night_owl_research_agent

Useful for

Use cases llm-inferred

Literature review and ranked research-gap analysis for a drainage or flood-risk evidence base before writing a technical note · Novelty check and spatial regression (OLS/GWR) on catchment attributes to support an evidence-based method statement · Dataset discovery and download with provenance logging from government portals for baseline environmental data · Consolidating pipeline outputs into a narrative technical report

Audience llm-inferred

GIS analysts · GIScientists · remote sensing researchers · geoscientists

Limitations

Constraints llm-inferred

Built for academic research workflows (papers, journal templates, reviewer loops); consultancy deliverables such as FRA or drainage design are not covered by the docs · Delivered as Claude Code skills (Markdown workflows), not as a standalone MCP data server; the tool names listed are skills · Requires Claude Code and paid Anthropic API usage · Track B spatial work needs a conda environment with geopandas, pysal, libpysal, esda, spreg, mgwr, rasterio and xarray; Track A deep-learning work needs a CUDA GPU (optional) · Requires copying the skills folder into ~/.claude/skills or a project .claude/skills directory before use · Licence not stated in metadata; maintenance status unknown · Automated pipelines are intended to run with human checkpoints; output needs expert review

Example tool calls docs-verified

{
  "tool": "lit-review",
  "arguments": {
    "$ARGUMENTS": "SuDS performance evidence for UK urban drainage strategies"
  }
}

{
  "tool": "data-download",
  "arguments": {
    "$ARGUMENTS": "UK river gauge daily flow records for the Thames catchment"
  }
}

{
  "tool": "spatial-analysis",
  "arguments": {
    "$ARGUMENTS": "Test whether catchment rainfall-runoff relationships vary spatially, with ESDA and conditional diagnostics"
  }
}