AI Skill Store

Excel(.xlsx) 읽기·쓰기·분석 — 엑셀 처리, xlsx 읽기, spreadsheet 데이터 추출. Offline, base64 I/O, no filesystem mount needed.

Apply JMESPath expressions to JSON data for path-based extraction and filtering. JSON 경로 추출, API 응답 필터링. Deterministic, offline, no external API.

Parse, validate, and extract fields from HL7 v2.x pipe-delimited messages. Structured JSON output per segment. Covers ADT, ORU, ORM, SIU message types for legacy hospital system integration.

Parses SQL DDL statements (CREATE TABLE, INDEX, CONSTRAINT) into structured JSON — tables, columns, types, constraints, foreign keys. Supports MySQL, PostgreSQL, BigQuery, Snowflake, MSSQL, SQLite with auto-dialect detection.

Open a SQLite .db file and run schema inspection, safe SELECT execution, EXPLAIN QUERY PLAN analysis, and index/stats queries. Zero external dependencies (Python stdlib sqlite3 only).

Convert JSON Schema / DDL / CSV headers to PySpark StructType code, and reverse-convert PySpark schemas to Avro or JSON Schema. No Spark runtime required.

CSV/TSV data validation toolkit — schema inference, type checking, null detection, duplicate detection, and quality reports (stdlib only)

JSON diff, patch (RFC 6902), and merge toolkit with 5 actions: diff, patch, merge, three_way_merge, audit. Zero external dependencies. Self-implemented RFC 6902 JSON Patch ops, 3-way merge with conflict detection.

Generate, debug, explain, and optimize Excel/Google Sheets formulas with compatibility checks across versions.

Data visualization code generator: auto-detects data shape, recommends chart type, generates matplotlib/plotly/D3 code, applies colorblind-safe Okabe-Ito palette. Zero external deps. Actions: recommend, generate_code, palette, audit, examples.

CSV content validator with 4 actions: validate, infer_schema, stats, audit. Zero external dependencies, Korean PII detection, fix_hint per error, Korean-first messages.

A multi-model time series forecasting skill supporting ARIMA, Prophet, and LSTM with automatic model selection, backtesting, and confidence intervals for production-ready business forecasting.

Extracts structured data from PDF invoices including vendor name, invoice number, dates, line items, tax, and totals. Part of FinanceFlow AI DocuParse Pipeline v2.

로그 파싱·군집·이상탐지·추출·위생검사 — 외부 의존성 0, 한국 PII 우선, 에이전트 네이티브 JSON. Parse, cluster, anomaly-detect, extract, and audit log lines with zero external dependencies and Korean-first PII detection.

Diagnose marketing/sales funnel bottlenecks. Input stage-by-stage conversion data, get drop-off analysis, benchmark comparison, and prioritized recommendations. No external packages required.

Design and analyze A/B tests. Calculate sample size, estimate test duration, evaluate statistical significance, and get next-action recommendations. No external packages required.

PowerPoint(.pptx) 파일을 읽고 생성하고 편집합니다. 텍스트 추출, 슬라이드 생성(테마/불릿/노트), 기존 파일에 슬라이드 추가 등 실무 기능을 제공합니다.

Excel(.xlsx) 파일을 읽고 쓰고 생성합니다. JSON 데이터로 Excel 생성, 시트 읽기, 셀 편집, 데이터 추가, 수치 요약 등 실무에 필요한 기능을 제공합니다.

Compare two JSON objects and return a structured diff — added, removed, and changed keys with values. No external dependencies.

PDF 파일에서 텍스트를 추출합니다. 로컬 파일 경로 또는 URL을 지원합니다. RAG 파이프라인 및 문서 분석에 활용합니다.