Agent Skills Hub

spawn-decision

A specialized decision-making agent for complex architectural choices, task planning, and error resolution within the orchestration system.

trulens-evaluation-workflow

A systematic workflow to instrument, evaluate, and monitor LLM applications using TruLens, supporting frameworks like LangChain, LangGraph, and LlamaIndex.

glyphbox

A framework for an LLM-based NetHack agent that dynamically synthesizes Python code in a secure sandbox to perform complex dungeon exploration and gameplay actions via a high-level API.

eval-harness

Official evaluation framework for AI agent sessions, implementing Evaluation-Driven Development (EDD) principles to ensure reliability.

Investigating Code Patterns

Systematically trace code flows, locate implementations, diagnose performance issues, and map system architecture to understand complex codebases.

moollm

A microworld operating system for LLM-based agent living memory, transforming filesystems into navigable rooms and code into habitable worlds.

matchms

Python toolkit for mass spectrometry data processing. Enables spectral file importing (mzML, MGF, MSP), metadata harmonization, peak filtering, and calculating spectral similarity scores (cosine, modified cosine) for metabolomics.

test-design-techniques

Expert systematic test design using BVA, equivalence partitioning, decision tables, and combinatorial testing to maximize coverage and minimize redundancy.

presentation-structure

Technical specification and structural guidelines for the project's single-file HTML/CSS/JS presentation system.

code-review-specialist

A specialized code review agent that performs multi-dimensional analysis covering security vulnerabilities, performance optimization, code quality, and maintainability standards.

calorie-detective-v2-0-0

AI-powered food calorie and nutrient calculator. Uses vision recognition to identify meals, calculate macronutrients, and provide health suggestions based on a built-in nutrition database.

swarm

Orchestrate parallel Claude Code worker swarms with protocol-based behavioral governance for complex features, multi-step refactors, and long-running autonomous coding sessions.