Agent Skills Hub

setup

Guide new contributors through the Chops development environment, including prerequisite checks, project generation via xcodegen, and architecture orientation.

evaluating-code-models

Evaluate code generation models using BigCode Evaluation Harness. Benchmarks include HumanEval, MBPP, and MultiPL-E with pass@k metrics for multi-language coding models.

repomix

Package entire code repositories into single, AI-optimized files. Ideal for providing codebase context to LLMs like Claude, ChatGPT, and Gemini for analysis, security audits, and bug investigations.

matlab-live-script

Generate professional MATLAB plain text Live Scripts (.m files) with rich text documentation, mathematical equations, and visualization code following specific formatting standards.

frontend-to-backend-requirements

Standardize frontend communication by documenting data requirements and business rules for backend developers, ensuring clear alignment without dictating implementation details.

lambda

Manage AWS Lambda serverless functions: deploy code, configure event triggers, debug invocations, optimize cold starts, and maintain layers.

structured-code-review

Performs a structured five-stage code review covering requirements, correctness, code quality, testing, and security. Provides actionable, categorized feedback (Blocker/Major/Minor/Nit) to improve PR quality.

mcp-development

Guidance for Model Context Protocol (MCP) server development, including tool design, resource handling, and AI/ML integration patterns.

nuxt-test-skill

A testing utility for the npm-agentskills framework, designed to validate Nuxt module integration and skill discovery patterns.

specstory-organize

Automatically organize your SpecStory AI coding session history into a structured YYYY/MM directory hierarchy to improve file management and archiving.

research-pipeline

End-to-end autonomous research agent: from idea generation and literature review to experiment execution, adversarial review loops, and paper writing.

yq

Extract specific fields from YAML files efficiently without reading entire files, saving 80-95% of context window usage.