Agent Skills Hub

guard

Epistemic safety analysis for JSON data in prompts to prevent LLM hallucinations and reasoning errors when handling incomplete or large-scale datasets.

data-cleaning-pipeline-generator

Generates data cleaning pipelines for pandas/polars/PySpark, handling missing values, duplicates, outliers, type conversions, and validation.

statsmodels

Statistical modeling and econometrics library for Python. Performs OLS, GLM, mixed models, ARIMA, diagnostics, and inference for rigorous scientific analysis.

predict-lucky-number

Generates a random lucky number between 0 and 9999 for games, decision-making, or entertainment.

auto-trading-strategy

Professional trading strategy and risk management toolkit for prediction markets and crypto, featuring trend analysis, position sizing, and stop-loss frameworks.

pipeline

Manage dlt data pipelines and Temporal workflows for the SignalRoom marketing platform. Sync sources like Everflow, Redtrack, and S3 to Postgres, check status, and debug ingestion.

qmd

Local hybrid search engine for markdown notes, documentation, and codebase knowledge bases to reduce token consumption and improve retrieval efficiency.

fullstack-workflow

A standardized fullstack pattern for Next.js features, integrating GET API routes, server actions, SWR data fetching, and React Hook Form with Zod validation.

differentiation-schemes

Generate finite-difference stencils, select optimal numerical schemes for PDEs/ODEs, and perform truncation error analysis to improve simulation accuracy.

writing-go-tests

Applies current Go testing best practices, including concurrent testing, mocking, and table-driven design for robust software development.

search

Search the web using Tavily's LLM-optimized search API for relevant, source-cited content without writing code.

identify-assumptions-existing

Stress-test existing product feature ideas by identifying risky assumptions across Value, Usability, Viability, and Feasibility using a multi-perspective devil's advocate framework.