One-Man-Company

One-Man-Company / Skills-ContextManager

Public

A self-hosted web application for managing AI skills, workflows, and contexts with full MCP (Model Context Protocol) integration. Organize, manage, and dynamically load specialized knowledge bases into any AI Agent just by toggling your Skills On/Off in simple local hosted WEB UI.

51
11
100% credibility
Found Feb 17, 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

Self-hosted web dashboard to organize, toggle, import, and serve AI skills/workflows to agents via simple MCP tools.

How It Works

1
🚀 Get the skill manager

Download and run the simple setup to prepare your personal AI skill library on your computer.

2
🌐 Open your dashboard

Visit the local web page in your browser to see your organized skill hub.

3
📚 Browse starter skills

Discover ready-to-use skills for coding, design, security, and more, all copied into your library.

4
🧩 Create skill groups

Make context groups and toggle skills on or off for always-ready or on-demand use.

5
📥 Add your own skills

Import folders, grab from GitHub, or pull from Skills.sh to expand your collection.

6
🔗 Connect to your AI

Copy the ready settings to link with your AI agent so it uses your exact skills.

🤖 AI supercharged

Your AI now pulls the perfect skills and workflows without overload, tailored just for you.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 46 to 51 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 Skills-ContextManager?

Skills-ContextManager is a self-hosted web app that lets you organize, toggle, and load AI agent skills, workflows, and knowledge bases through a simple local UI. It solves the chaos of scattering specialized contexts—like code validators or design checkers—across folders or repos by letting you import from GitHub, local files, or registries, then dynamically inject them into any MCP-compatible AI agent. Built with Python for the MCP server and Node.js for the web interface, you get token tracking, multi-workspace support, and on-demand loading without rebuilding agents.

Why is it gaining traction?

Unlike cloud-dependent agent tools, this runs fully self-hosted—like a self-hosted GitHub Copilot or self-hosted web-based file manager tailored for AI skills—giving devs full control over private knowledge without vendor lock-in. The killer hook is toggling 39+ starter skills (API validators, SEO checkers, UX auditors) on/off via drag-and-drop UI, plus seamless MCP tools for always-loaded vs. dynamic contexts. Early adopters love the one-command setup and GitHub import for quick agent customization.

Who should use this?

AI agent builders experimenting with local LLMs, backend devs managing validation workflows, or frontend teams needing self-hosted design/SEO checkers for custom agents. Ideal for indie hackers prototyping self-hosted GitHub Actions runners or self-hosted web scrapers as agent skills, without scattering scripts everywhere.

Verdict

Worth trying for self-hosted AI agent workflows—strong starter skills and MCP integration punch above its 45 stars and 1.0% credibility score. Still early (light tests, nascent community), but solid docs and MIT license make it a low-risk experiment for agent tinkerers.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.