Agent skill

Fixed Income Structured

by JoelLewis in JoelLewis/finance_skills

Analyze structured fixed income products including mortgage-backed securities, asset-backed securities, and CLOs.

MITAuto-check passedBusiness, Finance & HR

Install Fixed Income Structured

skills CLI
$ npx skills add JoelLewis/finance_skills --skill fixed-income-structured -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install JoelLewis/finance_skills fixed-income-structured --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/JoelLewis/finance_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/wealth-management/skills/fixed-income-structured .claude/skills/fixed-income-structured && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
fixed-income-structured
GitHub stars
206
Token cost
~1.9k tokens
SKILL.md length
907 words
Files
2 (incl. scripts)
Skills in repo
91
Repo updated
First seen
Licence
MIT

At a glance

Analyze structured fixed income products including mortgage-backed securities, asset-backed securities, and CLOs.

  • The user asks about MBS
  • SKILL.md covers Core Concepts, Key Formulas, Worked Examples and Common Pitfalls, plus 2 more sections
  • Runs Python scripts from its folder; calls uv, python3 and python
  • Prepayment risk

What it does

Fixed Income Structured is an agent skill from JoelLewis/finance_skills. Analyze structured fixed income products including mortgage-backed securities, asset-backed securities, and CLOs. Use when the user asks about MBS, ABS, CLOs, CDOs, prepayment risk, tranching, or waterfall structures. Also trigger when users mention 'mortgage bonds', 'agency MBS', 'pass-through securities', 'PSA prepayment speed', 'negative convexity', 'extension risk', 'contraction risk', 'CMO tranches', 'securitization', or ask how structured products redistribute credit and prepayment risk.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/fixed_income_structured.py`).

It sits in Business, Finance & HR, covering Real estate. The repository describes itself as: Claude Code skill plugins for financial services — 81 skills across 7 domain plugins covering investment management, compliance, advisory practice, trading, and operations. The licence is MIT.

When your agent uses it

  • The user asks about MBS
  • Prepayment risk
  • Waterfall structures
  • Users mention mortgage bonds

Example prompts

  • “mortgage bonds”
  • “agency MBS”
  • “pass-through securities”
  • “/fixed-income-structured”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 5c498ea. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • uv
    • python3
    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Fixed Income Structured loads about 1.9k tokens when it runs. Until then it costs about 131 tokens; SKILL.md has 907 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~131
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from JoelLewis/finance_skills at commit 5c498ea, republished under its MIT licence (© JoelLewis). 907 words, ~1,938 tokens.

Download SKILL.mdSave it as .claude/skills/fixed-income-structured/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
fixed-income-structured
description
Analyze structured fixed income products including mortgage-backed securities, asset-backed securities, and CLOs. Use when the user asks about MBS, ABS, CLOs, CDOs, prepayment risk, tranching, or waterfall structures. Also trigger when users mention 'mortgage bonds', 'agency MBS', 'pass-through securities', 'PSA prepayment speed', 'negative convexity', 'extension risk', 'contraction risk', 'CMO tranches', 'securitization', or ask how structured products redistribute credit and prepayment risk.

Fixed Income — Structured Products

Core Concepts

MBS Pass-Throughs

A pool of mortgages whose cash flows (principal, interest, prepayments) are passed through to investors on a pro-rata basis. Agency MBS (Ginnie Mae, Fannie Mae, Freddie Mac) carry a government or GSE guarantee against credit losses, isolating prepayment risk as the primary concern. Non-agency MBS lack this guarantee and carry both credit and prepayment risk.

Prepayment Risk

Borrowers can refinance when rates drop, returning principal early. This creates negative convexity — when rates fall, MBS prices rise less than comparable Treasuries because prepayments accelerate and shorten the bond's effective life. Prepayment risk has two faces:

Contraction risk: Rates fall, prepayments accelerate, duration shortens. Investors receive principal back when reinvestment rates are lower.

Extension risk: Rates rise, prepayments slow, duration extends. Investors are locked into below-market coupons for longer than expected.

