# ThinkRun

> ThinkRun — dundas-thinkrun. Use this tool when you need to record and analyze browser interactions for AI-powered coding assistance. ThinkRun solves problems of replicating complex user interactions and providing context for AI agents to generate accurate code, by capturing clicks, console output, network requests, and screenshots. It takes in browser sessions as input and outputs structured data for AI agents to understand and act upon.

Canonical page: https://skillsregistry.net/skills/dundas-thinkrun  
JSON: https://api.skillsregistry.net/v1/skills/dundas-thinkrun

## Description

Records browser sessions and provides structured context (clicks, console, network, screenshots) for AI coding agents to understand and act upon.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/x4k7b8ae9n)
- **Repository:** <https://github.com/dundas/thinkrun>

## 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": "dundas-thinkrun"
    }
  }
}
```

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