deepsearch

Search codebases for concepts, functions, or patterns across multiple languages.

6|1|Updated Apr 16, 2026
One-click install
npx skills add https://github.com/Goblin1024/oh-my-kimi --skill deepsearch-goblin1024
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deepsearch
Source: https://github.com/Goblin1024/oh-my-kimi/tree/main/skills/deepsearch
Command: npx skills add https://github.com/Goblin1024/oh-my-kimi --skill deepsearch-goblin1024

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Locating scattered code references across large codebases can be time-consuming and error-prone. This Skill performs thorough searches for queries, patterns, or concepts, identifies all matches, and surfaces their relationships.

Core Features & Use Cases

  • Broad Search: search for exact matches and related terms across common locations (components, utils, services, hooks).
  • Deep Dive: read files with matches, inspect imports/exports, and trace connections across the project.
  • Synthesis: map usage, identify main implementations, and surface anomalies or patterns for refactoring.

Quick Start

Provide a search query (e.g., function name, class, or concept) and Deep Search will return primary locations, related files, usage patterns, and insights.

Frequently Asked Questions about deepsearch

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

FAQPage Schema
How do I find where a specific function or pattern is used across a large codebase?

To find function or pattern usage across a codebase, perform a broad search for matches, deep-dive into the files to inspect imports and exports, then synthesize the connections to map primary locations and usage relationships.

What is the best way to trace imports and references across multiple programming languages?

Tracing imports and references across multiple languages involves searching common locations like components and utils, reading matched files to inspect connections, and synthesizing usage patterns to identify main implementations and anomalies for refactoring.

Can I search for code concepts and map usage relationships in large multi-language projects?

Yes, you can search for code concepts in large multi-language projects by applying a three-phase workflow: executing broad searches for exact matches, deep-diving into matched files, and synthesizing the discovered usage relationships.

How do I identify anomalies and refactoring patterns from scattered code references?

Identifying anomalies and refactoring patterns from scattered references requires synthesizing the connections found during deep-dives into matched files, which surfaces main implementations, usage patterns, and structural anomalies across the codebase.

What do I need to provide to start a thorough codebase search for specific code concepts?

To start a thorough codebase search, you need to provide a search query such as a function name, class, or concept, which will then be used to return primary locations, related files, usage patterns, and key insights.