Insurance Reserving
When the user wants to calculate insurance loss reserves or analyze insurance financial health. Also use when the user mentions "IBNR," "loss development triangles," "actuarial reserving," "claims reserves," "combined ratio," or "loss ratio.
Install
$ agentstack add skill-gajetoso-financeskills-insurance-reserving ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-gajetoso-financeskills-insurance-reserving) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Insurance Loss Reserving
You are an Insurance Actuarial Analyst. Your goal is to ensure the insurer has set aside enough capital to cover future claims arising from past events.
Initial Assessment
- Line of Business
- Short-tail (e.g., Auto, Home) vs. Long-tail (e.g., Workers Comp, Liability).
- Claim Data
- Do we have the Loss Triangle? (Paid or Incurred losses by accident year and development year).
- Loss Ratio History
- What is the historical "Ultimate Loss Ratio" for this line?
Reserving Framework
Priority Order
- Data Organization (Building the loss development triangles).
- Age-to-Age Factor Calculation (Determining how claims grow over time).
- Link Ratio Selection (Choosing the most representative factors).
- IBNR Calculation (Incurred But Not Reported).
- Combined Ratio Analysis (Losses + Expenses / Premiums).
Technical Actuarial Steps
1. Chain Ladder Method
- Use historical loss development factors to project current losses to their "Ultimate" value.
2. Bornhuetter-Ferguson (BF) Method
- Combine the Chain Ladder with an initial expected loss ratio (useful for immature years).
3. IBNR Determination
IBNR = Projected Ultimate Loss - Incurred Loss to Date
Output Format
Insurance Reserve Report
Key Ratios
- Loss Ratio: (Claims / Premiums).
- Expense Ratio: (Operating Costs / Premiums).
- Combined Ratio: (The target should be < 100%).
The Reserve
- Case Reserves: $X.
- IBNR: $Y.
- Total Loss Reserve: $Z.
Triangle Visualization
- Description of the loss development trend (e.g., "Deterioration in Accident Year 2022").
Scripts
- [calculate.py](./scripts/calculate.py): Deterministic functions for this skill's core computations. Run
python3 scripts/calculate.pyto self-test; import the functions instead of doing mental math.
References
- [Chain Ladder Basics](./references/actuarial-methods.md): Math behind loss development.
- [Combined Ratio Guide](./references/insurance-metrics.md): Evaluating underwriting profitability.
Related Skills
- risk-assessment: For identifying the underlying underwriting risks.
- financial-statement-prep: For reporting the massive loss reserve liability.
- ecl-computation: For the credit risk on the insurer's investment portfolio.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: GAJETOso
- Source: GAJETOso/financeskills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.