# Better Code Review Graph

> Use this tool when you need to analyze codebases and provide AI assistants with precise context, solving problems such as code review and understanding complex code structures. It takes in codebases as input and outputs a structural graph of functions, classes, and imports, allowing for multi-word search and qualified call resolution. Ideal for use cases where detailed code analysis is required, such as debugging, optimization, and maintenance.

Canonical page: https://skillsregistry.net/skills/n24q02m-code-review-graph  
JSON: https://api.skillsregistry.net/v1/skills/n24q02m-code-review-graph

## Description

Better Code Review Graph is a fork of code-review-graph with critical bug fixes and production enhancements. It parses codebases using Tree-sitter to build a structural graph of functions, classes, and imports, providing AI assistants with precise context. The implementation includes multi-word search with AND logic, qualified call resolution for callers/callees, dual-mode embeddings (local ONNX or cloud LiteLLM), and paginated output to prevent token overflow.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-29

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/n24q02m-code-review-graph)
- **Repository:** <https://github.com/n24q02m/better-code-review-graph>

## 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": "n24q02m-code-review-graph"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/n24q02m-code-review-graph` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/n24q02m-code-review-graph/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