Agent skills by HKUDS, page 2

Fallback ladder for failed sandboxed code runs, plus the habit of fixing the working directory first so generated files land in the right place.

HKUDS/OpenSpace

Frameworks for comparing the A-share, H-share and US ADR prices of one Chinese company: AH premium, arbitrage signals, dual-listing valuation and delisting risk.

HKUDS/Vibe-Trading

Pulls free market data from the AKShare Python library: A-share, US and Hong Kong prices, futures, China macro series and forex, with notes on symbol formats and Chinese column names.

HKUDS/Vibe-Trading

Browses prebuilt cross-sectional factor libraries (Kakushadze 101, GTJA 191, Qlib 158, Fama-French and Carhart) and benchmarks whole libraries with IC and IR over a stock universe.

HKUDS/Vibe-Trading

Explains portfolio theory and the built-in optimizers: mean-variance (MPT), Black-Litterman, risk budgeting and all-weather allocation, plus rebalancing rules and config output.

HKUDS/Vibe-Trading

Turns behavioral-finance theory into trading signals and risk rules: overreaction and underreaction, momentum and reversal, sentiment extremes and a cognitive-bias checklist.

HKUDS/Vibe-Trading

Detects 15 classic candlestick patterns with vectorized pandas code and combines bullish and bearish scores into a long, short or flat trading signal.

HKUDS/Vibe-Trading

Fetches public crypto market data (candles, tickers, order books, trades) from 100+ exchanges through CCXT, and serves as the fallback when OKX is unavailable.

HKUDS/Vibe-Trading

Analyzes crude oil, gold and copper through supply-demand balance, pricing models, inventory cycles and futures structure, and outputs directional signals suitable for backtesting.

HKUDS/Vibe-Trading

Analyzes Chinese A-share convertible bonds with a three-part valuation, clause game analysis, the double-low strategy and a rotation framework for choosing bonds; instructions are in Chinese.

HKUDS/Vibe-Trading

Builds event-driven analysis for A-share companies: merger arbitrage spreads, shareholder buying and selling signals, equity incentives, placements and ST or delisting warnings; Chinese text.

HKUDS/Vibe-Trading

Covers bond pricing, credit ratings, default risk models (Altman Z-score, Merton, KMV), spread analysis and rate risk for fixed income work, with a focus on China's bond market; Chinese text.

HKUDS/Vibe-Trading

Guides writing signal_engine.py for backtests that mix markets such as A-shares, crypto, US equities and forex, with per-market parameters and volatility-adjusted weights.

HKUDS/Vibe-Trading

Covers three crypto-derivatives approaches: perpetual funding-rate arbitrage, futures term-structure trading in contango and backwardation, and options volatility and Greeks analysis.

HKUDS/Vibe-Trading

Compares DeFi yields across lending, liquidity provision, staking and yield farming, adjusts them for risks such as impermanent loss, and judges whether a protocol's returns are sustainable.

HKUDS/Vibe-Trading

Separates durable dividends from yield traps by checking yield quality, payout coverage, balance sheet strength, dividend history and valuation, with sector-specific payout measures.

HKUDS/Vibe-Trading

Reads PDF, Word, Excel, PowerPoint, image (OCR), CSV, text, config and source files through one read_document tool that returns extracted text in a uniform JSON envelope.

HKUDS/Vibe-Trading

Builds earnings forecasts and compares them with analyst consensus to find surprise trades, using top-down and bottom-up methods, SUE, post-announcement drift and revision momentum; Chinese text.

HKUDS/Vibe-Trading

Tracks analyst estimate revisions, earnings surprises, management guidance and post-earnings drift for US and Hong Kong stocks, and turns them into long and short signals.

HKUDS/Vibe-Trading

Interprets US company filings from SEC EDGAR (10-K, 10-Q, 8-K, proxy statements, Form 4) to pull out financials, risk factors and investment signals.

HKUDS/Vibe-Trading

Framework for analyzing ETFs with emphasis on China's market: product types, tracking error, fees, premium and discount, liquidity, fund size and picking among ETFs on one index; Chinese text.

HKUDS/Vibe-Trading

Scores news, announcements and macro events with the LLM, stores them in an event CSV and blends the decaying event signal with technical signals in signal_engine.py.

HKUDS/Vibe-Trading

Adds realistic execution assumptions to backtests: fixed, linear and square-root slippage, delayed fills, VWAP and TWAP logic and market-impact cost estimates; never for live orders.

HKUDS/Vibe-Trading

Evaluates factors across many instruments with IC and IR statistics and quantile backtests, then guides screening and weighting; uses the factor_analysis tool with factor and return CSVs.

