# memorydetective

> Use this tool when you need to investigate iOS memory leaks and performance issues, as it analyzes .memgraph and .trace files to identify retain cycles and provides Swift fix templates. It solves problems related to memory management and performance optimization, offering a comprehensive interface with 28 tools, 34 catalog resources, and 5 investigation prompts. By bridging to source code via SourceKit-LSP, it streamlines the debugging process, making it an essential tool for iOS developers.

Canonical page: https://skillsregistry.net/skills/carloshpdoc-memorydetective  
JSON: https://api.skillsregistry.net/v1/skills/carloshpdoc-memorydetective

## Description

iOS leak hunting and performance investigation.
Reads .memgraph and .trace files, classifies retain cycles against a 34-pattern catalog with Swift fix templates, bridges to source via SourceKit-LSP. 28 MCP tools, 34 catalog resources, 5 investigation prompts.

## Trust

- **Trust score (0–1):** 0.86
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/lwdjx9s80m)
- **Repository:** <https://github.com/carloshpdoc/memorydetective>

## 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": "carloshpdoc-memorydetective"
    }
  }
}
```

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