@v587d/capital-generation 2.10.2 → 2.11.1

package/selected-skills/claude-for-financial-services-cn/vertical-plugins/wealth-management/skills/china-investment-proposal/SKILL.md

@@ -1,271 +0,0 @@
----
-name: china-investment-proposal
-description: Draft investment proposals for Chinese wealth management clients. Creates structured proposals with investment rationale, product recommendations, and risk disclosures. Adapted from the original investment-proposal skill for A-share products and Chinese regulatory requirements. Triggers on "A股投资建议书", "投资方案", "investment proposal China", "proposal for [client]", "investment recommendation A-share", or "build investment proposal".
----
-
-# china-investment-proposal
-
-## Purpose
-
-Create professional **A股财富管理投资建议书** — structured proposals for Chinese wealth management clients.
-
-## Data Sources
-
-### Primary: iFind MCP (Tier-1 付费) / AkShare MCP (Tier-2 免费备选)
-
-```python
-get_index_data("000001")              → Market context
-get_index_data("399006")              → ChiNext context
-get_quote(ticker)                     → Security analysis
-get_fund_data(fund_code)              → Fund analysis
-get_industry_stocks(industry="...")    → Sector analysis
-```
-
-### Secondary Sources
-- Portfolio management system
-- Research team — market outlook
-- Product providers — fund/insurance data
-
-## Workflow
-
-### Step 1: Understand Client Needs
-
-**Discovery questions:**
-
-1. **Investment objective**: 保值增值 / 稳健增值 / 积极增值 / 收入型
-2. **Time horizon**: 短期(<1年) / 中期(1-5年) / 长期(>5年)
-3. **Risk tolerance**: 保守 / 稳健 / 积极 / 激进
-4. **Liquidity needs**: 高 / 中 / 低
-5. **Special considerations**: 税务, 遗产, 慈善, etc.
-
-### Step 2: Market & Strategy Overview
-
-**Current market assessment:**
-
-```
-市场展望 [Period]
-
-一、宏观经济
-   [GDP, policy, rates outlook]
-
-二、权益市场
-   - 估值水平: 沪深300 PE [Xx] (历史[X]%分位)
-   - 资金面: 北向资金, 两融余额
-   - 情绪指标: [Index]
-
-三、行业配置观点
-   超配 (Overweight): [Sectors] — [Rationale]
-   标配 (Neutral): [Sectors]
-   低配 (Underweight): [Sectors] — [Rationale]
-
-四、风险提示
-   [Key risks]
-```
-
-### Step 3: Investment Strategy
-
-**Strategy design:**
-
-| Component | Allocation | Rationale |
-|-----------|-----------|-----------|
-| A股权益 | XX% | Growth engine |
-| 基金 (主动) | XX% | Professional management |
-| 基金 (指数) | XX% | Low-cost beta |
-| 债券/固收+ | XX% | Stability, income |
-| 现金/货币基金 | XX% | Liquidity |
-| 另类 (REITs, 黄金) | XX% | Diversification |
-
-**A-share equity allocation:**
-
-| Sector | Weight | Thesis |
-|--------|--------|--------|
-| 消费 | XX% | [Rationale] |
-| 科技 | XX% | [Rationale] |
-| 医药 | XX% | [Rationale] |
-| 金融 | XX% | [Rationale] |
-| 新能源 | XX% | [Rationale] |
-| 其他 | XX% | [Rationale] |
-
-### Step 4: Product Recommendations
-
-**Recommended securities:**
-
-| # | Type | Security | Ticker | Allocation | Rationale | Risk Level |
-|---|------|----------|--------|-----------|-----------|------------|
-| 1 | A股个股 | | | | | |
-| 2 | 主动基金 | | | | | |
-| 3 | 指数基金 | | | | | |
-| 4 | 债券/理财 | | | | | |
-| 5 | 现金管理 | | | | | |
-
-**For each recommendation:**
-- Investment thesis (3-5 bullet points)
-- Expected return range
-- Risk assessment
-- Suitable for client profile
-- Minimum investment
-- Liquidity terms
-
-### Step 5: Risk Assessment & Disclosure
-
-**Risk factors (standard Chinese disclosures):**
-
-```
-风险揭示
-
-一、市场风险
-   投资有风险, 入市需谨慎。本投资方案涉及A股市场投资,
-   股票价格可能因市场因素大幅波动。
-
-二、流动性风险
-   部分投资品可能存在流动性限制, 赎回/卖出可能受
-   市场流动性影响。
-
-三、政策风险
-   国家政策、行业监管变化可能影响投资组合表现。
-
-四、信用风险
-   固定收益类产品存在发行人信用风险。
-
-五、汇率风险
-   [If applicable]
-
-六、其他风险
-   [Product-specific risks]
-```
-
-**Risk level match:**
