
from insurance-skills49
OCR and classify scanned PDFs with an LLM+vision pipeline, then organize files into category folders with markdown and metadata sidecars.
Extracts text from scanned PDFs (Docling + vision OCR), classifies documents into categories using a language model, and moves files into <scans_dir>/<category>/ with .md and .meta.json sidecars. Provides auditability via a manifest and supports dry-run, reclass, undo, and single-file processing.
Use when you have a directory of scanned PDFs that need automated text extraction, classification (medical, financial, insurance, tax, legal, personal, household, other), and structured output for downstream workflows (search, ingestion, compliance). Good for medical records, invoices, insurance paperwork, and bulk archive processing.
Best used with agents that can call shell tooling and file I/O (Copilot/Codex/CLI-capable agents). The skill assumes an OpenAI-compatible model endpoint for classification (OpenAI, Ollama, OpenRouter).
Scan Organizer processes scanned PDFs through a Docling + vision OCR pipeline, classifies them via LLM into categories (medical, financial, insurance, etc.), and organizes files into subfolders with markdown and metadata sidecars. No bundled scripts were present to test. The SKILL.md is well-structured with clear commands, output format, and architecture overview, but lacks error handling details and edge case guidance.
Clean skill with no security concerns. No hardcoded credentials, no remote code execution patterns, no destructive commands. The skill requires external LLM API access and uv package manager, which adds setup complexity. Source is from an insurance-focused org (FDU-INS), category scope is narrow (insurance document workflows) limiting broad usefulness.
Claims Guide & Decision Logic
Interactive step-by-step guide and decision-tree for handling insurance claims (accidents, health, liability, property, auto, legal, death, disability) with Swi
Coverage and Insurance
Generates clinical insurance/coverage resources modeling payer types (Medicare, Medicaid, commercial, VA, Tricare) and coverage periods for FHIR-style resources
Explore Korea (FlyAI)
CLI-driven trip planner for Korea (Seoul, Busan, Jeju) that uses the flyai CLI to fetch live flights, hotels, POIs and booking links.
PolicyPulse Development
Guidance for building PolicyPulse — a synthetic-population simulation dashboard with clean architecture, strong Python typing, and Streamlit UI patterns.
IGW Error Management
MCP skill for listing, analyzing, reporting, and managing InsurGateway (IGW) integration errors across test and production, with filters, reports, and write-saf
Car Rental Search (flyai CLI)
CLI-driven car rental search skill: run the flyai CLI to find and compare car rentals, returning validated booking links and formatted results.
Family Assistant (Insurance-focused)
Personal family assistant skill to help fill forms, schedule appointments, handle insurance claims, coordinate service providers, and manage household reference
PolicyPulse Development
Guides AI agents to build PolicyPulse: a Python-based synthetic population simulator with clean architecture, type-safe code patterns, and Streamlit dashboard d
Insurance Agent Customer CRM
Tools to extract, consolidate, and query customer insurance records from Excel/PDF/Word/PPT/images and generate follow-ups, reminders, and simple gap analyses.