When an AI agent operates swatplus-builder, it works under an explicit division of authority. This contract is what makes agent-operated runs trustworthy: the agent's capabilities are real, but bounded.
AI-Hydro is a VS Code–integrated agentic hydrology platform. swatplus-builder integrates with AI-Hydro as both an MCP server (13 tools available to the agent) and a registered skill (the agent loads SKILL.md to understand the system before touching tools).
Agent "mcp-server" from AI-Hydro/swatplus-builder, covering mcp server, start the server, register it with an agent client, tool input shape (req wrapper) and teach the agent the system: skill.md.
Parallelizes analysis across multiple USGS gauges or sites using sub-agent delegation. Orchestrates data fetching, signature extraction, and summary synthesis for a list of sites. Use when the researcher asks to "analyze all these gauges", "run this on the whole list", or "batch process these sites".
End-to-end workflow for authoring a multi-module AI-Hydro course: interview the user for audience and goals, propose a module breakdown with an explicit prerequisite graph, scaffold the files via the coursescaffold tool, then author each module's body. Use when the user asks to "build a course", "create a curriculum"…
Create interactive HTML playgrounds for exploring hydrological data — parameter sensitivity explorers, gauge comparison dashboards, return-period calculators, and catchment signature browsers. Use when the user asks for an interactive explorer, dashboard, playground, or visual tool to explore hydrological data or…
Guide the agent to create new AI-Hydro MCP tools — Python @mcp.tool() functions that extend the platform's hydrological analysis capabilities. Use when the user wants to add a new tool, wrap a hydrology library, expose a new data source, or build a custom analysis function for the AI-Hydro MCP server.
Create new AI-Hydro workflow skills and iteratively improve them. Use when the user wants to capture a hydrological workflow as a reusable skill, turn a completed analysis into a SKILL.md, author a new skill from scratch, or improve an existing skill's instructions or triggering accuracy.
Create publication-quality hydrological figures — hydrographs, flow duration curves, Budyko plots, exceedance probability charts, spatial maps, and multi-panel diagnostic displays. Use when the user asks for a plot, chart, figure, visualization, or wants to create a visual for a report, paper, or presentation. Applies…
Analyzes snowpack and snowmelt dynamics using SNOTEL or gridMET data. Computes Snow Water Equivalent (SWE) trends, melt timing (center of mass), and rain-on-snow event frequency.