HKUDS/Vibe-Trading

Reads the income statement, balance sheet and cash flow statement together to judge earnings quality, apply DuPont analysis and check 12 red-flag indicators for manipulation; Chinese text.

HKUDS/Vibe-Trading

Evaluates mutual funds, private funds and ETFs by return, risk and risk-adjusted metrics, style box and drift, and manager quality, then builds FOF portfolios; Chinese text.

HKUDS/Vibe-Trading

Builds value or growth stock screens from PE, PB, ROE and financial statement fields for backtests, using tushare data for A-shares and yfinance for Hong Kong and US stocks.

HKUDS/Vibe-Trading

Framework for central bank policy, exchange rate forecasting, geopolitical risk and capital flows that produces macro factor signals to guide cross-asset allocation.

HKUDS/Vibe-Trading

Harmonic Patterns signal engine. Identifies XABCD five-point structures such as Gartley/Bat/Butterfly/Crab based on Fibonacci geometry, and…

HKUDS/Vibe-Trading

Designs hedging plans for existing positions with futures, ETFs and options, covering beta hedges, protective puts, collars, tail risk and cross-asset hedges, with hedge ratios and cost estimates.

HKUDS/Vibe-Trading

Analyzes Northbound and Southbound Stock Connect flows between the mainland and Hong Kong, including quota use, sector allocation shifts and cross-border arbitrage signals.

HKUDS/Vibe-Trading

Generates trading signals from the Ichimoku five-line system using Tenkan and Kijun crossovers, cloud position and cloud direction, implemented in pandas.

HKUDS/Vibe-Trading

Reads open-position data and liquidation heatmaps to find liquidation clusters, cascade risk and stop-hunt zones, and uses them as support and resistance signals.

HKUDS/Vibe-Trading

Reads GDP, inflation, PMI, rates and FX data plus central bank policy to place the economy in a cycle stage and derive major asset allocation tilts for China, the US and Europe.

HKUDS/Vibe-Trading

Assesses a company's management on integrity, ability, capital allocation and governance from public information, producing a weighted score and a final trust verdict.

HKUDS/Vibe-Trading

Measures spreads, order-flow toxicity (VPIN, Kyle's lambda) and liquidity (Amihud, Roll) to improve cost estimates and execution, including China A-share auction and block trade mechanics.

HKUDS/Vibe-Trading

Fetches minute candlesticks from OKX, Tushare or yfinance, computes intraday VWAP, TWAP and volume distribution, and runs minute-level backtests by setting an interval in config.json.

HKUDS/Vibe-Trading

Trains scikit-learn models with walk-forward validation on features from OHLCV data to predict return direction and turn the predictions into trading signals.

HKUDS/Vibe-Trading

Pulls A-share price data from 通达信 (TDX) servers through the mootdx library over TCP, free and without an API key, as a stable fallback when akshare scraping is throttled.

HKUDS/Vibe-Trading

Ranks stocks by standardized factor scores (momentum, reversal, volatility, volume and valuation) and builds an equal-weight TopN portfolio with periodic rebalancing.

HKUDS/Vibe-Trading

Reads public blockchain data (active addresses, whale activity, TVL, DEX liquidity) and valuation metrics such as MVRV, NVT and SOPR to interpret conditions and generate signals.

HKUDS/Vibe-Trading

Covers volatility-surface modeling (SABR, local volatility), dynamic Greeks management, calendar spreads, skew and volatility arbitrage, and market-making basics for options.

HKUDS/Vibe-Trading

Backtests multi-leg option strategies by synthesizing Black-Scholes prices from the underlying, simulating PnL, Greeks exposure and expiration for crypto and equity options.

HKUDS/Vibe-Trading

Trades mean reversion between two correlated instruments using the Z-score of their price ratio, going long one leg and short the other when the ratio stretches.

HKUDS/Vibe-Trading

Explains why a portfolio beat or lagged its benchmark with Brinson sector attribution, factor alpha and beta decomposition, timing evaluation and benchmark comparison.

HKUDS/Vibe-Trading

Analyzes perpetual futures funding rates and spot-futures basis to find carry trades, crowded positioning and sentiment signals, including funding arbitrage between exchanges.

HKUDS/Vibe-Trading

Translates a Python backtest strategy or a plain description into Pine Script v6, TDX formulas and MQL5 code for TradingView, Chinese broker terminals and MetaTrader 5.

HKUDS/Vibe-Trading

Runs a six-lens research framework on pre-IPO and private companies, labels every data point by confidence, and produces a fair-value range, exit-path analysis and information-gap map.

HKUDS/Vibe-Trading