Skills-ContextManager
Don’t pollute your AI agent’s context with 1,000 skills. Use Skills-ContextManager, a self-hosted web UI for managing AI skills and workflows by providing skills to an AI agent via MCP only when needed. Simply add skills to your library and enable or disable them with a toggle. Choose whether a skill is always loaded into context or dynamically activated when the AI agent determines it’s needed.
Skill-ContextManager & MCP Server
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.

Features
Web Application
- Skill & Workflow Management: Create, edit, delete, and organize skills and workflows
- Multi-Hub Support: Create isolated workspaces with separate skills/contexts
- Context Cells: Organize skills/workflows into logical groups with enable/disable toggles
- Dual Mode: Choose Always-loaded (auto-loaded) or Dynamic (on-demand) skills by on/off toggle
- File Editor: Built-in editor with file tree, create/delete files & folders
- Import Sources:
- 📂 Folder: Upload from local filesystem
- 🐙 GitHub: Clone from GitHub repositories
- ⚡ Skills.sh: Import from Skills.sh registry
- AI Description Generation: Auto-generate skill descriptions using AI APIs
- Secure API Key Storage: API keys stored with file mode 0600 (owner-only)
- Settings Profiles: Save and load configuration presets
- Search & Filter: Smart search, sort, favorites, active/inactive filters
- Token Counting: Track context size in tokens
- Drag & Drop: Move skills/workflows to contexts
MCP Server
- 3 Essential Tools for AI Agents:
get_default_skills()- Load skills with mode"always_loaded"list_available_skills()- List all enabled skills with modesload_full_skill_context(name)- Load dynamic skill on-demand
- Hub-Aware: Works with active hub from multiple workspaces
- Mode Support:
"always_loaded"vs"dynamic"skill loading - Type Support: Both Skills and Workflows
Quick Start
# Clone the repository
git clone https://github.com/One-Man-Company/Skills-ContextManager.git
cd Skills-ContextManager
# Make setup script executable and run it
chmod +x setup.sh
./setup.sh
# Start web application
cd Skill-ContextManager && npm start
Access: http://localhost:3000
MCP configuration saved to mcp_settings.json - add this to your AI Agent's MCP settings.
⚠️ Important: Copy the content of
MCP_instructions.mdto your AI Agent's System prompt or rules configuration.
MCP Configuration
The setup.sh script generates mcp_settings.json with correct paths. Add it to your AI Agent's MCP settings file:
{
"Skills-ContextManager": {
"command": "/absolute/path/Skills-MCP/.venv/bin/python3",
"args": ["-u", "/absolute/path/Skills-MCP/mcp_server.py"],
"env": {}
}
}
MCP Tools
AI Agents need only these 3 tools. Usage details are in MCP_instructions.md (system prompt):
| Tool | Description |
|---|---|
get_default_skills() | Load all skills with mode "always_loaded" into context |
list_available_skills() | List all enabled skills with descriptions and modes |
load_full_skill_context(name) | Load a specific skill on-demand (for mode "dynamic") |
mcpservers.org Submission
| Field | Value |
|---|---|
| Name | Skills-ContextManager |
| Description | Web UI for managing AI skills with MCP integration |
| Repository | https://github.com/One-Man-Company/Skills-ContextManager |
| Command | [path]/Skills-MCP/.venv/bin/python3 |
| Args | -u [path]/Skills-MCP/mcp_server.py |
Included Skills & Workflows
The repository includes starter content in MySkillsHUB/:
Skills (39): architecture, behavioral-modes, clean-code, code-review-checklist, documentation-templates, frontend-design, game-development, i18n-localization, mobile-design, nextjs-react-expert, nodejs-best-practices, parallel-agents, performance-profiling, python-patterns, seo-fundamentals, server-management, skill-creator, systematic-debugging, ui-ux-pro-max, vulnerability-scanner, webapp-testing, api-patterns, and more.
Workflows (3):
- best-standard-autonomous-coding
- elite-cognitive-operator-system
- plan-mode
All content is automatically copied to your library on first setup.
License
MIT License
Created: February 2026
Servidores relacionados
Scout Monitoring MCP
patrocinadorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
patrocinadorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
XTQuantAI
Integrates the xtquant quantitative trading platform with an AI assistant, enabling AI to access and operate quantitative trading data and functions.
Glider
Roslyn-powered C# code analysis server for LLMs. Supports stdio and HTTP transports.
MCP Image Placeholder Server
Generates placeholder images from various providers like placehold.co and lorem-picsum.
UnityNaturalMCP
An MCP server implementation for the Unity game engine that enables a natural user experience.
Project Atlantis
A Python MCP host server that allows for dynamic installation of functions and third-party MCP tools.
Hackle
Query A/B test data using the Hackle API.
BioMCP
Enhances large language models with protein structure analysis capabilities, including active site analysis and disease-protein searches, by connecting to the RCSB Protein Data Bank.
Code Understanding
Analyzes local and remote GitHub repositories to provide code understanding and context generation, including structure analysis, file identification, and semantic mapping.
Ionhour
Let AI agents monitor and manage your infrastructure through the Model Context Protocol. Query, create, and resolve — all in natural language.
Revit MCP
Interact with Autodesk Revit using the MCP protocol. This server provides AI tools and requires the corresponding Revit plugin to function.