MCP App StoreMCP App StoreSKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
autostar
A generalized autonomous optimization loop (soft RLVR) for iteratively improving any measurable artifact through structured experiments.
longrun
Generates structured orchestrator prompts and launch commands for GitHub Copilot CLI to handle long-running autonomous tasks.
auto-improve
An autonomous, judge-gated loop that iteratively improves text artifacts using a rubric and a separate evaluator model to ensure verified gains.
openskynet
Optimizes token usage by isolating large payloads to subagents and maintaining concise summaries in the main thread.
agentfiles
Structured personal AI knowledge pack: agent definitions and operational docs to help Claude Code–compatible agents apply a user's knowledge base.
code-abyss
Reference guide for designing single- and multi-agent LLM systems, RAG pipelines, security hardening, and prompt engineering for production agents.
langium-ai
CLI to generate language descriptors, synthesize system prompts, and run evaluations to iteratively refine AI tooling for Langium projects.
prompt-master
Generates production-ready, token-efficient prompts tailored to specific AI tools and tasks.
boss-skills
Turn meeting notes, chats, or archetypes into a reusable boss-persona skill for management guidance and role-based prompts.
boshu2
Mine past agent sessions for working prompts, decisions, rituals and recovery patterns (operational tooling).
claude-art-skill
Generate brand-aware visuals and diagrams with routing for multiple aesthetics, workflows for editorial headers, diagrams, and image editing, and opinionated mo