MCP App StoreMCP App StoreAgent Builder provides the agent-level workflow for creating, updating, and presenting custom AI agents. It guides the agent through collecting clear requirements, selecting appropriate tool categories and skills, and invoking create_agent or update_agent to instantiate the configured assistant. The skill enforces good defaults (descriptive names, explicit when-to-use wording) and safety around knowledge-base creation so agents can answer domain-specific questions.
Use this skill when a user asks explicitly to build or configure a chatbot/assistant, wants an agent tailored for a specific domain (e.g., data analysis, customer support), or needs an agent that integrates a website or uploaded documents as a knowledge base. It also applies when updating an existing agent's tools or knowledge bases.
Inferred compatibility: agent runtimes and orchestrators that support tool calls (create_agent / update_agent) such as Claude Code, Gemini/assistant runtimes, and agent frameworks that expose tool APIs.
Instructional SKILL.md for XAgent's agent-builder skill that guides users through creating and configuring custom AI agents with tools, knowledge bases, and settings. No bundled scripts — purely prompt-based. Well-written with clear error handling guidance and failure-mode instructions, though somewhat repetitive with multiple CRITICAL warnings restating similar points.
Clean skill with no security concerns. No scripts to test. Purely instructional content for guiding an agent through agent creation workflows within XAgent platform.
NGINX Integration
Integrate with NGINX via the Membrane CLI to query, manage, and proxy requests to NGINX for configuration, logs, and runtime operations.
Retriever (Membrane CLI)
Integrate Retriever search and discovery via the Membrane CLI — manage connections and run queries across Retriever data sources.
Yielding Bear — Unified LLM Routing
A unified LLM routing API that automatically routes requests to the cheapest capable model across providers to reduce inference cost by ~60-80%.
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Maestro Orchestrate
Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.
Run Execute
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
Overnight — Autonomous Long-Running Coding
Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges
tmux Remote Control
Control tmux sessions for interactive TTYs: send keystrokes, capture panes, orchestrate parallel coding agents, and monitor output safely.
