Prepare benefits and costs tables for a project before a cost-benefit analysis. Each item includes importance, sponsor cash flow, a measurement approach, and a monetary valuation method, using one of five supported appraisal frameworks.
Coordinate complex tasks across multiple agents through planning, execution, review, and revision. Agents save their work to local files and return status summaries, helping the main agent manage limited context while delivering the final result.
Prepare survey and administrative datasets for analysis with Python, R, or Stata. Generate cleaning code to handle missing values, duplicates, outliers, and derived variables, with documented transformations and integrity checks that support reproducible research.
Analyze interviews, focus groups, and open-ended survey responses using Braun and Clarke's six-phase framework. Label meaningful passages, develop and review themes, and produce an academic Word report with an annotated map showing theme relationships.
Analyze whether an intervention causes an outcome using DoWhy in Python. Build a graph of causal assumptions, determine whether the effect can be estimated, compare estimates, and test how well results withstand changes to assumptions or data.
Review difference-in-differences analyses, which compare changes across treated and comparison groups. It checks pre-policy trends, event-study charts, assumption violations, placebo tests, and robustness, then organizes findings and suggested revisions into a structured report.
Clean survey datasets using their codebooks, which explain variables and response codes. Check missing values and outliers, harmonize variables across years, and prepare combined data with a cleaning report, variable definitions, and recorded transformation history.
Evaluate policy effects with difference-in-differences, a method comparing changes in treated and untreated groups. Guides assumption checks, regression models, staggered adoption analysis, robustness checks, and reporting with event study plots.
Draft or revise introductions for economics papers using a clear sequence: motivation, research question, empirical approach, findings, and contribution to existing literature. A checklist helps identify vague claims, missing results, misplaced literature discussion, and excessive length.
Evaluate papers, research proposals, and literature reviews using structured criteria. Produces evidence-based feedback on research questions, methods, data, analysis, and writing, with optional scores and prioritized recommendations tailored to the work's stage and purpose.
Draft research funding proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Organize research aims, methods, expected contributions, budgets, and timelines around each agency’s review criteria and submission requirements, including revisions responding to reviewer feedback.
Evaluate research papers and scientific claims by examining study design, statistics, bias, and evidence quality. Receive a structured critique of strengths, weaknesses, supported conclusions, and practical improvements, with uncertainty and limitations made explicit.
Edit prose to remove formulaic AI phrasing, vague claims, inflated language, and repetitive structures. Apply context-appropriate tone to scientific papers, blog posts, and workplace documents, with review scores covering directness, rhythm, authenticity, and concision.
Develop literature reviews on AI for medical imaging, including segmentation, detection, and classification. Organize research from multiple sources into a structured manuscript with method comparisons, evaluation metrics, supporting citations, and limitations.
Develop a literature review from a focused research question through search planning, source evaluation, organization, and writing. It helps compare findings across papers, identify disagreements and research gaps, and build an outline with practical writing templates.
Proofread applied microeconomics manuscripts across prose, equations, tables, notes, and references. The workflow combines specialized reviews into a prioritized report with exact locations, suggested corrections, consistency checks, and items requiring author verification.
Coordinate research, drafting, citation and data verification, AI review, revision, and final formatting through connected skills. Start from a research topic, an existing manuscript, or reviewer comments, with progress tracking and user checkpoints.
Develop scientific manuscripts from literature-backed outlines into connected paragraphs. Organize introductions, methods, results, and discussions; integrate citations and figures; and adapt the manuscript to study reporting guidelines and the target journal’s requirements.
Turn observations or preliminary data into competing scientific hypotheses grounded in literature. Develop explanations, assess what could disprove them, and produce testable predictions and experimental designs in a structured report with diagrams.
Run empirical and causal analyses in Python with StatsPAI, from stating assumptions to estimating effects and checking how results change under alternative choices. Produce diagnostic figures, regression tables, and replication bundles for economics, public health, or machine learning studies.
Turn academic papers or written content into slide images, then combine them into PowerPoint and PDF files. The workflow extracts figures from PDFs and offers outline choices, visual styles, audience settings, and output languages.
Build Python code for economic models and policy evaluation, with guidance on choosing libraries, estimating effects, plotting results, and checking robustness. Covers macroeconomic simulation and causal inference, the analysis of cause and effect.
Interpret statistical models in R and Python using predictions, comparisons, and marginal effects, which describe how outcomes change with predictors. Get guidance on choosing quantities, evaluating scenarios, summarizing groups, measuring uncertainty, and testing hypotheses.
Turn observations or preliminary data into competing scientific hypotheses grounded in literature. It compares explanations, evaluates how they could be tested or disproved, and proposes experiments and measurable predictions in a structured report with diagrams.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)