claude

fin-models

Quantitative model families - factor models, covariance and risk models, VaR/CVaR and their backtests, portfolio optimizers, volatility models, state-space and Kalman, cointegration and statistical arbitrage, time-series forecasting, option pricing and implied-volatility surfaces, term-structure and credit models. One skill per model family: which Python implementation is verified, the pitfalls that produce wrong numbers, and an executable script that reproduces the claim.

1 on GitHubv0.1.0MITupdated 1 month ago
/

Plugin fin-models from marketplace fin-skills in howard-lynn-ye/fin-skills. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (13)

  • covariance-and-risk-models

    Estimate a covariance matrix an optimizer can actually invert, and report how much variance it hides. TRIGGER - covariance matrix estimation, sample covariance singular, "matrix is not positive definite", np.cov more assets than observations, N > T, condition number, Ledoit-Wolf shrinkage, sklearn L

  • credit-risk-models

    Estimate a default probability and price credit, and keep the two probabilities apart - the risk-neutral one that prices and the physical one that forecasts. TRIGGER - Merton model, structural credit model, KMV, distance to default, asset value and asset volatility from equity, N(-d2), solve the two

  • factor-and-timeseries-research

    Judge whether a cross-sectional factor predicts returns, and forecast financial series. TRIGGER - information coefficient, IC, quantile returns, factor decay, turnover, alphalens; Fama-French, Fama-MacBeth, PanelOLS, linearmodels, cross-sectional asset pricing; event study, abnormal returns, CAR, BH

  • factor-models

    Build long-short factor portfolios from a characteristic panel and test the alpha with standard errors that survive serial correlation. TRIGGER - factor model, Fama-French, Fama-MacBeth, cross-sectional regression, decile or quintile long-short sort, 2x3 sort, SMB and HML, value- weight vs equal-wei

  • implied-vol-surface

    Build a volatility surface that is not silently arbitrageable - invert prices to implied vols, fit a smile, check butterfly and calendar arbitrage, and interpolate between maturities. TRIGGER - implied volatility solver, Newton diverges, bisection bracket, "implied vol returns 0.001", "no implied vo

  • option-pricing-models

    Implement an option pricing model correctly - closed form, tree, characteristic function, Monte Carlo - and the four places each silently returns a plausible wrong number. TRIGGER - Black-Scholes-Merton with dividend yield, binomial tree, CRR, Cox-Ross-Rubinstein, American early exercise, Richardson

  • portfolio-optimizers

    Turn expected returns and a covariance matrix into weights, and measure what the optimizer did to your estimation error on the way. TRIGGER - portfolio optimization, mean-variance, Markowitz, efficient frontier, tangency or max-Sharpe portfolio, minimum-variance portfolio, long-only and budget const

  • risk-measures-var-cvar

    Compute Value-at-Risk and Expected Shortfall by the four estimators that disagree in the tail, and backtest them properly. TRIGGER - VaR, value at risk, CVaR, expected shortfall, ES, tail risk, 99% VaR, 95% VaR, historical simulation VaR, parametric normal VaR, Cornish-Fisher expansion, EVT, peaks o

  • stat-arb-cointegration

    Screen, test and trade a cointegrated pair without counting the trials wrong, applying the single-series ADF table to a fitted residual, or estimating the hedge ratio on the window you score it in. TRIGGER - cointegration, Engle-Granger, statsmodels coint, coint_johansen, Johansen, trace statistic,

  • state-space-and-kalman

    Estimate a time-varying hedge ratio or beta with a Kalman filter, and know which of its three state series you are allowed to trade - the smoothed one has read the whole sample. TRIGGER - Kalman filter, Kalman smoother, RTS smoother, state space model, local level, local linear trend, time-varying b

  • term-structure-models

    Build and fit a yield curve, and price a zero-coupon bond in a short-rate model, without the convention and identification traps. TRIGGER - bootstrap a zero curve, par rates to zero rates, discount factors to zero rates, par bond reprice, curve stripping; day count ACT/365 ACT/360 30/360, annual vs

  • time-series-forecasting-models

    Score a forecast against the baseline it has to beat - naive, seasonal-naive, drift, mean - with MASE, rolling-origin evaluation and a Diebold-Mariano test, instead of an R^2 on a price level. TRIGGER - forecasting, ARIMA, SARIMA, SARIMAX, auto_arima, ETS, Holt-Winters, exponential smoothing, statsm

  • volatility-models

    Fit and forecast volatility - GARCH, range-based realized variance, HAR-RV - without the two errors that silently move the answer: the units `arch` expects, and a range estimator used on bars that gap. TRIGGER - GARCH, GARCH(1,1), EGARCH, GJR-GARCH, arch_model, conditional_volatility, DataScaleWarni

View source on GitHub

More from howard-lynn-ye/fin-skills

All 109 plugins →

FEDERATED - the claims inside are not verified by this repo. 501 engineering-grade trading skills - point-in-time backtest schemas, universe look-ahead, alt-data availability lag, ML against transaction costs, adjusted-vs-unadjusted prices, backtest determinism and audit trails, broker idempotency and failover, exchange FIX specs (ASX, B3, Bursa, BIST, Cboe), regulatory gates and a key-scope audit skill. Its README claims 458 of 501 cite a primary source; it is clearly LLM-generated at scale and the depth is unverified. Upstream splits these into per-domain plugins, but its root manifest exposes all 501 at once - roughly 25x the discovery budget, which is yours to spend since it installs disabled. No credentials in the skills; nothing executes. Installs disabled.

200 skills

1

FEDERATED - the claims inside are not verified by this repo. FTShare's official one-endpoint-per-skill data catalogue for the Chinese market: A/HK/US quotes and K-lines, 可转债 including SZSE declaration snapshots, ETF PCF and IOPV, 龙虎榜, block trades, margin balances, executive holdings, the ChinaBond yield curve, the CPI/PPI/PMI/LPR/M2/credit macro series and news-sentiment factors. FTSHARE_API_KEY in the environment (a free tier exists per the launch article); read-only. Be deliberate: 215 sub-skills is roughly 10x the ~20-skill discovery budget, so treat it as a catalogue to enable for a session, not a standing install - it arrives disabled and the budget is yours to spend. Installs disabled.

200 skills

1

FEDERATED - the claims inside are not verified by this repo. The deepest IFRS/GAAP pack in this sweep that also validates cleanly: IFRS 9 expected credit loss, IFRS 16 leases, IAS 12 deferred tax, revenue recognition, consolidation, SOX, forensic accounting, insurance reserving, WACC, LBO, treasury and Basel banking compliance, with an eval harness in the repo. Outside this library's quant core and overlapping the banking-regulatory entry on Basel and IFRS 9. Optional Stripe/Plaid connectors; nothing executes. Installs disabled.

48 skills · 52 commands

1

FEDERATED - the claims inside are not verified by this repo. HKUDS' 33k-star trading agent, taken for its skill tree alone - the richest algorithm content this sweep found: the Kakushadze 101, GTJA 191 and Qlib 158 alpha zoos, factor IC/IR research, execution models (square-root impact, VWAP/TWAP), microstructure (VPIN, Kyle's lambda, Amihud), SABR and local-vol options, convertible bonds, credit, Brinson attribution, GARCH/ADF and a Pine/vnpy exporter. The skills are coupled to the app's data router and Python toolkit, so test them standalone before trusting them; data keys go in a .env, and live orders are reachable only through a separate gated connector with a kill switch, not from these skills. 90 skills is about 4.5x the discovery budget. Installs disabled.

91 skills

1

FEDERATED - the claims inside are not verified by this repo. The closest structural peer to fin-libraries found in the wild - 82 one-library skills in Chinese - and the only pack anywhere in this sweep with actuarial and structured-credit content: MlFinLab information bars and fractional differencing, arch/GARCH, alphalens, bt/backtrader/nautilus/qlib/LEAN, QuantLib and FinancePy day counts and schedules, XVA (CVA/DVA/FVA, SIMM), chainladder loss reserving, IFRS 9 ECL, credit scorecards and transition matrices, ABS waterfalls, Smith-Wilson EIOPA curves. Depth is unverified and the author has one star; the easytrader and nautilus skills document live-broker paths but nothing executes by default. 82 skills is roughly 4x the discovery budget. Installs disabled.

82 skills

1

FEDERATED - the claims inside are not verified by this repo. The maintained superset of geeksfino-finskills, 107 skills across China, Hong Kong and US directories: A+H premium, block deals, 龙虎榜, pledge risk, goodwill, 解禁 unlocks, margin risk, factor crowding, event studies, valuation regimes, and HK southbound, currency and liquidity monitors. Free data sources; nothing executes. Two caveats - it has been idle since February 2026, and 107 skills is roughly 5x the discovery budget, which is yours to spend since it installs disabled. Installs disabled.

79 skills

1

Similar plugins

Systematically diagnose Mooncake deployment and runtime issues (services, RDMA, env vars, connectivity, logs) and propose fixes.

1 skill

kvcache-ai/Mooncake 7,030

Skills and a local MCP server for portfolio risk on supplied data, with VaR, Expected Shortfall, backtests, stress tests and counterparty, credit and FRTB figures.

14 skills · 1 MCP server

hashgraph-online/awesome-codex-plugins 1,566

Switch or repair the model configuration of an OpenClaw instance (e.g., Kimi k2p6 → k3): change the default model, add model definitions, and fix model-config failures — 401 "Invalid token", "No available channel / model not found", thinking-level rejections, and config edits that don't take effect. Ships a config-discovering switch script with backup + mirror sync, an endpoint probe protocol, and a field-tested trap catalog (env-var key hijack, provider-plugin thinking restrictions, relay availability).

1 skill

daymade/claude-code-skills 1,527

jf-skills

claude

Twelve-skill bundle covering the The Journal of Finance (JF) manuscript lifecycle, with JF-specific mechanics (AFA portal, tiered submission fee, 60-page limit, bundled Internet Appendix, Data and Code Sharing Policy).

12 skills

brycewang-stanford/Awesome-Journal-Skills 1,413

Use when you need to refactor Java code to adopt modern Java features (Java 8+) — including migrating anonymous classes to lambdas, replacing Iterator loops with Stream API, adopting Optional for null safety, switching from legacy Date/Calendar to java.time, using collection factory methods, applying text blocks, var inference, or leveraging Java 25 features like flexible constructor bodies and module import declarations.

1 skill

jabrena/plinth 462

PreToolUse and PostToolUse hooks that catch secrets leakage patterns: echoing env vars, reading secret files, tokens in URLs, and missing gitignore/permissions on sensitive files.

hooks

ed3dai/ed3d-plugins 253

Maintain fin-models?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins109 plugins