Skill UI

Calculate the cost per million tokens for running AI models locally on your own hardware like Ollama or llama.cpp. It factors in electricity prices, hardware costs, power consumption, and generation speed to determine the break-even point against hosted API models. Useful for deciding whether to deploy models locally or use cloud services based on actual usage and financial constraints.

Use difyctl to discover and run operations on a Dify server, and build, test, publish, and modify Workflow and Chatflow apps through a dynamic command catalog.

This skill coordinates work across a RuFlo AI-agent swarm by discovering channels, reading signed updates, and checking claims. It helps manage multi-agent status, handoffs, ownership conflicts, and shared-work planning. Users must treat relay-sourced messages as untrusted and avoid irreversible actions unless explicitly requested. It ensures safe coordination without unauthorized state changes.

Connect AI agents to the A4A end-to-end encrypted agent-to-agent messaging network using local MCP tools or the Python SDK, with secure identity and contact controls.

This AI-powered tool generates engaging introductions for blog posts based on provided topics, article angles, or existing drafts. It helps streamline content creation by adapting to specific audiences and tones without requiring extensive form filling. Ideal for SEO-focused writers looking to optimize their opening paragraphs quickly and efficiently.

Reviews pasted text to detect signs of AI-generated content, returning an indeterminate authorship status with quoted editorial observations and suggested wording improvements. Useful for SEO content audits, editing, and quality review.

Generate structured content outlines for SEO articles based on topics or reader questions. This AI tool helps plan article structure, sections, and purposes efficiently without requiring manual form filling. Ideal for content strategists and writers needing quick scaffolding for blog posts or web pages.

Bifrost is an open-source, self-hosted AI gateway that unifies over 20 LLM providers behind a single OpenAI-compatible API. It supports provider failover, weighted load balancing, virtual keys with budgets, semantic caching, and observability. Ideal for applications needing multi-provider access, key management, and traffic governance without modifying existing SDKs.