codeindex

Name: codeindex
Availability: InStock
Author: smart-knowledge-systems

Embed code skeletons, summaries, and commit messages for semantic codebase search.

Updated Mar 13, 2026

Search Tags:#codebase #embeddings #semantic-search #commit-history #code-discovery #directory-summaries

Ready to run

npx skills add https://github.com/smart-knowledge-systems/codeindex --skill codeindex

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: codeindex
Source: https://github.com/smart-knowledge-systems/codeindex/tree/main/.claude/skills/codeindex
Command: npx skills add https://github.com/smart-knowledge-systems/codeindex --skill codeindex

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Locate relevant code across large or unfamiliar codebases by using semantic search that understands meaning rather than relying on file names or exact keywords.

Core Features & Use Cases

Semantic search across codebases by embedding file skeletons, directory summaries, and commit messages.
Cross-repo search and rapid discovery across multiple repositories with scope all.
Retrieve contextual results with file paths, skeletons, and summaries to guide inspection.

Quick Start

Query with a natural-language description of what you want to find, and let codeindex return ranked file paths and context-ready results.

Frequently Asked Questions about codeindex

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

FAQPage Schema

How do I find relevant code across large codebases using semantic search?▼

Semantic search across codebases works by embedding file skeletons, directory summaries, and commit messages, then ranking results by cosine similarity and recency. You query with a natural-language description to retrieve ranked file paths and context-ready snippets.

Can I search for code across multiple repositories at the same time?▼

Yes, cross-repo search supports rapid discovery across multiple repositories. By using a scoped search, you can retrieve contextual results with file paths, skeletons, and directory summaries from large or unfamiliar codebases simultaneously.

How does code discovery handle commit history and directory context?▼

Code discovery embeds commit messages and directory summaries to rank results by recency and relevance. This approach previews directory context alongside file paths and skeletons to guide inspection and rapid navigation.

What is the best way to locate code when I only know its function and not the file name?▼

The best way to locate code by function is using code-aware retrieval with natural-language queries. It understands meaning rather than relying on exact keywords or file names, returning ranked file paths and snippets for rapid navigation.

Does semantic code search support integration with agents and automated tools?▼

Yes, this semantic search approach is designed for integration with agents and tools requiring structured code discovery. It returns structured outputs including file paths, skeletons, and snippets for automated navigation across large repositories.

When should I avoid semantic search and rely on exact keyword matching instead?▼

Semantic search is not ideal when you know the exact variable or file name you are looking for. It is designed for locating relevant code by meaning and context across large or unfamiliar codebases rather than exact string matching.