Run an end-to-end actuarial reserving workflow for insurance/reinsurance: copy templates, execute Python scripts, track progress, apply chain-ladder LDF selection logic with diagnostic rules and tail factors, then generate a peer review report with advisory findings.
Get oriented with the TeamAnalyst plugin and explore available skills. Use when first getting started, checking what analysis capabilities are available, or surveying skills before beginning work. Trigger phrases "start", "get started", "what can you do", "help", "overview", "show skills".
Peer review of completed reserve analysis. Use after reserving-analysis workflow finishes. Do NOT use during initial analysis (separate skill exists).
Actuarial reserving analysis workflow. Use when the user requests reserving. Do NOT use for peer review (separate skill exists).
View the base actuarial LDF selection logic used for chain-ladder selections. Use when an actuary wants to review or understand the selection framework, criteria, and diagnostic rules.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Quick Start | Contribute | Repository Layout | How It Works | Resources | Install
TeamAnalyst is the result of a research initiative by the Casualty Actuarial Society (CAS) to explore the use of agentic tools in actuarial work. It targets a specific workflow: development of actuarial reserve ultimate estimates.
The project is a collection of Markdown files and Python scripts that agentic tools can use to run the workflow, organized to match the expected organization of these files for different tools.
DISCLAIMER: TeamAnalyst is a proof of concept and should be presented that way. It is not intended to be a complete, error-free, or production-approved actuarial system. The CAS does not guarantee the accuracy of the output, and users should not rely on the generated material as a final actuarial work product without appropriate professional review.
These files can be downloaded via git clone or Code (green button at the top of this page) > Download Zip.
These files can be used with many different agentic tools. For most users, we suggest Claude Cowork.
Instructions for other tools can be found here.
The video from our CAS presentation can be found at https://www.youtube.com/watch?v=8JZz2zYrim0. It is an edited screen recording of the plugin setup and workflow in Claude Cowork. It does not have audio but will give you a feel for the workflow.
These instructions are for Windows only. Mac/Linux is probably similar, if you find different steps please submit a PR to get them added.
teamanalyst-cowork.zip from https://github.com/cas-team-analyst/team-analyst/blob/main/plugins/teamanalyst-cowork.zipteamanalyst-cowork.zipNow you are ready to run the workflow! It may take 20-40 minutes to complete the workflow, so you may want to wait until you have about 40 minutes of free time.
If you want to just see what the output looks like, a sample workflow run with example output files is available at https://github.com/cas-team-analyst/team-analyst/tree/main/sample-data/sample-run.
/reserving-analysis (it will auto-complete and you can press enter to select it) in the chat box and press enter to get started!Additional skills are also available:
/help for orientation and help using the workflow/reserving-analysis for the full reserving workflow/selection-logic to inspect the LDF, tail, and ultimates selection strategy/peer-review perform AI peer review on a completed analysisTo go further:
See sections below on How It Works and Additional Resources
See the Executive Summary for a more detailed overview.
See guides for more information for advanced users looking to build on this work.
The CAS has generously funded this initial version. Now it is up to the community to expand it.
Contributions are welcome via Issues (the community may both add and resolve them) and Pull Requests.
For an introduction to collaborating on GitHub, we recommend this tutorial on Git and GitHub: https://www.w3schools.com/git/default.asp.
npx claudepluginhub cas-team-analyst/team-analyst --plugin team-analystCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer