# Polaroid

> Polaroid — sandeep-alluru-polaroid. Use this tool when you need to recall and query visual information from previous interactions with a computer interface. Polaroid solves problems of visual memory and intent-based recall, allowing agents to store and retrieve UI screenshots as semantic scene nodes across sessions. It takes in UI screenshots and intent-based queries as inputs and outputs relevant scene nodes, making it ideal for use cases requiring visual memory and recall in computer-use scenarios.

Canonical page: https://skillsregistry.net/skills/sandeep-alluru-polaroid  
JSON: https://api.skillsregistry.net/v1/skills/sandeep-alluru-polaroid

## Description

Visual memory for computer-use agents — stores UI screenshots as semantic scene nodes and queries them by intent across sessions.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/pcumqq7qw1)
- **Repository:** <https://github.com/sandeep-alluru/polaroid>

## 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": "sandeep-alluru-polaroid"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sandeep-alluru-polaroid` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sandeep-alluru-polaroid/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