ultrathink-detective

Name: ultrathink-detective
Availability: InStock
Author: tianzecn

Audit codebase architecture and dependencies using AST-based analysis.

2|Updated Dec 25, 2025

Search Tags:#architecture #security #implementation #holistic #multi-dimension

Ready to run

npx skills add https://github.com/tianzecn/myclaudecode --skill ultrathink-detective

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ultrathink-detective
Source: https://github.com/tianzecn/myclaudecode/tree/main/plugins/code-analysis/skills/ultrathink-detective
Command: npx skills add https://github.com/tianzecn/myclaudecode --skill ultrathink-detective

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires claudemem, and includes references (resource) and scripts (resource) components.

What problem does it solve?

This Skill provides holistic, multi-dimensional code analysis by combining architecture, implementation, testing, debugging, security, and performance perspectives using CLAUDEMEM AST commands.

Core Features & Use Cases

Multi-Dimensional Reasoning: map, symbol, callers, callees, context, and search in a unified flow.
Consensus-driven: synthesize analyses from all perspectives into actionable items.
Plan-oriented: identify risks, gaps, and remediation steps.

Quick Start

Run all detective dimensions in parallel and ask for a unified report with prioritized action items.

Frequently Asked Questions about ultrathink-detective

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I audit a codebase's architecture and dependencies without using grep or find?▼

Ultrathink-detective performs AST-based analysis using claudemem commands—map, symbol, callers, and callees—to reveal codebase structure and call relationships without text-search tools. It synthesizes architecture, security, and implementation perspectives into a unified report with prioritized findings.

Can I use AST analysis for security audits and refactoring large, multi-language codebases?▼

Yes. Ultrathink-detective is designed for complex, multi-language repositories during security audits, refactors, and incident investigations. It provides evidence-backed conclusions by combining architecture, testing, debugging, security, and performance analyses in parallel.

What's the best way to identify risks and dependencies in a codebase during onboarding?▼

Run ultrathink-detective's multi-dimensional analysis—map, symbol, callers, callees, context, and search commands—to uncover structure, call relationships, and architectural gaps. The consensus-driven approach synthesizes findings into actionable remediation steps.

Does this Skill require claudemem, and what version do I need?▼

Yes, ultrathink-detective requires claudemem v0.3.0. The Skill uses claudemem's AST commands—map, symbol, callers, callees, context, and search—and prohibits grep, find, and glob usage for strict AST-only analysis.

What are the limitations of AST-based analysis versus full-text search?▼

AST-based analysis requires claudemem v0.3.0 and structured symbol/call-graph queries; it cannot use grep, find, or glob patterns. Trade-off: precision and architectural insight gain at the cost of flexibility in ad-hoc text searches across unstructured content.

How does multi-dimensional reasoning improve code analysis quality?▼

Ultrathink-detective combines architecture, implementation, testing, debugging, security, and performance perspectives using claudemem commands. Consensus-driven synthesis across all dimensions produces deeper insights and identifies gaps that single-perspective analysis would miss.