APA 7th edition citation formatting and reference validation agent. Use this agent to: Format all references in APA 7th edition Validate in-text citations match reference list Check DOI availability and format Detect orphan citations and missing references Produce a final validated references.txt.
Research gap identification agent for geo/RS/GIScience papers. Use this agent to: Identify methodological, geographic, and thematic gaps in the literature Rank gaps by novelty, feasibility, and impact Connect gaps to research questions in program.md Output a ranked gap list for hypothesis generation.
Geospatial domain expert agent that injects spatial analysis context into the research pipeline. Use this agent to: Recommend appropriate spatial methods for the research question Suggest open-source datasets with spatial coverage and resolution Review spatial analysis code for CRS, projection, and autocorrelation…
Research hypothesis generation and scoring agent. Use this agent to: Generate testable research hypotheses from identified gaps Score hypotheses on novelty, feasibility, and alignment with program.md Suggest datasets and methods for each hypothesis Rank hypotheses and recommend the top candidate(s).
Literature search and paper retrieval agent for geo/RS/GIScience research. Use this agent to: Search ArXiv, Semantic Scholar, and CrossRef for relevant papers Build a paper cache with metadata and abstracts Identify papers from priority geo venues (RSE, IJGIS, IEEE TGRS, etc.) Filter by year range, citation count, and…
Full research pipeline orchestrator for NORA. Use this agent when: Starting a new research project from program.md Running the full iterative research loop end-to-end Coordinating specialist agents across a multi-session workflow Resuming a paused research session from saved state Managing section-by-section paper…
Academic paper section writing agent for geo/RS/GIScience papers. Use this agent to: Write individual paper sections (abstract, intro, lit review, methods, results, discussion, conclusion) Self-score drafts on the 5-dimension rubric (novelty, rigor, lit coverage, clarity, impact) Revise sections based on specific…
Simulated peer reviewer agent for geo/RS/GIScience papers. Use this agent to: Review a section or full paper from three reviewer perspectives Identify major and minor issues with specific line-level feedback Produce a formal review with a decision recommendation (Accept/Minor/Major/Reject) Generate a "path to…
Deep literature reading and knowledge extraction agent. Use this agent to: Analyze the paper cache and build a synthesis matrix Identify methodological approaches, datasets, and key findings Write a structured literature synthesis with thematic organization Extract numerical results for comparison tables Surface…
You are the interactive launcher for NORA — Night Owl Research Agent. Your job is to guide the user through a structured intake interview, gather all necessary information, write the configuration files, and then invoke the full-pipeline skill.
Gives the agent read and write access to a set of allowed directories on the local filesystem. Runs locally from the @modelcontextprotocol/server-filesystem npm package.
MCP server "geomcp" as configured in GRIND-Lab-Core/nightowlresearchagent. Runs mcp/geo_mcp_server.py with python. Needs 3 environment variables to run.
Lets the agent work with GitHub: search code, read and create issues and pull requests, and manage repositories through the GitHub API. Runs locally from the @modelcontextprotocol/server-github npm package. Needs 1 environment variable to run.
Lets the agent search the web and local businesses through the Brave Search API. Runs locally from the @modelcontextprotocol/server-brave-search npm package. Needs 1 environment variable to run.
Claude Code instructions for GRIND-Lab-Core/night_owl_research_agent, covering nora — dashboard, pipeline status, control flags, constants and session start checklist.
Adversarial iterative review loop with generator-evaluator separation. Up to 4 rounds of independent review, improvement, and re-evaluation. Persists state to output/REVIEWSTATE.json for recovery. Stop: score ≥ 7.5/10 on all dimensions, or 4 rounds. Writes full history to output/AUTOREVIEWREPORT.md.
Discover, evaluate, and download publicly available datasets from the internet. Infers data needs from a research question or task, selects authoritative sources, downloads reproducibly, validates file integrity, and documents provenance. Pauses for user input when authentication, API keys, or major tradeoffs require…
Deploy and run experiments for ML/DL training (local, remote, or Modal GPU) AND spatial data science / GIScience experiments (local, data-driven). Reads from output/refine-logs/EXPERIMENTPLAN.md and output/refine-logs/FINALPROPOSAL.md, writes to output/experiment/. Use when user says "run experiment", "deploy…
Run an end-to-end workflow that chains the skills refine-research and experiment-design. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to build a pipeline, do it end-to-end, or generate both the method and experiment plan…
Turn a refined GIScience / remote sensing / spatial data science proposal into a detailed, claim-driven experiment roadmap. Use after refine-research, or when the user asks for a detailed experiment plan, ablation matrix, spatial evaluation protocol, run order, compute budget, or paper-ready validation that supports…
Generate and rank research ideas given a broad direction. Use when user input "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.