# perceive

> perceive — gauthierpiarrette-perceive. Use this tool when you need to simulate human-like browser interactions, as it filters out unreachable elements and provides stable snapshots and state differences. It solves problems such as modal-occluded, off-screen, or inert element interactions, and closed-drawer access issues. The perceive tool takes browser snapshots as input and outputs ref-stable snapshots and state diffs, making it ideal for AI agents requiring accurate and relevant browser perception.

Canonical page: https://skillsregistry.net/skills/gauthierpiarrette-perceive  
JSON: https://api.skillsregistry.net/v1/skills/gauthierpiarrette-perceive

## Description

Reachability-filtered browser perception and actions for AI agents. Filters snapshots to elements a user could actually reach (removes modal-occluded, closed-drawer, off-screen and inert elements), with ref-stable snapshots and state diffs.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/u7h09pnu4r)
- **Repository:** <https://github.com/gauthierpiarrette/perceive>

## 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": "gauthierpiarrette-perceive"
    }
  }
}
```

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