PSA Prepayment Model

The Public Securities Association model provides a benchmark prepayment speed:

100% PSA = ramp from 0% CPR to 6% CPR linearly over the first 30 months, then constant at 6% CPR thereafter.

At 150% PSA, all speeds are multiplied by 1.5 (e.g., the plateau is 9% CPR). At 200% PSA, the plateau is 12% CPR.

CPR and SMM

CPR (Conditional Prepayment Rate): Annualized prepayment rate as a percentage of the remaining pool balance.

SMM (Single Monthly Mortality): Monthly prepayment rate.

SMM = 1 - (1 - CPR)^(1/12)

Weighted Average Life (WAL)

WAL = sum(t × Principal_t) / Total Principal. Unlike maturity, WAL accounts for the timing of principal repayments (both scheduled and prepayments). WAL is shorter than maturity for amortizing securities and is sensitive to prepayment assumptions.

CMO Tranches

Collateralized Mortgage Obligations redistribute MBS cash flows into tranches with different risk profiles:

Sequential pay: Principal flows to the first tranche until retired, then the second, etc. Earlier tranches have shorter duration, later tranches have longer duration.

PAC (Planned Amortization Class): Provides a predictable principal schedule within a band of prepayment speeds (e.g., 100-250% PSA). Stability comes at the expense of companion/support tranches that absorb prepayment variability.

Support/Companion tranches: Absorb excess or deficit prepayments to protect PAC tranches. Highly volatile duration.

ABS (Asset-Backed Securities)

Securitized pools of non-mortgage assets:

  • Auto loans: amortizing, relatively predictable cash flows
  • Credit cards: revolving, with a revolving period followed by a controlled amortization period
  • Student loans: longer duration, income-driven repayment creates uncertainty
CLOs (Collateralized Loan Obligations)

Tranched portfolios of leveraged loans (typically 150-250 loans). AAA tranches benefit from significant subordination (30-40% of the structure below them). Equity tranches receive residual cash flows after all senior tranches are paid. Waterfall tests (overcollateralization and interest coverage tests) redirect cash flows to protect senior tranches when the portfolio deteriorates.

Waterfall Structure

Cash flows are distributed by seniority: senior tranches receive interest and principal first, mezzanine next, equity last. If pool performance deteriorates, lower tranches absorb losses first (subordination protects senior tranches). Overcollateralization (OC) tests and interest coverage (IC) tests trigger cash flow diversions when breached.

OAS for Structured Products

OAS is essential for MBS because it captures prepayment optionality. Standard modified duration is inappropriate for MBS — use effective duration (computed via OAS models) or empirical duration. Monte Carlo simulation of interest rate paths and corresponding prepayment responses is the standard valuation approach for MBS.

Show full SKILL.md (379 more words)Show less

Key Formulas

FormulaExpressionUse Case
SMM from CPRSMM = 1 - (1-CPR)^(1/12)Monthly prepayment rate
CPR from SMMCPR = 1 - (1-SMM)^12Annualize monthly rate
PSA CPR (month t, t<=30)CPR = 6% × (t/30) × PSA/100Ramping prepayment model
PSA CPR (month t, t>30)CPR = 6% × PSA/100Plateau prepayment model
WALsum(t × Principal_t) / Total PrincipalAverage principal timing
OAS PriceP = E[sum CF_t(path) / (1+s_t+OAS)^t]MBS valuation

Worked Examples

Example 1: Convert PSA to CPR

Given: 150% PSA, month 20 Calculate: CPR and SMM in month 20 Solution: At 100% PSA, month 20: CPR = 6% × (20/30) = 4.0% At 150% PSA: CPR = 4.0% × 1.5 = 6.0% SMM = 1 - (1 - 0.06)^(1/12) = 1 - (0.94)^(0.0833) = 1 - 0.99486 = 0.00514 = 0.514%

In month 20 at 150% PSA, approximately 0.514% of the remaining pool balance prepays each month, equivalent to 6.0% annualized.