-- Conservative (保守型): 低风险产品为主, 权益<30%
-- Balanced (稳健型): 中等风险, 权益30-60%
-- Growth (积极型): 较高风险, 权益60-90%
-- Aggressive (激进型): 高风险, 权益>90%
-
-### Step 6: Expected Returns & Scenarios
-
-**Return scenarios:**
-
-| Scenario | Probability | Expected Return | Portfolio Value (3Y) |
-|-----------|-------------|----------------|---------------------|
-| 乐观 | 25% | +XX% | ¥XXX万 |
-| 中性 | 50% | +X% | ¥XXX万 |
-| 悲观 | 25% | -X% | ¥XXX万 |
-
-### Step 7: Implementation Plan
-
-**Implementation steps:**
-
-| Step | Action | Timeline |
-|------|--------|----------|
-| 1 | 方案确认 | [Date] |
-| 2 | 账户开立/激活 | [Date] |
-| 3 | 建仓 (首批建仓) | [Date] |
-| 4 | 分批建仓 (如需) | [Date range] |
-| 5 | 首次复核 | [Date] |
-
-**建仓策略:**
-- 一次性建仓: 适合积极型, 市场低点
-- 分批建仓: 适合稳健型, 降低择时风险
-- 定投: 适合长期投资, 平滑成本
-
-### Step 8: Monitoring & Review
-
-**Review schedule:**
-
-| Review Type | Frequency | Content |
-|-------------|-----------|---------|
-| 日常监控 | Daily | Market alerts, significant moves |
-| 月度回顾 | Monthly | Performance, attribution |
-| 季度复盘 | Quarterly | Full review, rebalancing |
-| 年度规划 | Annual | Goal review, strategy update |
-
-### Step 9: Proposal Document
-
-**Standard proposal format:**
-
-```
-【投资建议书】
-客户名称：[Name]
-风险等级：[R1-R5]
-投资期限：[X年]
-建议日期：[Date]
-
-一、客户需求分析
-   [Goals, constraints, preferences]
-
-二、市场展望
-   [Current market assessment]
-
-三、投资策略
-   [Allocation strategy with rationale]
-
-四、产品推荐
-   [Detailed recommendations]
-
-五、风险评估
-   [Risk factors, suitability assessment]
-
-六、预期表现
-   [Return scenarios]
-
-七、实施方案
-   [Implementation plan]
-
-八、后续服务
-   [Review schedule, monitoring]
-
-九、声明
-   [Standard regulatory disclaimers]
-
-客户签字：_________ 日期：_________
-理财师签字：_________ 日期：_________
-```
-
-## China-Specific Considerations
-
-### Suitability (适当性管理)
-
-**China regulatory requirements:**
-- 风险等级匹配: Product risk ≤ Client risk tolerance
-- 投资者分类: 普通投资者 / 专业投资者
-- 信息披露: Full and fair disclosure
-- 冷静期: Cooling-off period for certain products
-- 录音录像: Recording for in-person sales
-
-### Common Investment Products (China)
-
-| Product | Risk | Return | Liquidity |
-|---------|------|--------|-----------|
-| 银行理财 | Low | 2-4% | Medium |
-| 货币基金 | Low | 1.5-2.5% | High |
-| 国债 | Very low | 2-3% | Medium |
-| 企业债 | Low-Medium | 3-5% | Medium |
-| A股个股 | High | Variable | Medium |
-| 主动基金 | Medium-High | Variable | Medium |
-| 指数基金/ETF | Medium | Variable | High |
-| 私募基金 | High | Variable | Low |
-| 信托 | Medium-High | 5-8% | Low |
-| 保险产品 | Low-Medium | Guaranteed + bonus | Low |
-
-### Client Segmentation
-
-| Type | Profile | Strategy |
-|------|---------|----------|
-| 保守型 | Risk-averse, capital preservation focus | Bonds, money market, blue chips |
-| 稳健型 | Balanced, moderate growth | Balanced allocation, dividend stocks |
-| 积极型 | Growth-oriented, can tolerate volatility | Growth stocks, sector funds |
-| 激进型 | High risk tolerance, return-seeking | Small-caps, thematic, alternatives |
-
-## Quality Checks
-
-Before delivering:
-- [ ] Client profile understood
-- [ ] Allocation aligned with risk tolerance
-- [ ] Products suitable and available
-- [ ] Risk disclosures complete
-- [ ] Expected returns realistic
-- [ ] Implementation plan clear
-- [ ] Regulatory disclosures included
-> **Data Source Mode Switch**: Set env var `IFIND_DATA_SOURCE_MODE` to control data source preference.
-> - `ifind-only` (strict): Use iFind only, error if unavailable
-> - `ifind-fallback` (default): iFind preferred, fallback to AkShare
-> - `akshare-only, wind-only (Wind only), wind-fallback (Wind first, fallback to iFind → AkShare)`: Skip iFind, use AkShare only

