credit-risk

Assess credit risk and default probability for corporate bonds.

Updated Aug 27, 2026

Search Tags:#risk-management #default-probability #credit-risk #PD-LGD #credit-spreads

Ready to run

npx skills add https://github.com/keith-mvs/ordinis --skill credit-risk

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: credit-risk
Source: https://github.com/keith-mvs/ordinis/tree/main/docs/knowledge-base/domains/signals/fixed-income/credit-risk
Command: npx skills add https://github.com/keith-mvs/ordinis --skill credit-risk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, pandas, scipy, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides frameworks to evaluate issuer credit risk, downgrade probabilities, and market-implied default signals to support fixed income risk management and portfolio decisions.

Core Features & Use Cases

Fundamental vs Market-Implied Risk: Balance company fundamentals with market-implied default signals.
PD/LGD Modeling: Frameworks for estimating default probabilities and loss given default.
Rating Agency Context: Interpreting Moody's/S&P/Fitch scales and historical data.
Deliverables: PD/LGD dashboards, default-risk scoring, and risk monitoring templates.

Quick Start

Simple instruction: "Estimate implied default probability from given credit spread, recovery, and horizon."

Frequently Asked Questions about credit-risk

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I estimate implied default probability from credit spreads?▼

Implied default probability is calculated from credit spreads by using the spread, recovery rate, and time horizon. This Skill applies market-based models to derive probability estimates, enabling you to infer what the market is pricing for default risk without waiting for rating agency actions.

What's the difference between PD and LGD in credit risk analysis?▼

PD (probability of default) measures the likelihood an issuer will default; LGD (loss given default) estimates the percentage of principal lost if default occurs. This Skill provides frameworks to model both independently, then combine them into expected-loss calculations for portfolio decisions.

How can I monitor credit rating migrations and spread dynamics?▼

Credit rating migrations track issuer movements between rating tiers; spread dynamics measure how bond prices adjust to risk changes. This Skill delivers templates and dashboards to monitor these shifts across investment-grade and high-yield bonds, supporting early detection of credit deterioration.

Can I use this for corporate bond portfolio analysis?▼

Yes. This Skill is built for corporate bond and credit-portfolio analysis, letting you evaluate issuer fundamentals against market signals, analyze downgrade probability, and compare implied default risk across holdings to optimize allocation decisions.

What dependencies do I need to run credit risk assessments?▼

You need numpy (≥1.24.0), pandas (≥2.0.0), and scipy (≥1.10.0). These libraries enable numerical computation, data manipulation, and statistical modeling required to calculate PD, LGD, expected loss, and credit-spread decomposition outputs.

How do Moody's and S&P rating scales relate to default probability?▼

Rating scales from Moody's, S&P, and Fitch encode historical default frequencies tied to each tier. This Skill contextualizes rating agency frameworks and provides tools to interpret rating movements alongside market-implied signals for multi-dimensional risk assessment.