Fixed Income Sovereign logo

Fixed Income Sovereign

Community
JoelLewis
fixed-income-sovereign

Analyze US Treasury securities and interest rate risk: bond pricing, yield curve construction, duration, convexity, TIPS, and forward/spot rate analysis. Use when the user asks about Treasury bonds, yield curve construction, interest rate risk, duration, convexity, TIPS, or breakeven inflation rates. Also trigger when users mention 'T-bills', 'T-notes', 'bond pricing', 'yield to maturity', 'inverted yield curve', 'forward rates', 'spot rates', 'DV01', 'real yields', or ask how bonds react to interest rate changes.

Overview

PublisherJoelLewis
Repositoryfinance_skills
Skill namefixed-income-sovereign
Stars
217
Forks
37
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by JoelLewis on GitHub. Read the source before you install it.

Installation

Install the Fixed Income Sovereign AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/JoelLewis/finance_skills/tree/main/plugins/wealth-management/skills/fixed-income-sovereign
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/JoelLewis/finance_skills.git /tmp/finance_skills
mkdir -p .claude/skills
cp -r /tmp/finance_skills/plugins/wealth-management/skills/fixed-income-sovereign .claude/skills/fixed-income-sovereign
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Fixed Income Sovereign in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Fixed Income Sovereign on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Fixed Income Sovereign is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Fixed Income — Sovereign

Scope: US Treasuries and rates analytics. Sovereign credit risk — emerging market debt, default analysis, country risk spreads — is out of scope for this skill.

Core Concepts

Bond Pricing

The price of a bond is the present value of its future cash flows:

P = sum(t=1 to n) [C / (1+y)^t] + F / (1+y)^n

where C = coupon payment per period, y = yield to maturity per period, F = face value, n = total number of periods. For semi-annual bonds, divide the annual coupon by 2 and the annual yield by 2, and double the number of years to get n.

Yield to Maturity (YTM)

The discount rate y that solves the bond pricing equation — the single rate that equates the bond's market price to the present value of all future cash flows. Assumes reinvestment of coupons at the YTM rate. It is the standard yield measure for bonds.

Current Yield

Current Yield = Annual Coupon / Price. A simple income measure that ignores capital gains/losses and the time value of money.

Yield Curve: Spot Rates, Forward Rates, Par Curve

The spot curve gives zero-coupon yields for each maturity. The par curve gives coupon rates at which bonds would price at par. Forward rates are implied future rates derived from spot rates. The three curves contain equivalent information and can be derived from one another.

Bootstrapping the Spot Curve

Extract spot (zero-coupon) rates from par yields by starting at the shortest maturity and working outward. Each step uses previously derived spot rates to solve for the next spot rate.

Forward Rate

The implied rate between two future dates derived from spot rates:

f(t1,t2) = [(1+s_t2)^t2 / (1+s_t1)^t1]^(1/(t2-t1)) - 1

where s_t1 and s_t2 are spot rates for maturities t1 and t2.

Duration (Macaulay)

The weighted average time to receive cash flows, where weights are the present value of each cash flow as a proportion of the bond's price:

D_mac = (1/P) × sum(t × CF_t / (1+y)^t)

Measured in years. Longer maturity, lower coupon, and lower yield all increase duration.

Modified Duration

D_mod = D_mac / (1 + y/m)

where m = number of coupon periods per year. Gives the approximate percentage price change for a 1 percentage point change in yield: dP/P ≈ -D_mod × dy.

Dollar Duration (DV01)

The dollar change in price for a 1 basis point change in yield:

DV01 ≈ -D_mod × P × 0.0001

Used for hedging — match DV01 exposures to immunize a portfolio against parallel rate shifts.

Convexity

Measures the curvature of the price-yield relationship (second derivative):

C = (1/P) × sum(t(t+1) × CF_t / (1+y)^(t+2))

For option-free bonds, convexity is always positive — duration alone overstates losses and understates gains.

Price Change Approximation

ΔP/P ≈ -D_mod × Δy + 0.5 × Convexity × (Δy)²

The convexity term is a correction that becomes important for large yield changes.

TIPS (Treasury Inflation-Protected Securities)

Principal adjusts with CPI. The coupon rate is fixed but applied to the inflation-adjusted principal. Real yield = TIPS yield. Breakeven inflation = nominal Treasury yield - TIPS real yield. TIPS have a deflation floor that protects par value at maturity.

Key Rate Duration

Sensitivity to specific points on the yield curve (e.g., 2yr, 5yr, 10yr, 30yr). Allows analysis of non-parallel yield curve shifts such as steepening, flattening, or butterfly moves. Sum of key rate durations equals effective duration.

