Haaaiawd

AI-native codebase intelligence skills — generate persistent .nexus-map/ knowledge bases and instantly query file structure, dependency graphs, and change impact. Built for Copilot, Cursor, and any tool-calling LLM. 面向 AI 编程助手的代码库感知技能——生成持久化知识图谱,精准查询文件结构、依赖关系与改动影响半径。

83
4
100% credibility
Found Mar 10, 2026 at 46 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

nexus-skills provides two AI agent tools to create persistent knowledge maps of codebases for quick context recovery and to query code structures, dependencies, and change impacts precisely.

How It Works

1
🔍 Discover nexus-skills

You come across nexus-skills, a helpful set of tools that make your AI coding assistant much smarter about understanding any code project.

2
Add to your AI helper

You easily add these skills to your favorite AI coding companion, so it can use them right away.

3
📁 Choose a code project

You show the skills a folder containing your code project that you want to explore.

4
Pick your path
🗺️
Build full map

Your AI scans the entire project and saves a lasting guide with architecture, connections, and key insights.

🔍
Quick questions

Ask precise questions like what depends on a file or spots of frequent changes, getting answers instantly.

5
Magic happens

The tools analyze everything smoothly, uncovering hidden structures and relationships you didn't know about.

🎉 Smarter coding forever

Now every time you work with your AI on this project, it starts with full knowledge, helping you build and fix things faster and safer.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 46 to 83 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is Nexus-skills?

Nexus-skills provides AI-native codebase intelligence through two Python skills: one builds persistent knowledge bases (.nexus-map/) from repo ASTs and git history, capturing architecture, dependencies, and hotspots; the other delivers instant queries on file structures, reverse deps, and change impact. It solves the problem of AI tools like Copilot or Cursor rediscovering codebase context every session, letting devs start with precise maps instead of vague summaries. Supports 30+ languages out of the box, with CLI tools for on-demand analysis.

Why is it gaining traction?

Unlike generic repo summarizers, it outputs structured, token-efficient artifacts like Mermaid graphs and JSON knowledge graphs that AI agents reload fast, plus query commands for who-imports or impact radius without full parses. The hook is seamless integration with tool-calling LLMs—install via npx skills add, point your AI at a repo, and get reusable bases built for ai native development github workflows. Bilingual docs and phase-gated analysis reduce AI hallucinations on code structure.

Who should use this?

Backend engineers onboarding to legacy monoliths, before interface changes or refactors needing dep impact checks. AI-assisted devs in Copilot/Cursor hitting context limits on medium repos. Teams prepping architecture reviews, querying hubs or git forensics without manual greps.

Verdict

Early project (29 stars, 1.0% credibility score) with solid bilingual docs and MIT license, but light on evals—test on your repo before production. Worth adding to ai native github toolchains for nexus skills in dynamic change analysis.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.