Agent Skills Hub

novelty-check

Verify research idea novelty against recent literature. Use when user says '查新', 'novelty check', or needs to confirm if a method is original.

ascii-art

A generative agent skill for creating ASCII art, optimized for rapid, single-pass artistic output without iterative refinement.

BDD-prompts-with-eval

An AI-driven active listening framework to extract, clarify, and structure requirements, business values, and scope from ambiguous user stories.

evaluation

Build systematic evaluation frameworks for AI agents using multi-dimensional rubrics, LLM-as-a-judge, and regression testing to measure performance, quality, and context engineering effectiveness.

openai-agent-sdk-skill

Build AI agents, multi-agent systems, and workflows using the OpenAI Agents SDK for TypeScript/JavaScript. Supports tools, handoffs, guardrails, MCP, and realtime voice.

llm-integration

A toolkit for building robust LLM integrations: API patterns, streaming, function calling, RAG pipelines, and cost-effective model routing.

orchestrator

Autonomous multi-agent orchestration framework for Claude Code with memory-driven workflows, parallel-first task execution, Aristotle-based deconstruction, and multi-stage quality gates.

karpathy-guidelines

Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.

visual-creative

AI-powered creative visual prompt generator for posters, banners, product shots, and social media content.

user-story-mapping

Create a hierarchical user story map to visualize the user journey, plan MVP releases, and align product, design, and engineering teams on workflow priorities.

skyll

A runtime skill discovery engine for AI agents. Search and retrieve specialized agent skills (SKILL.md) on-demand via REST API or MCP to inject procedural knowledge into your agent's context.

project-development

A framework for managing the end-to-end LLM project lifecycle, from evaluating task-model fit and pipeline architecture design to implementing structured output parsing and agent-assisted development.