nixtla-liquidity-forecaster
Forecasts orderbook depth and spreads to optimize trade execution timing. Use when needing to estimate market liquidity for large orders. Trigger with 'forecast liquidity', 'predict orderbook', 'estimate depth'.
npx skills add majiayu000/claude-skill-registry --skill nixtla-liquidity-forecaster-intent-solutions-io-plugins-nixtla --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Liquidity Forecaster Predicts future orderbook depth and bid-ask spreads using historical market data and TimeGPT. ## Overview This skill analyzes historical trade data and orderbook snapshots from Polymarket to forecast liquidity conditions. It predicts near-term changes in orderbook depth and bid-ask spreads, helping determine optimal trade execution timing. The workflow fetches data via Polymarket API, preprocesses it for TimeGPT compatibility, and generates forecasts with visualizations and reports. **When to use**: Determining optimal trade execution timing based on expected liquidity conditions, predicting orderbook depth changes, estimating bid-ask spread evolution. **Trigger phrases**: "forecast liquidity", "predict orderbook depth", "estimate spread changes", "analyze market liquidity", "forecast trading conditions". ## Prerequisites **Required environment variables**: - `NIXTLA_TIMEGPT_API_KEY` - Your Nixtla TimeGPT API key **Python packages**: ```bash pip install nixtla pandas requests matplotlib ``` **Required tools**: Read, Write, Bash, Glob, Grep, WebFetch **Minimum Python version**: 3.8+ ## Instructions ### Step 1: Fetch orderbook data Fetch historical orderbook da
- Overview
- Prerequisites
- Instructions
- Step 1: Fetch orderbook data
- Step 2: Preprocess data
- Step 3: Execute forecast
- Step 4: Interpret results
- Output
- Error Handling
- Examples
- Example 1: Forecast depth for presidential election market
- Example 2: Forecast spread for cryptocurrency market
- Example 3: Quick workflow for sports outcome market
- Resources
pip install nixtla pandas requests matplotlib
python {baseDir}/scripts/fetch_data.py --market_id <MARKET_ID> [--output orderbook_data.csv]
python {baseDir}/scripts/preprocess_data.py --input_file orderbook_data.csv [--output preprocessed_data.csv]
python {baseDir}/scripts/forecast_liquidity.py --input_file preprocessed_data.csv --horizon <PERIODS> [--output depth_forecast.csv] [--plot_prefix depth]
python {baseDir}/scripts/fetch_data.py --market_id trump_election_2024
python {baseDir}/scripts/preprocess_data.py --input_file orderbook_data.csv
python {baseDir}/scripts/forecast_liquidity.py --input_file preprocessed_data.csv --horizon 6
python {baseDir}/scripts/fetch_data.py --market_id eth_price_3000 --output eth_orderbook.csv
python {baseDir}/scripts/preprocess_data.py --input_file eth_orderbook.csv --output eth_preprocessed.csv
python {baseDir}/scripts/forecast_liquidity.py --input_file eth_preprocessed.csv --horizon 24 --output eth_spread_forecast.csv --plot_prefix eth_spreadWhat does the nixtla-liquidity-forecaster skill do?
Forecasts orderbook depth and spreads to optimize trade execution timing. Use when needing to estimate market liquidity for large orders. Trigger with 'forecast liquidity', 'predict orderbook', 'estimate depth'.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill nixtla-liquidity-forecaster-intent-solutions-io-plugins-nixtla --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.