Agent Skills Hub

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.

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.

mutation-testing

Validate test suite effectiveness and uncover weak assertions by introducing code mutations and measuring kill rates. Essential for proving tests genuinely catch bugs rather than just satisfying coverage metrics.

plumb

Keep your technical specifications, test suites, and source code perfectly synchronized during AI-assisted development.

functions

Deploy serverless browser automation as cloud functions using Browserbase. Perfect for cron jobs, webhook endpoints, and scalable cloud-based automation tasks.

status

Monitor project progress, analyze active tracks, and identify blockers within your development workspace.

openai-agents-sdk

Build AI agents with the OpenAI Agents SDK for Python. Supports multi-agent handoffs, function tools, stateful sessions, streaming, and Azure OpenAI integration via LiteLLM.

mcp-builder

A guide for building high-quality MCP (Model Context Protocol) servers in Python or TypeScript to integrate external APIs and services into LLM workflows.

submit-work

Submit completed tasks on OpenAnt via CLI. Handles text reports, file uploads (images, docs, code), and external proof links to ensure verified deliverables.

context-compression

Optimize agent performance and token usage through advanced context compression, structured summarization, and task-oriented state management for long-running sessions.

pyhealth

Comprehensive Python healthcare AI toolkit for clinical data processing, medical coding translation, and developing deep learning models like RETAIN and Transformers for EHR, physiological signals, and clinical prediction tasks.

context-management

Proactive context window management for AI agents via intelligent token monitoring, snapshot creation, and selective state rehydration to maintain continuity during long sessions.