Key Formulas

FormulaExpressionUse Case
Bond PriceP = sum C/(1+y)^t + F/(1+y)^nPrice from yield
Current YieldAnnual Coupon / PriceSimple income measure
Forward Ratef(t1,t2) = [(1+s_t2)^t2 / (1+s_t1)^t1]^(1/(t2-t1)) - 1Implied future rate
Macaulay Duration(1/P) × sum(t × CF_t / (1+y)^t)Weighted avg time to cash flows
Modified DurationD_mac / (1 + y/m)% price sensitivity to yield
DV01D_mod × P × 0.0001Dollar price change per 1bp
Convexity(1/P) × sum(t(t+1) × CF_t / (1+y)^(t+2))Curvature of price-yield curve
Price ChangeΔP/P ≈ -D_mod×Δy + 0.5×Convexity×(Δy)²Estimate price impact of rate move

Worked Examples

Example 1: Price a 5-Year 4% Semi-Annual Coupon Bond at 5% YTM

Given: Face = $1,000, coupon = 4% (semi-annual), YTM = 5%, maturity = 5 years Calculate: Bond price Solution: Semi-annual coupon = $1,000 × 4% / 2 = $20 Semi-annual yield = 5% / 2 = 2.5% Number of periods = 5 × 2 = 10 P = $20 × [(1 - (1.025)^(-10)) / 0.025] + $1,000 / (1.025)^10 P = $20 × 8.7521 + $1,000 × 0.7812 P = $175.04 + $781.20 = $956.24

The bond trades at a discount ($956.24 < $1,000) because the coupon rate (4%) is below the market yield (5%).

Example 2: Modified Duration and Price Change Estimate

Given: A bond with Macaulay duration = 4.5 years, YTM = 5% (semi-annual), price = $956.24, convexity = 22.5 Calculate: Estimated price change for a +50bp rate increase Solution: D_mod = 4.5 / (1 + 0.05/2) = 4.5 / 1.025 = 4.39 years ΔP/P ≈ -4.39 × 0.005 + 0.5 × 22.5 × (0.005)² ΔP/P ≈ -0.02195 + 0.000281 = -0.02167 = -2.167% ΔP ≈ -2.167% × $956.24 = -$20.72 New price ≈ $956.24 - $20.72 = $935.52

Duration alone would estimate -2.195%; the convexity correction reduces the estimated loss by about 3bp.

Common Pitfalls

  • Confusing Macaulay and modified duration — Macaulay is in years, modified gives price sensitivity
  • Ignoring convexity for large yield changes — duration alone overstates losses and understates gains
  • Day count conventions (30/360 vs actual/actual) — Treasuries use actual/actual, corporates use 30/360
  • Clean price vs dirty price (accrued interest) — quoted prices exclude accrued interest, but settlement requires paying it

Cross-References

  • time-value-of-money (core plugin): discounting and present value fundamentals
  • fixed-income-corporate (wealth-management plugin): credit spreads over the sovereign curve
  • fixed-income-municipal (wealth-management plugin): muni-to-Treasury yield ratios
  • asset-allocation (wealth-management plugin): bonds as an asset class in portfolio construction

Running the Script

bash
uv run scripts/fixed_income_sovereign.py            # run the demo (uses PEP 723 inline deps)
uv run scripts/fixed_income_sovereign.py --verify   # check demo outputs against the worked examples (exit 1 on mismatch)
python3 scripts/fixed_income_sovereign.py            # alternative (requires: pip install numpy scipy)

The demo prints the calculations covered above; its values match the worked examples in this skill. Run --help for a list of the classes and functions. For programmatic use, import the module rather than running it — the demo only executes under python fixed_income_sovereign.py.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Fixed Income Sovereign AI skill do?

Analyze US Treasury securities and interest rate risk: bond pricing, yield curve construction, duration, convexity, TIPS, and forward/spot rate analysis. Use when the user asks about Treasury bonds, yield curve construction, interest rate risk, duration, convexity, TIPS, or breakeven inflation rates. Also trigger when users mention 'T-bills', 'T-notes', 'bond pricing', 'yield to maturity', 'inverted yield curve', 'forward rates', 'spot rates', 'DV01', 'real yields', or ask how bonds react to interest rate changes.

Why use Fixed Income Sovereign on TypingMind?

Because you install it once and use it with any model. Fixed Income Sovereign is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Fixed Income Sovereign in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/JoelLewis/finance_skills/tree/main/plugins/wealth-management/skills/fixed-income-sovereign. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Fixed Income Sovereign?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Fixed Income Sovereign?

As many as you like. As long as a model supports skills, you can use Fixed Income Sovereign with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Fixed Income Sovereign AI skill free?

Yes. It is published on GitHub by JoelLewis under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