Agent Skills Hub

build-design-system

Build a cohesive, constraint-based design system using the Design Graph methodology. Automate the creation of design tokens, typography scales, components, variants, and themes.

wechat-publisher

One-click publishing of Markdown articles to WeChat Official Account drafts, featuring automated image hosting, multi-theme styling, and code syntax highlighting.

plan-down

Method-driven planning workflow that intelligently decomposes tasks into structured plan.md files using zen-mcp tools, adapting to user clarity and automation needs.

google-calendar

Manage and sync multiple Google Calendar accounts with parallel querying, scheduling, and conflict detection.

figma-design-to-code

Convert Figma designs to project-consistent UI code using TemPad Dev MCP for precise markup, styling, and token integration.

deepscan-monitor

Manage long-running PapersFlow DeepScan research workflows with asynchronous monitoring, live progress tracking, and automated report generation.

my-tasks

Manage your personal OpenAnt task history, status, and assignments. Retrieve, track, and review tasks as a worker or creator.

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.

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.

video-pipeline

An end-to-end video processing pipeline that transforms raw recordings into transcripts, key insights, short clips, and polished articles.

serena-mcp

Semantic code analysis guide for Serena MCP. Automatically prioritizes Serena tools for symbols, references, and code memory to optimize context and efficiency.

sequential-thinking

Structured reasoning tool for complex problem decomposition, step-by-step analysis, consistency verification, and evidence-based synthesis with confidence scoring.