verify-regime
Performs rigorous verification of financial regimes, stress tests, and data parity.
Install
mkdir -p .claude/skills/verify-regime && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14641" && unzip -o skill.zip -d .claude/skills/verify-regime && rm skill.zipInstalls to .claude/skills/verify-regime
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Level 5 verification: regime conditioning tests across VIX regimes, stress event validations (March 2020, February 2018), and A-B data source comparisons. Runs after verify-empirical passes.Key capabilities
- →Test parity deviation by VIX regime
- →Test backtest performance by VIX regime
- →Check VRP signal behavior across regimes
- →Validate regime transitions
- →Validate specific stress events like COVID crash
- →Compare FRED VIXCLS and CBOE VIX historical data
How it works
The skill runs pytest on regime tests, which check VIX-based thresholds for expected behavior in different market regimes and validates specific historical stress events. It also compares data sources.
Inputs & outputs
When to use verify-regime
- →Validating regime-based strategies
- →Testing performance in market stress
- →Comparing financial data sources
About this skill
Verify Regime — Level 5
Command
uv run pytest tests/regime/ -v
Regime definitions
VIX-based thresholds applied to data/computed/regime_labels.csv:
| Regime | VIX range | Expected behavior |
|---|---|---|
| Low | < 12 | Small parity deviations, positive VRP |
| Normal | 12–20 | Baseline results hold |
| Elevated | 20–30 | Wider deviations, VRP signal noisy |
| Crisis | > 30 | Large parity deviations, VRP may flip |
What regime tests check
- Parity deviation by regime — crisis deviation > normal deviation (statistically)
- Backtest performance by regime — strategy Sharpe higher in normal than crisis
- VRP signal — positive mean in low/normal; check sign in elevated/crisis
- Regime transition — no artificial jumps at threshold boundaries
Stress event validations
Specific dates that must show expected behavior:
| Event | Date | Expected |
|---|---|---|
| COVID crash | 2020-03-16 | VIX > 80, parity deviation > 2% |
| VIX spike | 2018-02-05 | VIX > 37, large call/put spread widening |
| GFC | 2008-10-10 | If in sample: VIX > 70 |
A-B data source comparison
FRED VIXCLS vs CBOE VIX historical should match within 0.01 vol points.
Run: pytest tests/regime/test_source_comparison.py -v
Current status
tests/regime/ and data/computed/regime_labels.csv aren't built yet.
Depends on the data-computed skill producing regime labels from VIX thresholds.
When not to use it
- →When `verify-empirical` has not passed
- →When not testing across VIX regimes
- →When not validating stress events
Limitations
- →The skill depends on `data-computed` skill producing regime labels
- →The stress event validation is limited to specific dates like 2020-03-16 and 2018-02-05
- →The data source comparison is limited to FRED VIXCLS vs CBOE VIX historical data
How it compares
This skill provides a structured, automated way to verify financial models against specific market conditions and historical events, unlike manual data analysis.
Compared to similar skills
verify-regime side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| verify-regime (this skill) | 0 | 3mo | Review | Advanced |
| backtesting-frameworks | 17 | 2mo | No flags | Advanced |
| backtesting-trading-strategies | 10 | 1mo | Review | Intermediate |
| llm-evaluation | 6 | 2mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
backtesting-frameworks
wshobson
Build robust backtesting systems for trading strategies with proper handling of look-ahead bias, survivorship bias, and transaction costs. Use when developing trading algorithms, validating strategies, or building backtesting infrastructure.
backtesting-trading-strategies
jeremylongshore
Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".
llm-evaluation
wshobson
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
evaluating-llms-harness
davila7
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
data-quality-frameworks
wshobson
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
ab-test-setup
sickn33
Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.