Fixed Income Corporate logo

Fixed Income Corporate

Community
JoelLewis
fixed-income-corporate

Analyze corporate bonds and credit instruments including investment grade and high yield debt. Use when the user asks about corporate bonds, credit spreads (OAS, Z-spread, G-spread), credit ratings, default probabilities, callable bonds, or private credit. Also trigger when users mention 'junk bonds', 'fallen angel', 'yield-to-worst', 'covenant analysis', 'CDS spreads', 'recovery rates', 'direct lending', 'mezzanine debt', 'BBB downgrade risk', or ask how to evaluate corporate credit risk.

Overview

PublisherJoelLewis
Repositoryfinance_skills
Skill namefixed-income-corporate
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 Corporate 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-corporate
  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-corporate .claude/skills/fixed-income-corporate
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Fixed Income Corporate 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 Corporate 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 Corporate 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 — Corporate

Core Concepts

Credit Spreads

Compensation for default risk, liquidity risk, and downgrade risk above the risk-free rate. Multiple spread measures exist with increasing precision:

G-spread (Government Spread): Bond yield minus interpolated Treasury yield of the same maturity. Simple but assumes a flat term structure between benchmark maturities.

Z-spread (Zero-Volatility Spread): The constant spread added to each point on the risk-free spot rate curve such that the sum of discounted cash flows equals the bond's market price. Superior to G-spread because it accounts for the full shape of the term structure.

OAS (Option-Adjusted Spread): For bonds with embedded options, OAS = Z-spread minus the value of the embedded option. OAS represents the "true" credit compensation after removing the option component. Requires an interest rate model to compute.

Credit Ratings

AAA/AA/A/BBB are investment grade. BB/B/CCC/CC/C/D are high yield (speculative grade). The BBB/BB boundary is the most consequential threshold — many institutional mandates prohibit sub-investment-grade holdings. A downgrade across this boundary ("fallen angel") forces selling by constrained investors.

Migration Matrix

A transition matrix shows the probability of moving from one rating to another over a 1-year horizon. A BBB-rated issuer has roughly 85-90% probability of remaining BBB, 4-5% chance of upgrade, 4-5% chance of downgrade, and a small probability (~0.2%) of default. Migration matrices are published annually by rating agencies.

Default Probability, Loss Given Default, and Recovery Rate

  • PD = Probability of Default over a given horizon
  • LGD = Loss Given Default (percentage of exposure lost)
  • Recovery Rate (RR) = 1 - LGD
  • Expected Loss: EL = PD × LGD × EAD (Exposure at Default)

Recovery rates vary by seniority: senior secured (60-65%), senior unsecured (40-50%), subordinated (20-30%).

Callable Bonds

The issuer can redeem the bond early. Call schedules specify prices and dates. Yield-to-call (YTC) is calculated using the call date and call price. Yield-to-worst (YTW) is the minimum of YTM and all possible YTCs. For callable bonds, OAS is the appropriate spread measure (not G-spread or Z-spread).

Covenants

Maintenance covenants: Tested periodically (e.g., quarterly). Issuer must maintain financial ratios at all times. Common in bank loans.

Incurrence covenants: Tested only when the issuer takes a specific action (e.g., issues new debt). Common in bond indentures. Key covenants include leverage ratio (Debt/EBITDA), interest coverage (EBITDA/Interest), and restricted payments.

Private Credit

Direct lending by non-bank lenders to middle-market companies. Offers an illiquidity premium of 150-400bp over comparable syndicated loans. Typically features stronger covenant protection than public market deals. Valuations are mark-based (quarterly), which smooths reported volatility.

CDS (Credit Default Swaps)

A derivative where the protection buyer pays a periodic spread and receives payment upon a credit event. CDS spreads can be used to derive market-implied default probabilities. CDS spreads are often more responsive to credit deterioration than bond spreads.

Key Formulas

FormulaExpressionUse Case
G-spreadBond Yield - Interpolated Treasury YieldSimple spread measure
Z-spreadConstant spread s: P = sum CF_t / (1+s_t+s)^tFull curve spread
OASZ-spread - Option CostSpread for callable bonds
Expected LossEL = PD × LGD × EADCredit loss estimation
Recovery RateRR = 1 - LGDRecovery from default
Yield-to-Worstmin(YTM, YTC_1, YTC_2, ...)Conservative yield measure

Worked Examples

Example 1: Compare Z-spread vs G-spread

Given: A 7-year corporate bond yields 5.8%. The 7-year interpolated Treasury yield is 4.5%. The Z-spread (computed using the full spot curve) is 118bp. Calculate: G-spread and compare to Z-spread Solution: G-spread = 5.8% - 4.5% = 1.30% = 130bp Z-spread = 118bp The G-spread (130bp) exceeds the Z-spread (118bp) by 12bp. This difference arises because the G-spread uses a single interpolated benchmark point while the Z-spread properly accounts for the shape of the entire yield curve. In a steep curve environment, G-spread tends to overstate the true spread.

Example 2: Expected Loss Calculation

Given: PD = 2% (annual), LGD = 60%, EAD = $1,000,000 Calculate: Expected annual loss Solution: EL = PD × LGD × EAD EL = 0.02 × 0.60 × $1,000,000 EL = $12,000

The expected annual credit loss is $12,000, or 1.2% of the exposure. This represents the actuarial cost of credit risk — the spread must at least cover this expected loss, with additional compensation for unexpected losses and risk aversion.

Common Pitfalls

  • Using G-spread for callable bonds — use OAS instead, which removes the option component
  • Ignoring liquidity premium in spread analysis — part of the spread compensates for illiquidity, not just default risk
  • Rating agency lag vs market-implied credit quality — CDS spreads often move before rating actions
  • Assuming recovery rates are constant — they vary significantly by seniority and economic cycle (lower in recessions)

Cross-References

  • fixed-income-sovereign (wealth-management plugin): the Treasury curve used as the risk-free benchmark
  • fixed-income-structured (wealth-management plugin): CLOs and structured credit products
  • alternatives (wealth-management plugin): private credit as an alternative investment
  • asset-allocation (wealth-management plugin): credit allocation in multi-asset portfolios

Running the Script

bash
uv run scripts/fixed_income_corporate.py            # run the demo (uses PEP 723 inline deps)
uv run scripts/fixed_income_corporate.py --verify   # check demo outputs against the worked examples (exit 1 on mismatch)
python3 scripts/fixed_income_corporate.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_corporate.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 Corporate AI skill do?

Analyze corporate bonds and credit instruments including investment grade and high yield debt. Use when the user asks about corporate bonds, credit spreads (OAS, Z-spread, G-spread), credit ratings, default probabilities, callable bonds, or private credit. Also trigger when users mention 'junk bonds', 'fallen angel', 'yield-to-worst', 'covenant analysis', 'CDS spreads', 'recovery rates', 'direct lending', 'mezzanine debt', 'BBB downgrade risk', or ask how to evaluate corporate credit risk.

Why use Fixed Income Corporate on TypingMind?

Because you install it once and use it with any model. Fixed Income Corporate 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 Corporate 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-corporate. 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 Corporate?

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 Corporate?

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

Is the Fixed Income Corporate 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 👇