package/selected-skills/claude-for-financial-services-cn/vertical-plugins/wealth-management/skills/china-portfolio-rebalance/SKILL.md

@@ -1,191 +0,0 @@
----
-name: china-portfolio-rebalance
-description: Portfolio rebalancing analysis for A-share wealth management portfolios. Analyzes allocation drift, generates rebalancing trades, and optimizes for tax efficiency. Adapted from the original portfolio-rebalance skill for Chinese portfolios. Triggers on "A股组合再平衡", "调仓", "rebalance China", "portfolio rebalance A-share", "rebalance portfolio", or "adjust allocation [client]".
----
-
-# china-portfolio-rebalance
-
-## Purpose
-
-Perform **A股投资组合再平衡** — analyze allocation drift, generate rebalancing recommendations, and optimize trade execution.
-
-## Data Sources
-
-### Primary: iFind MCP (Tier-1 付费) / AkShare MCP (Tier-2 免费备选)
-
-```python
-get_quote(ticker)                     → Current prices for holdings
-get_historical_data(ticker)           → Tax lot / cost basis context
-```
-
-### Secondary Sources
-- Portfolio management system
-- Wind / Choice — market data
-- Tax rules — A-share tax treatment
-
-## Workflow
-
-### Step 1: Current Allocation
-
-**Portfolio snapshot:**
-
-| Asset Class | Target % | Current % | Drift | Market Value | Action |
-|-------------|----------|-----------|-------|--------------|--------|
-| | | | | | |
-
-**Within A-share equity:**
-
-| Sector | Target | Current | Drift | Action |
-|--------|--------|---------|-------|--------|
-| 消费 | XX% | XX% | ±X% | Buy/Sell/Hold |
-| 科技 | XX% | XX% | ±X% | Buy/Sell/Hold |
-| 医药 | XX% | XX% | ±X% | Buy/Sell/Hold |
-| 金融 | XX% | XX% | ±X% | Buy/Sell/Hold |
-| 新能源 | XX% | XX% | ±X% | Buy/Sell/Hold |
-| 其他 | XX% | XX% | ±X% | Buy/Sell/Hold |
-
-### Step 2: Identify Drift
-
-**Drift thresholds:**
-
-| Drift Level | Action |
-|-------------|--------|
-| ±2% | Monitor, no action |
-| ±3-5% | Consider rebalancing |
-| ±5%+ | Rebalance recommended |
-
-**Drift causes:**
-- Market price movements
-- Dividend reinvestment
-- Previous trades
-- Cash flows (contributions/withdrawals)
-
-### Step 3: Generate Rebalancing Trades
-
-**Rebalancing logic:**
-
-| Situation | Action |
-|-----------|--------|
-| Sector overweight + price up | Trim position |
-| Sector underweight + price down | Add to position |
-| Overweight + price down | Monitor (may converge) |
-| Underweight + price up | Monitor (may converge) |
-
-**Trade list:**
-
-| Action | Ticker | Security | Current % | Target % | Trade Amount | Est. Shares |
-|--------|--------|----------|-----------|----------|-------------|------------|
-| Buy | | | | | | |
-| Sell | | | | | | |
-| Hold | | | | | | |
-
-### Step 4: Tax Considerations
-
-**A-share tax treatment:**
-
-| Item | Tax Rate | Notes |
-|------|----------|-------|
-| 股票买卖价差 | 暂免 (temporarily exempt) | Capital gains on stocks |
-| 股息红利 | 20% (持股>1年减半/免征) | Dividend tax |
