# Thinking

> Use this tool when you need to analyze and understand AI decision-making processes, identify inconsistencies, and extract valuable insights from conversations. It solves problems related to AI transparency, explainability, and reliability by surfacing heuristics, contradictions, and mental models. With inputs from AI conversations and API keys from Anthropic and Voyage, it outputs a queryable graph of thinking patterns accessible through various MCP-compatible clients.

Canonical page: https://skillsregistry.net/skills/multimail-dev-thinking  
JSON: https://api.skillsregistry.net/v1/skills/multimail-dev-thinking

## Description

Extracts thinking patterns from AI conversations and stores them in a typed graph backed by SQLite. Surfaces heuristics, contradictions, and mental models so they can be queried by any MCP-compatible client. Requires Anthropic and Voyage AI API keys for extraction and embedding. Compatible with Claude Code, Claude Desktop, Cursor, and Windsurf.

## Trust

- **Trust score (0–1):** 0.83
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/multimail-dev-thinking)
- **Repository:** <https://github.com/multimail-dev/thinking-mcp>

## 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": "multimail-dev-thinking"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/multimail-dev-thinking` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/multimail-dev-thinking/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