skills.rest
google
googleOFFICIAL
Explore all skills by this author →
Website𝕏@GoogleOSSGitHub

mantis-structural-index

Build a content-addressed semantic-unit index of symbols, call edges, and function boundaries from source code.

731|84|Updated Jun 15, 2026
Search Tags:#static analysis#code analysis#indexing#semantic search#security review#call graph
One-click install
npx skills add https://github.com/google/mantis --skill mantis-structural-index
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mantis-structural-index
Source: https://github.com/google/mantis/tree/main/mantis-structural-index
Command: npx skills add https://github.com/google/mantis --skill mantis-structural-index

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill addresses the lack of structural awareness in LLM-based code analysis by building a content-addressed semantic index that provides function boundaries, call-site awareness, and symbol cross-references.

Core Features & Use Cases

  • Semantic Indexing: Generates a searchable catalog of symbols, call edges, and function boundaries using language-specific backends.
  • Incremental Updates: Uses content-addressed caching to ensure only modified code units are re-indexed, optimizing performance for large repositories.
  • Use Case: When performing a complex security review, use this skill to enable the AI to accurately trace function calls and identify callers of a specific vulnerable symbol across a large codebase.

Quick Start

Invoke the mantis-structural-index skill to generate a structural index for the current codebase to improve research accuracy.

Frequently Asked Questions about mantis-structural-index

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

FAQPage Schema
How do I perform semantic code indexing for static analysis on a large repository?▼

To perform semantic code indexing, you can generate a content-addressed semantic-unit index from your local source code to extract symbols, call edges, and function boundaries. This provides structural context for deep static analysis.

What is the best way to improve call-site discovery and trace function calls during a security review?▼

Build a structural code index to achieve high-precision call-site discovery. This enables accurate tracing of function calls and identifies callers of specific vulnerable symbols across the codebase during security reviews.

Does semantic code indexing support incremental updates for modified code units?▼

Yes, semantic code indexing supports incremental updates by using content-addressed caching. This ensures only modified code units are re-indexed, optimizing performance across multiple snapshots of large repositories.

Can I use structural context from code analysis without relying on manual symbol cross-referencing?▼

Yes, you can generate a searchable catalog that automatically extracts symbol cross-references and function boundaries. This provides immediate structural context for code analysis without manual cross-referencing.

How does semantic search indexing handle multiple programming languages in a codebase?▼

Semantic search indexing uses capability-based backend selection to handle multiple programming languages. It applies language-specific backends to accurately extract semantic units and structural boundaries from diverse source code.

Related Skills

Explore More Software Engineering Skills→
RheasilviaRheasilvia

gitnexus-explorer

Index source code into a knowledge graph for visual exploration.

Community
Advanced
2389-research2389-research
90

binary-re:static-analysis

Analyze binary structure and decompile functions with radare2 and Ghidra headless.

Official
Advanced
lyq-linlyq-lin

ant-design-knowledge-base

Query a local knowledge base for Ant Design component semantics and documentation links.

Community
Advanced
alexei-ledalexei-led
35

smart-explore

Outline codebases, search symbols across files, and unfold function bodies via AST.

Community
Advanced