-| 基金分红 | 暂免 (some funds) | Fund distributions |
-| 买卖印花税 | 0.05% (seller only) | Stamp duty |
-
-**Tax-loss harvesting opportunities:**
-
-| Position | Cost Basis | Current Value | Unrealized Loss | Tax Benefit |
-|----------|-----------|--------------|-----------------|-------------|
-| | | | | |
-
-**Tax-efficient selling:**
-- Prioritize selling positions with losses
-- Consider holding period for dividend tax
-- Batch sales to minimize stamp duty impact
-
-### Step 5: Execution Plan
-
-**Trade sequencing:**
-
-| Priority | Trade | Rationale |
-|----------|-------|-----------|
-| 1 | | Tax loss harvesting |
-| 2 | | Largest drift correction |
-| 3 | | Smaller adjustments |
-
-**Execution considerations:**
-- Market impact (liquidity)
-- Trading costs (commissions, stamp duty)
-- Market timing (volatility)
-- Block trading for large positions
-
-### Step 6: Rebalancing Report
-
-**Standard rebalancing report:**
-
-```
-【组合再平衡报告】[Client] [Date]
-
-一、当前配置 vs 目标配置
-   [Allocation table with drift]
-
-二、再平衡建议
-   [Trade list]
-
-三、税务影响
-   [Tax implications]
-
-四、执行计划
-   [Sequencing and timing]
-
-五、预期效果
-   [Projected post-rebalance allocation]
-```
-
-## China-Specific Rebalancing Considerations
-
-### A-share Market Characteristics
-
-| Factor | Rebalancing Implication |
-|--------|------------------------|
-| 涨跌停限制 | May prevent immediate rebalancing |
-| T+1 settlement | Trade settlement timeline |
-| 印花税 | 0.05% on sell side |
-| 佣金 | Varies by broker (typically 0.02-0.03%) |
-| 最低手续费 | Minimum commission threshold |
-
-### Tax-Loss Harvesting (A-share)
-
-**China-specific TLH:**
-- Capital gains on stocks: currently tax-exempt (暂免)
-- Losses: can offset gains within the same asset class
-- 股息红利 tax: 20%, reduced to 10% for >1 year holding, 0% for >1 year (recent changes)
-- Fund distributions: tax treatment varies by fund type
-
-### Common Rebalancing Triggers
-
-| Trigger | Frequency | Action |
-|---------|-----------|--------|
-| Calendar rebalancing | Quarterly/Semi-annual | Systematic rebalance |
-| Drift threshold | When ±5% | Opportunistic rebalance |
-| Cash inflow | As received | Deploy to underweights |
-| Client request | Ad-hoc | Targeted rebalance |
-| Tax planning | Year-end | Harvest losses, reset cost basis |
-
-## Quality Checks
-
-Before executing:
-- [ ] Allocations calculated correctly
-- [ ] Trades aligned with policy
-- [ ] Tax implications assessed
-- [ ] Trading costs estimated
-- [ ] Client approval obtained
-- [ ] Execution plan sequenced
-
-After rebalancing:
-- [ ] Trades confirmed
-- [ ] Allocation updated
-- [ ] Tax lots recorded
-- [ ] Client notified
-> **Data Source Mode Switch**: Set env var `IFIND_DATA_SOURCE_MODE` to control data source preference.
-> - `ifind-only` (strict): Use iFind only, error if unavailable
-> - `ifind-fallback` (default): iFind preferred, fallback to AkShare
-> - `akshare-only`: Skip iFind, use AkShare only

package/selected-skills/financeskills/skills/ai-anomaly-detection/EXAMPLE.md

@@ -1,21 +0,0 @@
-# Worked Example - ai-anomaly-detection
-
-## Ask
-
-> We have 1 million credit card transactions. We want to find weird spending patterns that don't follow our standard rules. Which ML model should we use?
-
-## What a correct response contains
-
-Should recommend unsupervised learning models like Isolation Forest or Autoencoders. Should explain why these are better than rules-based systems for large datasets. Should mention feature engineering (e.g. txn frequency, distance). Should provide an AI Audit Report structure.
-
-## File-driven variant
-
-With fixture(s) `evals/files/expense_ledger.csv`:
-
-> Screen the attached expense ledger (evals/files/expense_ledger.csv) for anomalies using at least two methods (z-score and IQR). Report flagged rows with their references and quantify how extreme each is.
-
-Expected: Two planted anomalies: GL-4057 (290.00, high) and GL-4101 (12.00, low). Z-score flags indices [57, 101].
-
-## Compute, don't estimate
-
-All figures above come from [`scripts/calculate.py`](./scripts/calculate.py) - import its functions rather than doing arithmetic in prose.

package/selected-skills/financeskills/skills/ai-anomaly-detection/SKILL.md

@@ -1,84 +0,0 @@
----
-name: ai-anomaly-detection
-description: When the user wants to use machine learning to detect fraud, errors, or unusual patterns in high-volume financial data. Also use when the user mentions "ML fraud detection," "unsupervised learning for audit," "isolation forest," "autoencoders for finance," "unusual transaction clusters," or "automated expense auditing."
-metadata:
-  version: 1.0.0
----
-
-# AI Anomaly Detection
-
-You are an AI Financial Systems Engineer. Your goal is to deploy machine learning models to identify "needles in the haystack"—anomalies that human-coded rules might miss.
-
-## Initial Assessment
-
-1. **Data Volume & Velocity**
-   - How many transactions are we analyzing? (e.g., 10,000 vs 10,000,000).
-   - Is the data structured (CSV/SQL) or semi-structured (JSON logs)?
-
-2. **Anomaly Definition**
-   - Are we looking for "Point Anomalies" (one weird transaction)?
-   - "Contextual Anomalies" (weird for this specific user/time)?
-   - "Collective Anomalies" (a series of transactions that are weird together)?
-
----
-
-## AI Framework
-
-### Technical Limitation
-**LLMs are not ML Models.**
-While LLMs (like Claude/GPT) can reason about small sets of anomalies, for millions of rows, you should use specialized Python libraries (Scikit-Learn, PyOD). This skill provides the *logic* and *code* for those implementations.
-
-### Priority Order
-1. **Feature Engineering** (Creating inputs like 'time_since_last_txn', 'distance_from_home').
-2. **Unsupervised Learning** (Isolation Forest, Local Outlier Factor).
-3. **Cluster Analysis** (K-Means to identify unusual spending groups).
-4. **Scoring & Flagging** (Assigning a "Risk Score" to every row).
-
----
-
-## Technical AI Steps
-
-### 1. Isolation Forest Implementation
-- Use the `IsolationForest` algorithm to isolate observations by randomly selecting a feature and a split value. 
-- Anomalies are the points that require fewer splits to isolate.
-
-### 2. Autoencoder Analysis (Advanced)
-- Train a neural network to compress and reconstruct "normal" data. 
-- High "Reconstruction Error" identifies anomalies that don't fit the normal pattern.
-
-### 3. Feature Scaling
-- Apply `StandardScaler` or `MinMaxScaler` to ensure transaction amounts don't overwhelm other features (like frequency).
-
----
-
-## Output Format
-
-### AI Audit Report Structure
-
-**Model Performance**
-- Anomaly rate detected (e.g., 0.5% of total data).
-- Top features driving the anomaly score.
-
-**The Flags**
-- Top 20 "High Risk" transactions with confidence scores.
-- "Why this was flagged" (e.g., "Unexpected high value for this vendor category").
-
-**Python Integration**
-- Ready-to-run script for the user to execute against their full dataset.
-
----
-
-## Scripts
-- [calculate.py](./scripts/calculate.py): Deterministic functions for this skill's core computations. Run `python3 scripts/calculate.py` to self-test; import the functions instead of doing mental math.
-
----
-
-## References
-- [Anomaly Detection Algorithms](./references/ml-algorithms.md): Isolation Forest vs. LOF.
-- [Feature Engineering for Finance](./references/feature-engineering.md): Key inputs for fraud models.
-
----
-
-## Related Skills
-- **forensic-accounting**: To manually investigate the flags raised by the AI.
-- **audit-checklist**: To integrate AI detection into the standard audit flow.

package/selected-skills/financeskills/skills/ai-anomaly-detection/references/feature-engineering.md

