catalan-adobe/browser-universal
Detect available browser interaction layer (Playwright MCP, Slicc playwright-cli, cmux-browser, CDP) and load the right commands — then navigate, click, fill, and screenshot through a unified verb set. Use before any browser interaction in skills that shouldn't hardcode a specific layer. Triggers on: browser universal, detect browser, browser layer, browser setup, which browser, browser interaction, open browser, use browser.
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 an excellent skill description that hits all the marks. It clearly explains the capability (detecting and abstracting browser interaction layers), provides explicit usage guidance for when to apply it, and includes comprehensive trigger terms. The description is specific enough to avoid conflicts with individual browser automation skills while being discoverable for its intended use case.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'detect available browser interaction layer', 'navigate, click, fill, and screenshot', and names specific tools (Playwright MCP, Slicc playwright-cli, cmux-browser, CDP). Uses third person voice correctly. | 3 / 3 |
Completeness | Clearly answers both what ('Detect available browser interaction layer and load the right commands — then navigate, click, fill, and screenshot') and when ('Use before any browser interaction in skills that shouldn't hardcode a specific layer') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms explicitly listed: 'browser universal, detect browser, browser layer, browser setup, which browser, browser interaction, open browser, use browser'. These match what users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: focuses specifically on browser layer detection and abstraction, not general browser automation. The emphasis on 'unified verb set' and 'shouldn't hardcode a specific layer' clearly differentiates it from individual browser tool 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 that efficiently handles browser layer detection and abstraction. It provides executable detection commands, a clear priority system, proper error handling with user guidance, and a well-organized universal verb mapping. The progressive disclosure to LAYERS.md keeps the main skill focused while enabling deep dives.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient, assuming Claude's competence with shell commands and browser concepts. No unnecessary explanations of what browsers or CLI tools are—jumps straight to detection commands and usage patterns. | 3 / 3 |
Actionability | Provides fully executable bash commands for detection, a complete universal verb mapping table, and specific targeting model instructions. The detection scripts are copy-paste ready with proper error handling. | 3 / 3 |
Workflow Clarity | Clear multi-step detection workflow with explicit parallel checks, priority ordering, and a blocking error state with user-facing remediation steps. The 'Universal Pattern' section explicitly requires re-snapshot after state changes—a validation checkpoint. | 3 / 3 |
Progressive Disclosure | Well-structured with quick reference table inline and detailed layer-specific commands properly delegated to [references/LAYERS.md]. One-level-deep reference that's 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.
Reviewed
Table of Contents