Skillsphere Agent
What is Skillsphere Agent
SkillSphere-Agent is a framework designed to publish skills and experiences using the Model Context Protocol (MCP). It transforms career notes into a query-ready knowledge graph and generates job-targeted, ATS-friendly résumés on demand.
Use cases
Use cases for SkillSphere-Agent include creating tailored résumés for specific job applications, visualizing career skills and projects in a hypergraph format, and managing career data efficiently in a single location.
How to use
To use SkillSphere-Agent, clone the repository from GitHub, set up a Python virtual environment, install the required packages, and configure the Neo4j credentials. After that, build or refresh the hypergraph to start using the knowledge graph and résumé builder.
Key features
Key features of SkillSphere-Agent include a single-source-of-truth for career data, a hypergraph structure for querying specific skills, an ATS-optimized résumé generation pipeline, and the ability to run entirely local without needing an OpenAI key.
Where to use
SkillSphere-Agent can be used in various fields including career development, recruitment, and personal knowledge management, particularly for professionals looking to streamline their job application process.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Skillsphere Agent
SkillSphere-Agent is a framework designed to publish skills and experiences using the Model Context Protocol (MCP). It transforms career notes into a query-ready knowledge graph and generates job-targeted, ATS-friendly résumés on demand.
Use cases
Use cases for SkillSphere-Agent include creating tailored résumés for specific job applications, visualizing career skills and projects in a hypergraph format, and managing career data efficiently in a single location.
How to use
To use SkillSphere-Agent, clone the repository from GitHub, set up a Python virtual environment, install the required packages, and configure the Neo4j credentials. After that, build or refresh the hypergraph to start using the knowledge graph and résumé builder.
Key features
Key features of SkillSphere-Agent include a single-source-of-truth for career data, a hypergraph structure for querying specific skills, an ATS-optimized résumé generation pipeline, and the ability to run entirely local without needing an OpenAI key.
Where to use
SkillSphere-Agent can be used in various fields including career development, recruitment, and personal knowledge management, particularly for professionals looking to streamline their job application process.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
SkillSphere ⚡️
Graph-powered talent intelligence in < 10 min
Turn scattered career notes into a live knowledge graph — and one-click, ATS-ready résumés.
🌟 Why you’ll care
| Problem | SkillSphere’s answer |
|---|---|
| Career data everywhere — LinkedIn, slides, docs | Markdown → Neo4j hypergraph (one source of truth) |
| Generic CVs don’t win roles | Graph-query → Job-specific résumé PDF |
| LLM privacy & cost nerves | Runs fully local on Ollama, no API keys |
| Need proof of my graph/AI chops | This repo is the demo — explore the live graph or read the code |
🚀 30‑second taste
git clone https://github.com/bprager/SkillSphere.git
cd SkillSphere && ./scripts/quick_start.sh # builds graph + sample résumé
open output/resume_google.pdf
Full install & config instructions live in
docs/installation.md.
🔍 See it in action
🧩 Inside the box
- Hypergraph‑of‑Thought model → Neo4j + Node2Vec embeddings
- Gleaning loop wrings 25 % extra facts from each chunk
- Graph→Markdown→PDF pipeline for recruiter‑ready résumés
- 100 % unit‑tested core modules
Deep‑dive architecture and research notes are in docs/architecture.md.
🤝 Work with me
I design & build graph‑driven AI solutions that make talent, knowledge and content searchable & actionable.
If that sparks ideas for your team:
- Book a 30‑min chat
- Connect on LinkedIn
- Say hi via email:
[email protected]
Let’s turn your data into an unfair advantage.
© 2025 Bernd Prager — Apache 2.0
Clone it, fork it, improve it — and tell me what you build!
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.