Example 2: CLO Tranche Analysis

Given: A CLO with $500M total assets. AAA tranche = $325M (65%), AA = $50M (10%), A = $37.5M (7.5%), BBB = $25M (5%), BB = $12.5M (2.5%), Equity = $50M (10%). Calculate: Subordination level for the AAA tranche Solution: Subordination below AAA = AA + A + BBB + BB + Equity = $50M + $37.5M + $25M + $12.5M + $50M = $175M Subordination % = $175M / $500M = 35%

The AAA tranche has 35% subordination — the portfolio would need to lose more than 35% of its value before AAA investors suffer any principal loss. This substantial credit enhancement is why CLO AAA tranches have historically experienced zero defaults.

Common Pitfalls

  • Ignoring negative convexity of MBS — MBS underperform Treasuries in both rallies (contraction) and selloffs (extension)
  • Using modified duration for MBS — use effective/OAS duration instead, as cash flows change with rates
  • Assuming constant prepayment speeds — speeds vary with rates, seasonality, borrower demographics, and housing turnover
  • Not understanding that waterfall mechanics affect tranche risk differently — senior and subordinate tranches of the same deal have very different risk profiles

Cross-References

  • fixed-income-sovereign (wealth-management plugin): the Treasury curve and duration/convexity concepts
  • fixed-income-corporate (wealth-management plugin): credit spread concepts applied to non-agency MBS and CLOs
  • real-assets (wealth-management plugin): real estate market fundamentals underlying MBS
  • asset-allocation (wealth-management plugin): structured products in multi-asset portfolios

Running the Script

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

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_structured.py.

© JoelLewis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in plugins/wealth-management/skills/fixed-income-structured of JoelLewis/finance_skills.

  • SKILL.md
  • scripts/fixed_income_structured.py

Open the folder on GitHubat commit 5c498ea

Compare with similar skills

Fixed Income Structured next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Fixed Income Structured compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fixed Income Structured this skillJoelLewis/finance_skills206—~1.9kAutomated safety check: PassMIT
Thue Tncn Vietnamdotanminh/thue-tncn-vietnam241—~2.8kAutomated safety check: PassNone
Apartment Finderhanzili/hanzi-browse177—~2.1kAutomated safety check: PassCustom licence
Realestate Commercialzubair-trabzada/ai-realestate-claude179—~3.2kAutomated safety check: PassMIT
Vet PRetewiah/awesome-real-estate375—~1.5kAutomated safety check: PassCC0-1.0
Realestate Comparezubair-trabzada/ai-realestate-claude179—~3.7kAutomated safety check: PassMIT

Similar skills

  • Thue Tncn Vietnam

    dotanminh/thue-tncn-vietnam

    A skill your agent uses when user asks about Vietnamese personal income tax (TNCN), tax finalization (quyet toan), dependent deductions (giam tru gia canh), freelancer/KOL/online seller tax, eTax…

    241 GitHub stars~2.8k tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed
  • Apartment Finder

    hanzili/hanzi-browse

    Search for apartments across multiple real estate platforms, compare listings side by side, and help submit inquiries or applications.

    177 GitHub stars~2.1k tokensUpdated 5 mo ago
    Business, Finance & HRAuto-check passed
  • Realestate Commercial

    zubair-trabzada/ai-realestate-claude

    Commercial Property Analysis — NOI, cap rate, expense ratio, tenant mix, vacancy, debt coverage, replacement cost, and lease analysis with Commercial Score (0-100)

    179 GitHub stars~3.2k tokensUpdated 5 mo ago
    Business, Finance & HRAuto-check passed
  • Vet PR

    etewiah/awesome-real-estate

    Rigorous checklist for triaging PRs on the awesome-real-estate list.

