59 / 168 · 01 Agent Skills for Browser Automation · Hybrid Strategies: Using Skills and MCP Together← prev⊞ allnext →☰ Read as one page
9.1Why Hybrid?
Skills and MCP each have strengths the other lacks:
| Capability | Skills (Playwright CLI) | MCP |
|---|---|---|
| Token efficiency | Excellent (~4x cheaper per task, measured) | Poor |
| Semantic page understanding | YAML accessibility snapshots — read on demand | Accessibility trees — streamed always |
| Speed per step | Dozens of tokens per command | Thousands of tokens per action |
| Works without a filesystem | No — disk is the whole trick | Yes — inline state |
| Discovery | snapshot + read the YAML |
Automatic (tree arrives with every action) |
The 2026 division of labor is simpler than it was in the vibe-check era: the CLI now carries semantic page understanding too (same accessibility data, on disk). What MCP retains is environments where there is no disk. A hybrid approach uses the CLI wherever the agent has a filesystem and MCP where it doesn't — or where an integration is MCP-native.