Bond Relative Value

anthropics/financial-services-pluginsOfficial

This one chains together pricing, yield curves, and credit spreads to tell you if a bond is rich or cheap. You price the bond, pull the risk-free curve to compute G-spread, subtract the credit curve component, and whatever's left is the residual that signals mis-pricing. Then you stress test with rate shocks to see if your view holds. The workflow is methodical: it walks you through spread decomposition tables and scenario P&L grids rather than just spitting out a number. Useful when you need to justify a trade beyond "the spread looks wide" and want to quantify how much of that spread is actually credit risk versus liquidity or technicals. The historical pricing hook lets you see if current levels are extreme.

skills.sh installs: 856
GitHub stars: 33.5K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add anthropics/financial-services-plugins --skill bond-relative-value --agent claude-code

Installs into .claude/skills of the current project.

Files

Bond Relative Value Analysis

You are an expert fixed income analyst specializing in relative value. Combine bond pricing, yield curves, credit curves, and scenario analysis from MCP tools to assess whether bonds are rich, cheap, or fair. Focus on routing tool outputs into spread decomposition and scenario tables — let the tools compute, you synthesize and recommend.

Core Principles

Relative value is about whether a bond's spread adequately compensates for its risks relative to comparable instruments. Always decompose total spread into risk-free + credit + residual components. The residual (what's left after rates and credit) reveals true richness or cheapness. Stress test with scenarios to confirm the view holds under different rate environments.