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 a strong skill description that clearly communicates its purpose as a browser interaction abstraction layer, lists concrete actions and supported tools, and provides explicit trigger guidance. It effectively distinguishes itself from individual browser tool skills by emphasizing its detection and unification role. The explicit trigger term list is comprehensive and well-chosen.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'detect available browser interaction layer', 'navigate, click, fill, and screenshot through a unified verb set', and names specific tools (Playwright MCP, Slicc playwright-cli, cmux-browser, CDP). Very specific about what it does. | 3 / 3 |
Completeness | Clearly answers both 'what' (detect browser layer, load commands, navigate/click/fill/screenshot via unified verbs) and 'when' ('Use before any browser interaction in skills that shouldn't hardcode a specific layer') with explicit trigger terms listed. | 3 / 3 |
Trigger Term Quality | Includes a comprehensive explicit trigger list covering natural variations: 'browser universal', 'detect browser', 'browser layer', 'browser setup', 'which browser', 'browser interaction', 'open browser', 'use browser'. These cover many natural ways a user or system might reference browser interaction needs. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a very clear niche — browser abstraction layer detection and unified verb set. The specific mention of tool names (Playwright MCP, Slicc, cmux-browser, CDP) and the meta-skill nature (detecting which layer to use) makes it highly distinct from any individual browser automation skill. | 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 a complex multi-layer detection and abstraction problem. It provides concrete detection commands with clear success/failure criteria, a well-structured universal verb mapping table, and appropriate progressive disclosure to a layers reference file. The workflow is clear with explicit checkpoints including a blocking error state when no layer is detected.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what browsers are or how MCP works — it jumps straight into detection commands and verb mappings. Every section earns its place with no padding or unnecessary exposition. | 3 / 3 |
Actionability | Detection steps include concrete, executable shell commands with specific success criteria (exit codes, output patterns). The universal verbs table provides exact command names per layer. The error message when no layer is detected gives specific remediation steps. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced: detect layers → apply priority → load reference → use universal verbs. Detection has explicit pass/fail criteria for each layer. The 'No Layer Detected' section is a clear blocking checkpoint. The universal pattern requiring re-snapshot after state changes is an explicit validation step. | 3 / 3 |
Progressive Disclosure | The skill provides a concise overview with the universal verb table inline (appropriate since it's the core quick-reference), while deferring detailed layer-specific commands, targeting models, and gotchas to a single one-level-deep reference (references/LAYERS.md). Well-signaled and appropriately split. | 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
- catalan-adobe/skills
- Commit
54a7b1a
- 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.