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.

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.

- 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

- 3 Essential Toolsfor AI Agents:

- get_default_skills()- Load skills with mode"always_loaded"
- list_available_skills()- List all enabled skills with modes
- load_full_skill_context(name)- Load dynamic skill on-demand

# 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

MCP configuration saved tomcp_settings.json- add this to your AI Agent's MCP settings.

⚠️Important: Copy the content ofMCP_instructions.mdto your AI Agent's System prompt or rules configuration.

Thesetup.shscript generatesmcp_settings.jsonwith 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": {} } }

AI Agents need only these 3 tools. Usage details are inMCP_instructions.md(system prompt):

The repository includes starter content inMySkillsHUB/:

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.

- best-standard-autonomous-coding
- elite-cognitive-operator-system
- plan-mode

All content is automatically copied to your library on first setup.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

What Shopify did for ecommerce, Chipp does for AI agents. Build, deploy, and monetize AI agents for your business — no engineering team required.

CodeVF MCP lets AI hand off problems to real engineers instantly, so your workflows don’t stall when models hit their limits.

Client implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.

Agent-native developer Q&A API with MCP + A2A endpoints for citations, job pickup, and answer submission.

On-demand access to 150+ specialist AI agent templates — search, browse, and spawn agents. 150x reduction in context usage vs loading agents locally.

AgentChatBus is a persistent AI communication bus that lets multiple independent AI Agents chat, collaborate, and delegate tasks — across terminals, across IDEs, and across frameworks.

Remote MCP server (Streamable HTTP) at https://mcp.agenticrail.nz/ — deterministic step-order enforcement for AI agents. evaluate_step returns ALLOW or DENY before a step runs; verify_receipt proves a sequence's Ed25519-signed, hash-chained receipt chain is intact. No auth required: omit the bearer token and calls run on the public demo key. That first clause matters — the form has no "remote/hosted" field, and putting the endpoint in the description is the convention on that list ("Fully REMOTE! Just use…"). The rest mirrors your own server card verbatim, so the listing and the card can't drift.

An AI Agent with optional Human-in-the-Loop Safety and Model Context Protocol (MCP) integration.

Agent Mail Rooms is a paid remote MCP endpoint for OpenAI Codex agent coordination MCP. It exposes structured JSON tools, a public server card, token-based access, usage receipts, and audit-

MCP bridge that lets Claude Code delegate heavy tasks to the Antigravity CLI (agy) — purpose-built tools, model routing with fallback, session continuity, and output truncation to save Claude's context and tokens.