{"skill":{"slug":"claimback-radar","displayName":"Claimback Radar","summary":"Scans emails and bills to extract billing data, detect refund opportunities, subscription risks, and generate actionable savings recommendations.","tags":{"audit":"1.0.3","email":"1.0.3","finance":"1.0.3","latest":"1.0.3","refund":"1.0.3","savings":"1.0.3","subscription":"1.0.3"},"stats":{"comments":0,"downloads":98,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":4},"createdAt":1776870980136,"updatedAt":1776877312972},"latestVersion":{"version":"1.0.3","createdAt":1776874065172,"changelog":"# Changelog\n\nAll notable changes to this project will be documented in this file.\n\nThe format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),\nand this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).\n\n## [1.0.3] - 2026-04-23\n\n### Fixed\n\n- Unified package version to `1.0.3` across `pyproject.toml` and registry metadata\n- Added prominent `OPENAI_API_KEY` credential declaration to `README.md` and `SKILL.md` first lines\n- Removed unused `pydantic` dependency from `requirements.txt` and `pyproject.toml`\n- Clarified external data flow warning (OpenAI API) in registry metadata\n\n## [0.1.0] - 2026-04-22\n\n### Added\n\n- **Function 1: Structured Extraction** — Scans raw email/bill text and extracts service name, provider, amount, billing cycle, next charge date, refund deadline, warranty expiry, and cancellation method\n- **Function 2: Risk Detection & Action Generation** — Detects risks (upcoming charges, refund windows closing, unused services, price hikes, warranty expiring) and generates prioritized action receipts with deadlines and estimated savings\n- **Schema definitions** — `schema/input.json` and `schema/output.json` for strict validation of Skill invocation and response\n- **System prompt** — `prompts/system.txt` containing the core extraction and detection logic for LLM execution\n- **Reference implementation** — `src/runner.py` with `ClaimbackRadar` class, runnable via `main.py` CLI or imported as a module\n- **Examples** — Netflix subscription and Amazon Prime renewal cases with expected input/output\n- **Unit tests** — `tests/test_runner.py` covering prompt loading, valid output structure, and error handling\n- **Paper reference** — Links to Zenodo preprint (DOI: 10.5281/zenodo.19678205) and MDPI *Information* submission\n\n[1.0.3]: https://github.com/schchit/claimback-radar/releases/tag/v1.0.3\n[0.1.0]: https://github.com/schchit/claimback-radar/releases/tag/v0.1.0","license":"MIT-0"},"metadata":null,"owner":{"handle":"schchit","userId":"s1792pfv3byw2ah26z463sfgr184xckb","displayName":"JEP (Judgment Event Protocol)","image":"https://avatars.githubusercontent.com/u/10815391?v=4"},"moderation":null}