skills.rest
CarbeneAI
CarbeneAICOMMUNITY
Explore all skills by this author →
Website𝕏@CarbeneAIGitHub

Codebase Indexer

Index codebases into concept-to-file JSON maps with semantic search.

9|1|Updated Apr 16, 2026
Search Tags:#embeddings#developer-tools#token-optimization#semantic-search#code-navigation#concept-mapping#code-indexing
One-click install
npx skills add https://github.com/CarbeneAI/Forge --skill codebase-indexer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Codebase Indexer
Source: https://github.com/CarbeneAI/Forge/tree/main/.claude/skills/codebase-indexer
Command: npx skills add https://github.com/CarbeneAI/Forge --skill codebase-indexer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, git.

What problem does it solve?

Large codebases are hard to explore using filename search alone; this Skill indexes source files into compact concept-to-file mappings and provides semantic search so developers can quickly find where concepts are implemented without reading every file.

Core Features & Use Cases

  • Semantic Indexing: Extracts concepts from filenames, exports, imports, and comments, generates embeddings, and stores concept → file mappings in a JSON index.
  • Smart Navigation: Natural-language queries return ranked files, token-efficient summaries, related concepts, and dependency hints to guide code review and feature discovery.
  • Token Optimization & Incremental Updates: Uses compressed summaries, lazy loading, cached embeddings, and a script-driven incremental updater to minimize tokens and rebuild work.
  • Use Case: Developer asks "where is payment processing implemented?" and receives a ranked list of candidate files, short summaries, and the option to analyze any file further.

Quick Start

Ask the assistant to "Find files related to payment processing in this repository" to get a ranked list of implementing files and summaries.

Frequently Asked Questions about Codebase Indexer

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

FAQPage Schema
How do I search a large codebase by concept instead of filename?▼

Semantic code indexing extracts concepts from filenames, imports, and comments to map them to source files, enabling natural-language concept search so developers can locate implementations without reading every file. Results include ranked files and token-efficient summaries.

What is the best way to find where a specific feature is implemented in a repository?▼

Finding feature implementations is best handled by querying a concept-to-file semantic index with natural language. You ask where a concept like payment processing is implemented, and the index returns ranked candidate files, short summaries, and dependency hints for navigation.

Can I generate embeddings for code navigation without Python sentence-transformers?▼

Yes, code navigation and semantic search can fall back to grep if Python sentence-transformers is unavailable. This ensures concept-to-file indexing still functions for code discovery and mapping without requiring the optional embedding generation dependency.

How do I minimize token usage when indexing source files for code review?▼

Token usage during source file indexing is minimized using compressed summaries, lazy loading, and cached embeddings. The semantic index stores compact concept-to-file mappings and exports as JSON to keep code discovery and review workflows token-efficient.

Does semantic code indexing support incremental updates in CI environments?▼

Yes, semantic code indexing supports incremental reindexing in CI environments via a script-driven updater. This reduces rebuild work by re-indexing only changed files, maintaining an exportable JSON index for continuous developer workflows and code reviews.

Do I need jq and git installed to index codebases for semantic search?▼

Yes, jq and git are required dependencies to index codebases for semantic search. These tools enable the script-driven incremental updater to process repository changes and export the concept-to-file JSON index needed for natural-language concept mapping.

Related Skills

Explore More Software Engineering Skills→
92Bilal2692Bilal26

docusaurus-deployer

Automate Docusaurus site deployment to GitHub Pages with GitHub Actions.

Community
Intermediate
audibleblinkaudibleblink
4

grepai

Perform semantic code search and trace call relationships across codebases.

Community
Advanced
NITISH-gitbitNITISH-gitbit

chroma

Store, search, and retrieve embeddings and metadata with a vector database.

Community
Intermediate
masrurimzmasrurimz

explorer

Locate code implementations and trace usage with semantic search, grep, and glob.

Community
Basic