Skip to main content

absbox

Model, project, and analyze structured finance deals (ABS, MBS, CLO, SRT) with the absbox Python library and Hastructure engine. Use for securitization modeling, deal maps, pool cashflow projection, bond waterfalls, tranche pricing, IRR/WAL, sensitivity analysis, root finding, and debugging projections. Python 3.10+.

v1.0.0New

Signing

SignedSLSA L2
Signed by
skills-hub.ai distributor
Method
Distributor-signed by skills-hub.aiCryptographically signed by the skills-hub.ai distributor key at publish time.
Signed

Install this skill

Run this command in your terminal. No account required — it auto-detects your AI tool and installs the skill file.

npx @skills-hub-ai/cli install absbox
Or download directly:
Browse all CLI commands →

Setup by platform

Claude Code

~/.claude/skills/<skill>/SKILL.md

Setup guide →

Codex CLI

~/.codex/skills/<skill>/SKILL.md, or reference via codex.md instructions file

Setup guide →

Cursor

~/.cursor/skills/<skill>/SKILL.md

Setup guide →

Windsurf

~/.windsurf/skills/<skill>/SKILL.md, or add to .windsurfrules in your project

Setup guide →

GitHub Copilot

.github/copilot-instructions.md (project-level), paste skill content into instructions

Setup guide →

Install

One-click setup for your editor

Run in your project root

npx @skills-hub-ai/cli install absbox --target claude-code
0Save

Examples

Prompt

Model a simple mortgage-backed security with a pool of loans and generate cashflow projections.

Output

import absbox
from absbox import API, EnginePath, mkDeal
api = API(EnginePath.PROD)
pool_assets = [
    ["Mortgage",
     {"originBalance": 200000, "originRate": ["fix", 0.04], "originTerm": 360, "freq": "Monthly", "type": "Level", "originDate": "2020-01-01"},
     {"currentBalance": 198000, "currentRate": 0.04, "remainTerm": 359, "status": "Current"}]
]
deal_data = {
    "name": "MortgagePoolDeal",
    "dates": {"cutoff": "2023-01-01", "closing": "2023-02-01", "firstPay": "2023-02-15", "payFreq": ["MonthEnd", 15], "poolFreq": "MonthEnd", "stated": "2033-01-01"},
    "pool": {"assets": pool_assets},
    "accounts": {"acc01": {"balance": 0}},
    "bonds": {"A": {"balance": 200000, "rate": 0.035, "originBalance": 200000, "originRate": 0.035, "startDate": "2023-02-01"}}
}
deal = mkDeal(deal_data)
response = api.run(deal)
print(response['bonds'])  # Bond cashflows
print(response['pool'])   # Pool cashflows
print(response['result']) # Overall deal analysis

Prompt

Create a securitization deal with tranches and perform sensitivity analysis on CPR assumptions.

Output

import absbox
from absbox import API, EnginePath, mkDeal
api = API(EnginePath.PROD)
pool_assets = [
    ["Loan",
     {"originBalance": 500000, "originRate": ["fix", 0.045], "originTerm": 120, "freq": "Monthly", "type": "Level", "originDate": "2021-01-01"},
     {"currentBalance": 490000, "currentRate": 0.045, "remainTerm": 119, "status": "Current"}]
]
deal_data = {
    "name": "CLOWithTranches",
    "dates": {"cutoff": "2023-01-01", "closing": "2023-02-01", "firstPay": "2023-02-15", "payFreq": ["MonthEnd", 15], "poolFreq": "MonthEnd", "stated": "2033-01-01"},
    "pool": {"assets": pool_assets},
    "accounts": {"acc01": {"balance": 0}},
    "bonds": {
        "Senior": {"balance": 400000, "rate": 0.03, "originBalance": 400000, "originRate": 0.03, "startDate": "2023-02-01"},
        "Mezzanine": {"balance": 100000, "rate": 0.06, "originBalance": 100000, "originRate": 0.06, "startDate": "2023-02-01"}
    }
}
# Run initial deal
deal = mkDeal(deal_data)
response = api.run(deal)
# Sensitivity analysis with CPR variation
sensitivity_params = {'CPR': [0.06, 0.08, 0.10]}
response_sensitivity = api.run(deal, params=sensitivity_params)
print(response_sensitivity['result'])  # Sensitivity results for different CPRs

Instructions

This skill doesn’t include stateful context yet, instructions only. Learn about stateful skills.

Security

Loading security scan...

Reviews (0)

More Build skills

Browse category →
senior-frontendBuild and review React, Next.js, TypeScript or Tailwind frontends: components, scaffolding, performance and bundle size. Use whenever the user wants a new component or app, a page feels slow, the bundle is too big, or asks for a frontend code review.618 installsui-design-systemUse when building a design system: tokens, component docs, responsive scales or developer handoff. Generates tokens with design_token_generator.py.523 installsfrontend-designGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.328 installssenior-backendBuild and fix backend services: REST or GraphQL APIs, auth, microservices, PostgreSQL queries, migrations and load tests. Use whenever the user's API is slow or broken, needs login or auth added, a schema change, or a new endpoint or service scaffolded.236 installsself-improving-agentCurate what the agent has learned into durable project knowledge. Reviews Claude Code auto-memory (MEMORY.md and its topic files) for learnings worth keeping, promotes proven ones into CLAUDE.md or .claude/rules/, records a correction as a lesson that persists across sessions, prunes stale or duplicate entries, and turns a recurring fix into a reusable skill. Use whenever the user asks what you have learned or saved about the project, which memories should become permanent rules, to remember a lesson or stop repeating a mistake, or to clean up, audit or check memory health.167 installsusing-superpowersUse when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions141 installs

Frequently asked questions about absbox

What does the absbox skill do?

Model, project, and analyze structured finance deals (ABS, MBS, CLO, SRT) with the absbox Python library and Hastructure engine. Use for securitization modeling, deal maps, pool cashflow projection, bond waterfalls, tranche pricing, IRR/WAL, sensitivity analysis, root finding, and debugging projections. Python 3.10+. It's a reusable SKILL.md instruction set that loads into your AI coding assistant on demand, no prompt engineering, no copy-pasting every session.

How do I install the absbox skill?

Run `npx @skills-hub-ai/cli install absbox` from your terminal. The CLI writes the SKILL.md to the correct location for your AI tool (e.g. ~/.claude/skills/absbox/ for Claude Code or ~/.cursor/skills/ for Cursor with --target cursor) and adds it to your project's .skills.json lockfile.

Which AI tools does absbox work with?

absbox runs in Claude Code, OpenCode, Codex CLI, Cursor, Windsurf, GitHub Copilot. It follows the open Agent Skills standard (SKILL.md), so the same skill works in every supported tool without modification.

Is the absbox skill free?

Yes. Every skill on skills-hub.ai is free and open-source. There are no premium tiers, paywalls, or usage limits. You only pay for whatever AI assistant you're already using.

How do I use absbox after installing it?

In Claude Code, type `/absbox` (or whatever slash command the skill registers) and the AI follows the skill's instructions immediately. You can also reference it by name in natural language, your AI loads the skill into context when relevant.

Can I share the absbox skill with my team?

Yes. Commit your project's .skills.json lockfile and teammates run `npx @skills-hub-ai/cli install` (no args) to install every skill at the exact version you pinned. Organization-scoped installs work via skills-hub.ai organizations.