ecl-calculation

ecl-calculation is a skill for Claude Code from vivy-yi/finance-skills. It costs 95 tokens per session (1,890 once invoked), scanned A, original, MIT.

A workflow for calculating expected credit loss, the amount a lender estimates it may lose when borrowers do not repay. It uses exposure, default probability, loss severity, and discounting inputs for each IFRS 9 stage.

In plain words
What is it for?
It helps calculate losses for Stage 1, Stage 2, and Stage 3 exposures, total the results, measure coverage ratios, and validate the input assumptions.
Why use it?
It provides a consistent way to calculate 12-month or lifetime losses and check whether the results are reasonable.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md.

Good fit It helps calculate losses for Stage 1, Stage 2, and Stage 3 exposures, total the results, measure coverage ratios, and validate the input assumptions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vivy-yi/finance-skills/ecl-calculation
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add vivy-yi/finance-skills --skill ecl-calculation
Clone the repo
git clone --depth 1 https://github.com/vivy-yi/finance-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ecl-calculation

README.md
[![agentmods](https://agentmods.dev/badge/skills/vivy-yi/finance-skills/ecl-calculation/github.svg)](https://agentmods.dev/skills/vivy-yi/finance-skills/ecl-calculation)
Your own site
<a href="https://agentmods.dev/skills/vivy-yi/finance-skills/ecl-calculation"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/ecl-calculation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ecl-calculation

Your own site · 80×15
<a href="https://agentmods.dev/skills/vivy-yi/finance-skills/ecl-calculation"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/ecl-calculation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,890 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00095 $0.01890
Opus 5 $0.00048 $0.00945
Sonnet 5 $0.00019 $0.00378
Haiku 4.5 $0.00010 $0.00189

Measured 9d ago against content hash d1e398316fff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ecl-calculation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

finance-skills/skills/ifrs9-credit-risk/skills/ecl-calculation/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

加载上下文

首次使用时: 读取 ../../CLAUDE.md 获取 PD/LGD/EAD 参数配置和前瞻调整要求。


/ecl-calculation — ECL 计量

第一步:确认参数配置

□ PD 来源:
□ 内部评级系统:[✅ 可用 / ⚠️ 须手动映射]
□ 外部评级映射:[✅ 已建立 / ⚠️ 须建立]
□ 内部历史数据年限:[X] 年

□ LGD 来源:
□ 内部历史回收数据:[✅ 可用 / ⚠️ 须参照外部]
□ 抵押品处理历史:[✅ 可用 / ⚠️ 须补录]

□ EAD 来源:
□ 表内:账面余额 [✅ 直接取数]
□ 表外:已承诺金额 × CCF [X]%

□ 前瞻调整:
□ 是否须应用宏观调整:[是/否]
□ 宏观情景权重:[乐观 X]% / [基准 X]% / [悲观 X]%

第二步:Stage 1 ECL 计量

□ 计量公式:
□ ECL = EAD × PD(12个月) × LGD × [1/(1+r)^t](折现因子)

□ 对每个 Stage 1 敞口计算:
□ [客户 A] — EAD [X]万 × PD [X]% × LGD [X]% × 折现 = ECL [X]元
□ [客户 B] — ...

□ Stage 1 汇总:
□ Stage 1 敞口:[X] 万元
□ Stage 1 ECL:[X] 万元
□ Stage 1 覆盖率:ECL / 敞口 = [X]%

□ PD 合理性验证:
□ Stage 1 加权平均 PD:[X]% — [✅ 与预期一致 / ⚠️ 偏高]

第三步:Stage 2 ECL 计量

□ 计量公式(存续期):
□ ECL = EAD × PD(存续期,当前评级) × LGD × 折现因子

□ PD(存续期) 计算:
□ 当前评级 [X] → 对应存续期 PD [X]%
□ 须使用存续期 PD(不是 12 个月 PD)

□ 对每个 Stage 2 敞口计算:
□ [客户 C] — EAD [X]万 × PD(存续) [X]% × LGD [X]% × 折现 = ECL [X]元
□ ...

