One-Man-Company/Skills-ContextManager

↗ GitHub

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.

Stars

Forks

Watchers

Open Issues

Python·Last commit Feb 15, 2026·by @One-Man-Company·Published April 1, 2026

Safety Rating A

No hardcoded secrets, malicious code patterns, suspicious dependency configurations, or prompt injection attempts were identified. The README notes that API keys are stored with restrictive file permissions (mode 0600), which is a positive security practice. The repository appears to be a legitimate self-hosted developer tool with no red flags.

ℹAI-assisted review, not a professional security audit.

AI Analysis

Skills-ContextManager is a self-hosted web application and MCP (Model Context Protocol) server that provides a local web UI for organizing, managing, and dynamically loading AI skill knowledge bases and workflows into AI agents. Users can toggle skills on or off, group them into context cells, import from local folders or GitHub, and expose them to any MCP-compatible AI agent via three core tools: loading default skills, listing available skills, and on-demand dynamic skill loading. It ships with 39 starter skills and 3 workflows covering topics such as code review, debugging, frontend design, and more.

Use Cases

Managing and organizing reusable AI skill/knowledge-base files through a local web interface
Dynamically injecting specialized context into MCP-compatible AI agents at runtime
Importing skills from GitHub repositories or a Skills.sh registry into a personal library
Maintaining isolated multi-hub workspaces with separate skill sets for different projects
Tracking token usage of loaded skill contexts before sending to an AI agent