# snapsurf

> snapsurf — zumerlab-snapsurf. Use this tool when you need to automate web navigation and verification for AI agents, solving problems such as ensuring accurate webpage interactions and validating semantic page structure. It takes in webpage inputs and outputs a compact semantic page digest, typed diff, and assertions, providing a reliable interface for verification. Ideal for use cases requiring precise web interaction validation, such as automated testing and AI training.

Canonical page: https://skillsregistry.net/skills/zumerlab-snapsurf  
JSON: https://api.skillsregistry.net/v1/skills/zumerlab-snapsurf

## Description

Web navigation and verification for AI agents: a compact semantic page digest, a typed diff after each action, and assertions over that diff. MCP server and CLI on Playwright and SnapDOM.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/zumerlab/snapsurf)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "zumerlab-snapsurf"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zumerlab-snapsurf` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zumerlab-snapsurf/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt