Skill UI

A comprehensive tool for importing structured data from various sources (CSV, JSON, Google Sheets) into connected platforms like CRMs, email marketing systems, or custom data stores. It manages the entire import pipeline, including automated field mapping, rigorous data validation, deduplication against existing records, and critical compliance verification (GDPR, CCPA). Features a mandatory execution gate for risk management.

A comprehensive tool for importing and validating leads into a CRM. It performs advanced data scrubbing, deduplication, and mandatory compliance checks (GDPR, CCPA). Leads are automatically scored and qualified (MQL/SAL), ensuring that only high-quality, clean data reaches the sales team, while low-scoring leads are automatically routed into nurture sequences. Supports CSV, JSON, and manual sources.

This guide outlines the mandatory data and code deposit policy for articles published in the Journal of Applied Econometrics (JAE). Authors must submit a complete, non-confidential set of input data (plain ASCII/CSV), programs that replicate every result, and a detailed README file. It emphasizes strict adherence to archival format rules, ensuring the research is fully reproducible for the academic community.

This guide provides a comprehensive, step-by-step preflight checklist for authors submitting manuscripts to the Journal of Applied Econometrics (JAE). It covers critical rules such as strict page limits (≤35 pages), summary word counts (≤100 words, citation-free), data archiving requirements (ASCII/CSV), and proper formatting to prevent administrative rejection before peer review.

This skill automates the creation of professional, multi-element Excel dashboards from raw CSV or tabular data. It structures the output with a dedicated 'Dashboard sheet' that serves as the primary landing view. Features include formula-driven KPI cards, linked charts, sparklines, and semantic conditional formatting. It is ideal for generating executive, analytics, or performance dashboards, ensuring that the user sees immediate, actionable insights without needing to navigate raw data sheets.

NetworkX is a powerful Python package designed for creating, manipulating, and analyzing complex networks and graphs. It supports various graph types (Directed, Undirected, MultiGraphs) and provides extensive functionality for graph algorithms, including shortest path calculation, centrality measures (like PageRank), community detection, and connectivity checks. Users can generate synthetic networks, read/write data from multiple formats (GraphML, CSV, Pandas), and visualize results using Matplotlib. Ideal for social network analysis, biological research, and system modeling.

This tool de-identifies sensitive free-text columns (e.g., names, dates, identifiers) in local structured datasets (CSV, JSONL, Parquet) using advanced OpenMed models. It ensures strict privacy by generating a completely redacted dataset and a separate PHI-free aggregate summary, allowing for secure data sharing and analysis without compromising source privacy or logging sensitive values.

This skill automatically detects and extracts tabular laboratory panels from diverse sources, including scanned images, photos, and delimited files (CSV/TSV). It converts complex visual data into clean, structured rows, capturing the test name, measured value, unit, reference range, and abnormal flag. It is essential for preparing medical data for subsequent standardization using LOINC and UCUM, and for mapping into FHIR resources.

Synthea generates statistically realistic, fully synthetic patient records in multiple standards (FHIR R4, C-CDA, CSV). This tool is essential for developers and researchers needing safe, shareable test data for OpenMed pipelines, CI fixtures, or specialized de-identification leakage gate test sets. It ensures zero risk of exposing real Protected Health Information (PHI).

This module converts diverse clinical inputs—including scanned images, faxes, CSV/TSV exports, and C-CDA XML—into a normalized, clean text format (`ExtractedDocument`). It supports on-device OCR (Tesseract/PaddleOCR) and structured redaction for tables. It is the crucial first stage for feeding de-identification and Named Entity Recognition (NER) pipelines.

A utility designed to read the contents of local data files by specifying their file path. This tool is useful for quick data inspection, initial data loading, or preliminary analysis when a user needs to access raw information from various file formats (e.g., TXT, CSV).

Displays a dashboard of all autoresearch experiments, showing results, active optimization loops, and progress. Supports per-experiment detail, domain filtering, and format export (Markdown/CSV) for sharing. Useful for monitoring ongoing experiments.