□ Stage 2 汇总:
□ Stage 2 敞口:[X] 万元
□ Stage 2 ECL:[X] 万元
□ Stage 2 覆盖率:[X]% — [✅ 充足 / ⚠️ 偏低]

□ PD 合理性验证:
□ Stage 2 加权平均 PD(存续):[X]% — [✅ 与预期一致 / ⚠️ 偏高]
□ Stage 2 vs Stage 1 PD 差异:[X]x — [✅ 合理差异 / ⚠️ 差异过大]

第四步:Stage 3 ECL 计量

□ 计量公式(已减值):
□ ECL = (EAD + 逾期利息资本化) × LGD × 折现因子
□ PD = 100%(已违约)

□ 抵押品处理:
□ 抵押品评估价值:[X] 万元
□ 折现率:[X]%
□ 抵押品净可回收:[X] 万元
□ ECL 扣除抵押品后净额:[X] 万元

□ Stage 3 汇总:
□ Stage 3 敞口:[X] 万元
□ Stage 3 ECL(扣除抵押品前):[X] 万元
□ 抵押品价值:[X] 万元
□ Stage 3 ECL(扣除抵押品后):[X] 万元
□ Stage 3 覆盖率:[X]% — [✅ 充足 / ⚠️ 偏低]

第五步:ECL 汇总与覆盖率验证

□ ECL 汇总:

| Stage | 敞口(万)| ECL(万)| 覆盖率 |
|-------|-----------|----------|---------|
| Stage 1 | [X]     | [X]      | [X]%   |
| Stage 2 | [X]     | [X]      | [X]%   |
| Stage 3 | [X]     | [X]      | [X]%   |
| **合计** | **[X]** | **[X]** | **[X]%** |

□ 覆盖率合理性检查:
□ Stage 1 覆盖率 vs 监管最低 [X]%:[✅ 达标 / ❌ 不达标]
□ Stage 2 覆盖率 vs 监管最低 [X]%:[✅ 达标 / ❌ 不达标]
□ Stage 3 覆盖率 vs 监管最低 [X]%:[✅ 达标 / ❌ 不达标]

□ 与上期对比:
□ 上期 ECL:[X] 万元 → 本期 [X] 万元
□ 变动:[±X] 万元 / [±X]%
□ 主要变动驱动因素:[...]

Read the full file on GitHub · 188 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 188 lines · 95 tokens per session scan A d1e398316fff

Subscribe to this mod's changes

ecl-calculation is a skill published in the GitHub repository vivy-yi/finance-skills (29 stars, last pushed 3mo ago), licensed MIT. It adds 95 tokens to every session and 1,890 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

wealth-structure

A framework for thinking about wealth through ownership, responsibility, leverage, and avoiding risks that could end your progress.

kangarooking/cangjie-skill · 141 tokens

alpha-vantage

Access real-time and historical stock market data, forex rates, cryptocurrency prices, commodities, economic indicators, and 50+ technical indicators via the Alpha Vantage API. Use when fetching stock prices (OHLCV), company fundamentals (income statement, balance sheet, cash flow), earnings, options data, market…

foryourhealth111-pixel/Vibe-Skills · 126 tokens

hedgefundmonitor

Query the OFR (Office of Financial Research) Hedge Fund Monitor API for hedge fund data including SEC Form PF aggregated statistics, CFTC Traders in Financial Futures, FICC Sponsored Repo volumes, and FRB SCOOS dealer financing terms. Access time series data on hedge fund size, leverage, counterparties, liquidity…

foryourhealth111-pixel/Vibe-Skills · 123 tokens

edgartools

Python library for accessing, analyzing, and extracting data from SEC EDGAR filings. Use when working with SEC filings, financial statements (income statement, balance sheet, cash flow), XBRL financial data, insider trading (Form 4), institutional holdings (13F), company financials, annual/quarterly reports (10-K…

foryourhealth111-pixel/Vibe-Skills · 110 tokens

asc-ppp-pricing

Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands. Use when adjusting prices by country or implementing localized PPP strategies.

rorkai/app-store-connect-cli-skills · 45 tokens

fred-economic-data

Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources. Access GDP, unemployment, inflation, interest rates, exchange rates, housing, and regional data. Use for macroeconomic analysis, financial research, policy studies, economic forecasting, and academic research requiring…

foryourhealth111-pixel/Vibe-Skills · 75 tokens