    375 GitHub stars~1.5k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • Realestate Compare

    zubair-trabzada/ai-realestate-claude

    Side-by-Side Property Comparison — takes two addresses and compares across price, specs, rental income, neighborhood, and investment potential with a winner per category and overall recommendation

    179 GitHub stars~3.7k tokensUpdated 5 mo ago
    Business, Finance & HRAuto-check passed
  • Taichung Land Parcel Query

    h30190/HJPLUS_Taiwan_Architect_KB

    This skill should be used when an architect receives just an address or lot number (地號) for a site in Taichung City, Taiwan, and needs the land's basic data — zoning, registered land area, land…

    158 GitHub stars~1.9k tokensUpdated 3 days ago
    Business, Finance & HRAuto-check passed

More from JoelLewis/finance_skills

All 91 skills in this repo
  • Asset Allocation

    JoelLewis/finance_skills

    Determine how to distribute capital across asset classes using strategic and tactical allocation frameworks.

    206 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Bet Sizing

    JoelLewis/finance_skills

    Determine how much capital to allocate to individual positions within a portfolio.

    206 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Commodities

    JoelLewis/finance_skills

    Analyze commodity markets including futures curve dynamics, roll yield, and supply/demand fundamentals.

    206 GitHub stars~1.9k tokensUpdated 2 mo ago
    Auto-check passed
  • Currencies And Fx

    JoelLewis/finance_skills

    Analyze currency markets, exchange rate mechanics, and FX risk management for international portfolios.

    206 GitHub stars~1.9k tokensUpdated 2 mo ago
    Auto-check passed
  • Debt Management

    JoelLewis/finance_skills

    Provide frameworks for managing and paying off personal debt effectively.

    206 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Diversification

    JoelLewis/finance_skills

    Build diversified portfolios using correlation analysis, efficient frontier construction, and factor-based diversification.

    206 GitHub stars~2.3k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Fixed Income Structured

What does Fixed Income Structured do?

Analyze structured fixed income products including mortgage-backed securities, asset-backed securities, and CLOs. Fixed Income Structured is an agent skill from JoelLewis/finance_skills. Analyze structured fixed income products including mortgage-backed securities, asset-backed securities, and CLOs.

When should I use Fixed Income Structured?

Fixed Income Structured fits situations like: the user asks about MBS; prepayment risk; waterfall structures; users mention mortgage bonds.

How do I install Fixed Income Structured in Claude Code?

Run `npx skills add JoelLewis/finance_skills --skill fixed-income-structured -a claude-code`. Or copy the skill folder (plugins/wealth-management/skills/fixed-income-structured in JoelLewis/finance_skills) into .claude/skills/fixed-income-structured in your project. Claude Code loads it when a task matches its description.

How do I install Fixed Income Structured in Codex?

Run `npx skills add JoelLewis/finance_skills --skill fixed-income-structured -a codex`. Or copy the skill folder (plugins/wealth-management/skills/fixed-income-structured in JoelLewis/finance_skills) into .agents/skills/fixed-income-structured in your project. Codex loads it when a task matches its description.

Can I use Fixed Income Structured in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JoelLewis/finance_skills --skill fixed-income-structured -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fixed-income-structured, .gemini/skills/fixed-income-structured, .github/skills/fixed-income-structured and .opencode/skills/fixed-income-structured in your project.

What does Fixed Income Structured need to run?

Going by SKILL.md and its folder, Fixed Income Structured needs Python for the scripts in its folder and the command-line tools its instructions call (uv, python3 and python). Our summary lists: Python 3.

Does Fixed Income Structured access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Fixed Income Structured safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Fixed Income Structured use?

Fixed Income Structured is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Fixed Income Structured use?

About 1.9k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Fixed Income Structured?

Skills that share tags, products or a category with Fixed Income Structured: Thue Tncn Vietnam (dotanminh/thue-tncn-vietnam, 241 stars), Apartment Finder (hanzili/hanzi-browse, 177 stars), Realestate Commercial (zubair-trabzada/ai-realestate-claude, 179 stars) and Vet PR (etewiah/awesome-real-estate, 375 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fixed Income Structured?

JoelLewis (a GitHub user) maintains it in JoelLewis/finance_skills, which has 206 GitHub stars. The repository holds 91 skills in this directory. The repository was last updated on July 18, 2026.

Source: JoelLewis/finance_skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.