@@ -1,20 +0,0 @@
-# Feature Engineering for Financial Anomaly Detection
-
-## Journal Entry Features
-- **Amount-based**: raw amount, log(|amount|), roundness score (trailing zeros), distance to nearest approval threshold (e.g., amount/threshold ratio in [0.9, 1.0) is suspicious), first-two-digit Benford deviation of the user's population.
-- **Timing**: hour-of-day, day-of-week, posted-on-weekend/holiday flag, days from period end (entries on WD-0/WD+1 deserve weight), posting date vs. effective date gap.
-- **User behavior**: entries per user per period vs. trailing median, new user flag (< 90 days), user-account pair novelty (first time this user touches this account), seniority-vs-amount mismatch.
-- **Account patterns**: rare account combination flag (debit-credit pair frequency), suspense/clearing account usage, P&L-to-BS reclass patterns.
-- **Text**: description length, generic-description flag ("adjustment", "misc", blank), duplicate description with different amounts.
-
-## Transaction-Level (AP/AR) Features
-- Vendor: invoice number gaps/sequences, duplicate detection key (vendor + amount + date ±3d), bank account changes, vendor-employee address/phone match.
-- Payment: split-payment detection (same vendor, same day, sum > threshold), velocity (payments per vendor per week vs. baseline).
-
-## Aggregation Windows
-Build each behavioral feature at 3 windows (7/30/90 days) and use the ratio of short-to-long window as a drift signal.
-
-## Encoding & Hygiene
-- High-cardinality categoricals (account, vendor): frequency encoding or target-free hashing — never one-hot 10k vendors.
-- Winsorize at 0.1%/99.9% before scaling for distance-based models.
-- Keep a human-readable reason string per feature so flags are explainable to auditors.

package/selected-skills/financeskills/skills/ai-anomaly-detection/references/ml-algorithms.md

@@ -1,28 +0,0 @@
-# Anomaly Detection Algorithms for Financial Data
-
-## Algorithm Selection
-| Algorithm | Best For | Notes |
-|---|---|---|
-| Z-score / modified Z (MAD) | Univariate amounts, quick baselines | Robust version uses median/MAD; flag \|z\| > 3 (or > 3.5 MAD) |
-| IQR fences | Skewed distributions | Outlier if < Q1 − 1.5×IQR or > Q3 + 1.5×IQR |
-| Isolation Forest | Multivariate, mixed features, large JE populations | contamination ≈ expected anomaly rate (0.001–0.01 for JEs); fast, no distribution assumption |
-| Local Outlier Factor | Density-varying data (different entities/scales) | Catches local anomalies global methods miss |
-| One-Class SVM | Small, clean training sets | Sensitive to scaling; slower |
-| Autoencoder | High-dimensional, abundant data | Reconstruction error as anomaly score; needs volume |
-| Benford's Law | First/second-digit tests on populations > 1,000 | Screening only — deviations need investigation, not accusation |
-| Time-series (STL + residual z) | Seasonality-aware account monitoring | Decompose, then flag residual outliers |
-
-## Practical Pipeline for Journal Entry Testing
-1. Score with 2–3 uncorrelated methods (e.g., Isolation Forest + MAD + rules).
-2. Combine: rank-average or max-rule; rule-based flags (weekend posting, round amounts, manual JEs by unusual users, just-below-approval-threshold) always surface regardless of model score.
-3. Triage queue sorted by composite score × monetary value.
-
-## Evaluation Without Labels
-- Precision@k: review top-k flags, count true issues.
-- Inject synthetic anomalies (duplicated invoices, split transactions) to measure recall.
-- Track investigator feedback to recalibrate quarterly.
-
-## Pitfalls
-- Scaling: tree methods don't need it; distance methods (LOF, SVM) require it.
-- Train/score leakage: fit on prior periods, score current.
-- Anomalous ≠ fraudulent — output is a *review queue*, never an auto-accusation.

package/selected-skills/financeskills/skills/aro-computation/EXAMPLE.md

@@ -1,21 +0,0 @@
-# Worked Example - aro-computation
-
-## Ask
-
-> We built a factory that must be restored in 10 years at an estimated cost of $1M. Our credit-adjusted risk-free rate is 5%. How do we record this today?
-
-## What a correct response contains
-
-Should calculate the Present Value of the $1M ($1M / (1.05)^10 = ~$613.9k). Should describe the entry to Debit Asset / Credit ARO Liability. Should mention subsequent Accretion and Depreciation. Should provide an ARO Schedule.
-
-## File-driven variant
-
-With fixture(s) `evals/files/retirement_obligations.csv`:
-
-> Using the attached asset retirement obligations file (evals/files/retirement_obligations.csv), measure the initial ARO liability for each asset (inflate current cost to retirement date, discount back at the credit-adjusted rate), total the provision, and compute year-1 accretion expense.
-
-Expected: AROs: Alpha $5,893,636, Beta $4,979,947, Gamma $1,270,349; total $12,143,931; year-1 accretion $958,811.
-
-## Compute, don't estimate
-
-All figures above come from [`scripts/calculate.py`](./scripts/calculate.py) - import its functions rather than doing arithmetic in prose.