cycle-detector
Analyzes market data to classify real estate cycles into Recovery, Boom, Bust, or Stabilization phases.
Install
mkdir -p .claude/skills/cycle-detector && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15264" && unzip -o skill.zip -d .claude/skills/cycle-detector && rm skill.zipInstalls to .claude/skills/cycle-detector
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.
Real estate cycle phase detection using price momentum, credit conditions, construction activity, and sentiment indicators. Classifies markets into Recovery, Boom, Bust, or Stabilization phases.Key capabilities
- →Detect current phase of the real estate cycle
- →Identify market risk using a multi-indicator framework
- →Determine investment timing for property
- →Analyze property market overheating
- →Classify markets into Recovery, Boom, Bust, or Stabilization phases
How it works
The skill uses a 7-indicator model, including price momentum and credit growth, to score and classify the current phase of the real estate cycle.
Inputs & outputs
When to use cycle-detector
- →Check property market phase
- →Evaluate housing correction status
- →Analyze market overheating
- →Determine investment timing
About this skill
Property Cycle Detector
Purpose
Detect the current phase of the real estate cycle for any country or city using a multi-indicator framework. The property cycle is one of the most predictable economic cycles (18-year average) — correct phase identification is the foundation of property investment, mortgage risk management, and construction sector analysis.
When to Use
- "Where are we in the property cycle?"
- "Is it time to buy or sell property?"
- "Property market overheating?"
- "Is the housing correction over?"
- "Which cycle phase is [City/Country] in?"
Phase Detection Framework
7-Indicator Model
| # | Indicator | Weight | Recovery | Boom | Bust | Stabilization |
|---|---|---|---|---|---|---|
| 1 | Real House Price Momentum (12M) | 25% | Flat to +3% | +5 to +15% | -5 to -15% | -3 to +3% |
| 2 | Price-to-Income vs LT Avg | 20% | Below avg | Above avg | Falling to avg | At avg |
| 3 | Housing Credit Growth (YoY) | 15% | Low, turning up | High, accelerating | Contracting | Turning positive |
| 4 | Building Approvals (YoY) | 15% | Low, stabilizing | High, rising | Collapsing | Bottoming |
| 5 | Months of Inventory | 10% | High, declining | Low (<3 months) | Rising rapidly | Peaking, then declining |
| 6 | Auction Clearance Rate | 10% | 50-60% (improving) | > 70% | < 50% | 50-60% (stabilizing) |
| 7 | Investor Activity (% of lending) | 5% | Low, turning up | High (>35%) | Very low | Low |
Phase Classification
Each indicator is scored -2 (bust signal) to +2 (boom signal). Weighted sum determines phase:
| Score Range | Phase | Signal |
|---|---|---|
| +8 to +14 | Boom (Late) | Reduce — speculative excess |
| +4 to +7 | Boom (Early-Mid) | Hold — momentum intact |
| -3 to +3 | Transition | Watch — phase change approaching |
| -7 to -4 | Bust (Early-Mid) | Avoid — correction underway |
| -14 to -8 | Bust (Late) / Stabilization | Screen for value — bottom forming |
Country Data Sources
| Country | House Price Index | Source |
|---|---|---|
| US | Case-Shiller National | FRED: CSUSHPISA |
| UK | UK HPI / Nationwide | ONS API |
| Australia | CoreLogic HVI | ABS / CoreLogic |
| New Zealand | REINZ HPI | REINZ / RBNZ |
| Canada | Teranet-National Bank HPI | CREA / Teranet |
| China | 70-City Index | NBS |
Process
# US example
python3 mcp-servers/fred-mcp/server.py get_series '{"series_id":"CSUSHPISA","limit":60}'
python3 mcp-servers/fred-mcp/server.py get_series '{"series_id":"HOUST","limit":60}'
python3 mcp-servers/fred-mcp/server.py get_series '{"series_id":"MORTGAGE30US","limit":24}'
# NZ example
python3 mcp-servers/stats-mcp/server.py get_series '{"series_id":"house-price-index"}'
Red Flags
- National averages mask city-level divergence — drill down to city for investment decisions
- The cycle can extend — Phase 2 (Boom) has lasted 15+ years in some markets (Australia 1991-2017 with brief interruptions)
- Policy intervention (macroprudential, tax) can accelerate or delay phase transitions
- The 18-year cycle is an empirical observation, not a law — treat as framework, not prediction
When not to use it
- →When national averages are used for city-level investment decisions
- →When the cycle is assumed to be fixed at 18 years
- →When policy intervention is not considered
Limitations
- →National averages mask city-level divergence
- →The cycle can extend
- →Policy intervention (macroprudential, tax) can accelerate or delay phase transitions
How it compares
This skill provides a structured 7-indicator model for real estate cycle detection, offering a quantitative approach to phase classification unlike general market observations.
Compared to similar skills
cycle-detector side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| cycle-detector (this skill) | 0 | 3mo | Review | Intermediate |
| exploratory-data-analysis | 15 | 2mo | Review | Intermediate |
| model-compare | 7 | 8mo | Review | Advanced |
| astropy | 6 | 7mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by wonderstone
View all by wonderstone →You might also like
exploratory-data-analysis
K-Dense-AI
Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.
model-compare
rawwerks
Compare 3D CAD models using boolean operations (IoU, Dice, precision/recall). Use when evaluating generated models against gold references, diffing CAD revisions, or computing similarity metrics for ML training. Triggers on: model diff, compare models, IoU, intersection over union, model similarity, CAD comparison, STEP diff, 3D evaluation, gold reference, generated model, precision recall 3D.
astropy
davila7
Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.
statistical-analysis
anthropics
Apply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing. Use when analyzing distributions, testing for significance, detecting anomalies, computing correlations, or interpreting statistical results.
datacommons-client
davila7
Work with Data Commons, a platform providing programmatic access to public statistical data from global sources. Use this skill when working with demographic data, economic indicators, health statistics, environmental data, or any public datasets available through Data Commons. Applicable for querying population statistics, GDP figures, unemployment rates, disease prevalence, geographic entity resolution, and exploring relationships between statistical entities.
analyzing-market-sentiment
jeremylongshore
Analyze cryptocurrency market sentiment using Fear & Greed Index, news analysis, and market momentum. Use when gauging overall market mood, checking if markets are fearful or greedy, or analyzing sentiment for specific coins. Trigger with phrases like "analyze crypto sentiment", "check market mood", "is the market fearful", "sentiment for Bitcoin", or "Fear and Greed index".