files are provided to offload detail. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sendbird/stave
- Commit
e275ad5
- 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.