explore

Searches a codebase with semantic queries to locate entry points, data flow, and implementations.

Updated Jul 13, 2026
One-click install
npx skills add https://github.com/Ohmnia/site-build --skill explore-ohmnia
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: explore
Source: https://github.com/Ohmnia/site-build/tree/main/.opencode/skills/explore
Command: npx skills add https://github.com/Ohmnia/site-build --skill explore-ohmnia

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Answering questions like "how does this work?" or "where is X implemented?" often requires manually grepping and reading many files, which is slow and token-expensive. This Skill uses semantic codebase search to find relevant code quickly. ## Core Features & Use Cases - Semantic Codebase Search: Translates a user question into natural language queries and runs multiple codebase_search calls from different angles. - Flow Tracing: Identifies entry points, data flow, and ownership of a behavior across routers, handlers, config, and tests. - Use Case: When a developer asks "where is authentication handled?", the Skill runs parallel searches, reads the returned sections, and summarizes the flow with concrete file paths. ## Quick Start Ask the assistant to explore the codebase and explain where a specific feature is implemented and how its data flows.

Frequently Asked Questions about explore

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

FAQPage Schema
How do I find where a feature is implemented in a large codebase?

Use semantic codebase search with a natural language description of the functionality instead of keyword grep. Running 2-3 queries from different angles surfaces entry points, handlers, and related tests, which you then read to trace the flow.

How to trace data flow through a codebase?

Formulate a query like "Find the entry points and data flow for X, including router/handlers, config, and tests." Run it with codebase_search, read the returned sections, and summarize the flow with concrete file paths.

When should I use semantic search instead of grep for code?

Use semantic search when keyword grep is likely to miss relevant files, such as when you do not know exact symbol names. It works better for conceptual questions about behavior, ownership, and architecture.

What are the limitations of codebase semantic search?

Semantic search depends on the quality of the query and the index coverage of the repository. It may miss dynamically dispatched code or generated files, so results should be verified by reading the returned file sections.