When is this skill automatically triggered?

It triggers automatically when you ask about project structure, start a task requiring architectural awareness, or when a fresh session begins in a directory containing a .phi folder.

What is the 'Memory' layer in phi-analyzer?

The memory layer utilizes cross-session insights stored in a local vessel, allowing the tool to recall architectural decisions and previous debugging outcomes to inform current tasks.

How does phi-analyzer improve Claude's performance?

It provides a structured, semantic, and historical map of the project, allowing Claude to understand complex file relationships and architectural patterns that aren't visible when looking at single files.

Does this skill modify my source code?

No, phi-analyzer is a read-only tool designed for analysis and context gathering. It reads from .phi metadata and your filesystem but never performs code modifications.

Phi Project Analyzer

Name: Phi Project Analyzer
Author: adimov-eth

byadimov-eth

0•

Herramientas para Desarrolladores

Analyzes codebases through a multi-layered compositional lens to provide deep architectural awareness and persistent project memory.

Phi Project Analyzer is a sophisticated project context engine that builds a holistic understanding of codebases using three integrated layers: deterministic structure (file maps), curated semantics (architectural patterns), and learned memory (cross-session insights). By calculating integrated project information (φ), it enables Claude to provide more accurate architectural advice, find implementations faster, and maintain context across different working sessions. This skill is particularly useful for developers onboarding to complex repositories, managing large-scale refactors, or anyone needing to bridge the gap between file-level code and high-level system architecture.

Características Principales

010 GitHub stars

02Persistent cross-session learning via vessel memory semantic search

03Auto-invocation triggered by architectural queries or fresh sessions

04S-expression map parsing for deterministic project layout understanding

05Progressive disclosure for optimal token usage and performance

06Integrated multi-layer analysis (Structure, Semantics, and Memory)

Casos de Uso

01Mapping complex architectural patterns and identifying technical debt

02Maintaining persistent context and insights across multiple coding sessions

03Rapidly onboarding and navigating large or unfamiliar codebases

Características Principales

010 GitHub stars

02Persistent cross-session learning via vessel memory semantic search

03Auto-invocation triggered by architectural queries or fresh sessions

04S-expression map parsing for deterministic project layout understanding

05Progressive disclosure for optimal token usage and performance

06Integrated multi-layer analysis (Structure, Semantics, and Memory)

Casos de Uso

01Mapping complex architectural patterns and identifying technical debt

02Maintaining persistent context and insights across multiple coding sessions

03Rapidly onboarding and navigating large or unfamiliar codebases