Agent Skills Hub

dashboard-design

A structured design and planning tool for Vizro dashboards, enforcing a 3-step workflow (requirements, layout, visualization) to ensure production-ready dashboard development.

llm-integration

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

crowi-migration

Automated migration workflow from legacy Crowi (Express/Swig) to modern architecture (Next.js 16/Fastify/ts-rest).

context-engineering-collection

A structured repository of Agent Skills for context engineering, multi-agent architectures, and production-grade agent system optimization.

subagent-driven-development

Execute implementation plans using isolated subagents for each task, featuring a rigorous two-stage review process for spec compliance and code quality.

tikhub-api-helper

Search and query TikHub social media APIs for TikTok, Douyin, Xiaohongshu, Instagram, YouTube, and more to fetch cross-platform data.

nuxt

Nuxt framework disambiguation layer for optimizing project development, routing to the correct Nuxt pack, Vue guidance, or module-specific logic.

agent-architecture

Implement production-grade AI agents with LangGraph, tool-calling guardrails, SSE streaming, and episodic memory. Includes anti-patterns, fix pairs, and stateful architecture patterns.

openai-whisper

Local speech-to-text transcription using the OpenAI Whisper CLI, providing private, high-accuracy audio processing without external API keys.

session-memory

Enables cross-session context persistence for Claude Code, managing history, project decisions, and workflow patterns to ensure seamless task continuation.

openapi-spec-generator

Generates OpenAPI 3.0/3.1 specs from code (FastAPI, NestJS) or design-first schemas. Includes client SDK generation, mock server setup, and support for Swagger/ReDoc/Stoplight documentation workflows.

performance-testing

Profiles application performance using k6, Artillery, or JMeter to measure latency, throughput, and error rates. Ideal for planning load, stress, and soak tests to identify bottlenecks.