Agent Skills Hub

context-degradation

Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.

workflow-execute-plans

Execute implementation plans in small, verifiable batches with pause-for-feedback checkpoints to prevent drift and ensure code quality.

conference-talk-builder

Transform raw ideas into structured conference talk scripts using narrative frameworks. Features slide-by-slide content planning, speaker notes, and timing guidance in a tool-agnostic format.

minimax-tts

Perform internet searches using the Zhipu AI web search API to retrieve real-time information, news, and current data.

gemini-api

Google Gemini Image Generation API interface for text-to-image, editing, style templates, and automated retry workflows.

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.

milady-development

Self-modify your Milady agent by managing plugins. Edit code, rebuild, and restart the runtime to develop new capabilities or improve agent workflows locally.

supermemory

Supermemory is a long-term memory infrastructure for AI agents, enabling persistent context, user profiles, and semantic RAG across multi-modal knowledge bases.

workflow-producer

A stage-driven AI writing agent for structured, repeatable, and reversible long-form content production with human-in-the-loop workflows.

hs

Pre-execution security guardrails for AI agents. Validates shell commands and file reads against 400+ security patterns to block destructive operations, credential theft, and unauthorized system access.

brave-search

Headless web search and content extraction using Brave Search API. Perform documentation lookups, factual research, and web data retrieval without a browser.

swarm

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