New to Claude Skills? Learn how to install them →

anthropics on GitHub

Bond Relative Value Analysis

OfficialFree

Analyze bond pricing and risk with precision.

Get this skill

Free · Opens the source repo

What Bond Relative Value Analysis does

The Bond Relative Value Analysis skill is designed for fixed income analysts seeking to evaluate bonds based on their relative value. This skill integrates various financial metrics such as bond pricing, yield curves, credit spreads, and scenario stress testing to determine whether bonds are rich, cheap, or fairly valued. By leveraging the outputs of multiple MCP tools, users can synthesize comprehensive analyses that inform investment decisions.

At its core, this skill emphasizes the importance of spread decomposition, breaking down the total spread into its fundamental components: risk-free spread, credit spread, and residual spread. This decomposition allows analysts to understand the true richness or cheapness of a bond relative to its peers. Additionally, the skill facilitates scenario analysis, enabling users to stress test bonds under different interest rate environments, thereby confirming their assessments across varying market conditions.

The workflow begins with pricing the bond using the bond_price tool, followed by obtaining the risk-free and credit curves to compute the G-spread and residual spread. Users can then run parallel rate shift scenarios with the yieldbook_scenario tool to see how price changes and P&L would be affected. Historical context can also be analyzed using tscc_historical_pricing_summaries, providing a deeper insight into how current spreads compare to historical averages. This comprehensive approach allows users to make informed recommendations based on a thorough analysis of bond value.

This skill is particularly beneficial for financial analysts, portfolio managers, and anyone involved in fixed income investment strategies. By combining quantitative analysis with scenario testing, users can enhance their decision-making processes and better navigate the complexities of the bond market.

When to use it

Use this skill when you need to evaluate bonds for investment, particularly in assessing their relative value and risk.

When not to use it

This skill may not be suitable for users looking for basic bond pricing without the need for in-depth analysis or scenario testing.

What you can build with it

Assessing Bond Investment Opportunities

Use this skill to evaluate potential bond investments by analyzing their relative value against market benchmarks.

Conducting Stress Tests on Bond Portfolios

Run scenario analyses to understand how bond prices may react to interest rate changes, informing risk management strategies.

Comparing Bonds from Different Issuers

Utilize the skill to compare bonds from various issuers by decomposing their spreads and assessing their relative risk.

How to install Bond Relative Value Analysis

View source

1. Install with the skills CLI

npx skills add anthropics/financial-services/bond-relative-value --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by anthropics

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.

Available MCP Tools

  • bond_price — Price bonds. Returns clean/dirty price, yield, duration, convexity, DV01, Z-spread. Accepts ISIN, RIC, or CUSIP.
  • interest_rate_curve — Government and swap yield curves. Two-phase: list then calculate. Use to compute G-spreads.
  • credit_curve — Credit spread curves by issuer type. Two-phase: search by country/issuerType, then calculate. Use to isolate credit component.
  • yieldbook_scenario — Scenario analysis with parallel rate shifts. Returns price change and P&L under each scenario.
  • tscc_historical_pricing_summaries — Historical pricing data. Use for historical spread context and Z-score analysis.
  • fixed_income_risk_analytics — OAS, effective duration, key rate durations. Use for callable bonds and deeper risk decomposition.

Tool Chaining Workflow

  1. Price the Bond(s): Call bond_price for target and any comparison bonds. Extract yield, Z-spread, duration, convexity, DV01.
  2. Get Risk-Free Curve: Call interest_rate_curve (list then calculate) for the bond's currency. Interpolate at bond maturity to compute G-spread.
  3. Get Credit Curve: Call credit_curve for the issuer's country and type. Extract credit spread at the bond's maturity. Compute residual spread = G-spread minus credit curve spread.
  4. Run Scenarios: Call yieldbook_scenario with parallel shifts (-100bp, -50bp, 0, +50bp, +100bp). Extract price changes and P&L per scenario.
  5. Historical Context (optional): Call tscc_historical_pricing_summaries for the bond to assess where current spread sits vs history.
  6. Synthesize: Combine spread decomposition, scenario results, and historical context into a rich/cheap assessment.

Output Format

Spread Decomposition

ComponentSpread (bp)% of Total
G-spread (total over govt)...100%
Credit curve spread......%
Residual (liquidity + technicals)......%

Scenario P&L

ScenarioPrice ChangeP&L (per 100 notional)
-100bp......
-50bp......
Base......
+50bp......
+100bp......

Rich/Cheap Summary

State the primary spread metric, its historical context (percentile, comparison to averages), the residual spread signal, and a clear recommendation: rich (avoid/underweight), cheap (buy/overweight), or fair (neutral). Quantify how many bp of spread move would change the recommendation.

Frequently asked questions about Bond Relative Value Analysis

Similar skills