Agent Skills Hub

policyengine-review-patterns

Standardized review patterns, validation checklists, and quality benchmarks for PolicyEngine codebases.

claude-code-skill

Control Claude Code via MCP protocol for autonomous development. Features persistent sessions, agent teams, precise execution planning, and advanced tool management for complex coding tasks.

seaborn

Statistical visualization library for Python. Create publication-quality graphics like box plots, heatmaps, and violin plots with pandas integration and automatic statistical estimation.

property-based-testing

Automated guidance for implementing property-based testing (PBT) in software and smart contracts to improve test coverage and edge case detection.

stats-tracker

Monitor Claude Code usage, token consumption, productivity streaks, and skill effectiveness metrics to optimize your development workflow.

risk-based-testing

Focus testing effort on highest-risk areas using risk assessment and prioritization. Use when planning test strategy, allocating resources, or making coverage decisions.

inno-prepare-resources

Automates research resource preparation by loading instances, searching GitHub for codebases, building dataset descriptions, and downloading arXiv papers.

margin-management

Monitor and manage margin-living strategy by tracking balances, interest costs, and coverage ratios. Provides automated scaling recommendations and safety alerts based on portfolio-to-margin thresholds.

karpathy-guidelines

Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.

senior-data-engineer

World-class senior data engineering skill for building scalable data pipelines, ETL/ELT systems, and modern data infrastructure using Python, Spark, dbt, and Kafka.

physics-student-focus

Teacher-focused student profiling tool: OCR answer sheets, summarize performance, and update student profiles with targeted physics learning goals.

autoresearch

Autonomous multi-team codebase improvement agent with specialized modes: narrow (goal-directed), broad (hypothesis-divergent), and sweep (quality-focused).