dair-ai/dair-academy-plugins

DAIR.AI Academy Plugins

What it solves

This project is a collection of ready-made plugins that extend Claude Code with a variety of AI-powered capabilities: generating and editing images, building course lessons, adaptive tutoring, orchestrating multiple open-weight LLMs, generating HTML survey papers, turning YouTube talks into study notes, building research wikis, and creating AI intelligence feeds from X. Instead of building these tools yourself, you can install them as plugins.

How it works

You add the marketplace to Claude Code with a single command (/plugin marketplace add dair-ai/dair-academy-plugins), then install any plugin individually (/plugin install <plugin-name>@dair-academy-plugins). Each plugin follows a standard structure: a plugin.json with metadata, a README.md, and one or more skills defined in SKILL.md files. You can also try most of these skills without any local setup inside the DAIR Academy AI Builder.

Who it's for

Anyone using Claude Code who wants quick access to these specific AI tools, and developers who want to contribute their own plugins by following the outlined structure and submitting a pull request.

Highlights

  • image-generator: Generate and edit images using Gemini's Nano Banana Pro model.
  • lesson-generator: Build compact, standalone multi-lesson course artifacts with navigation, objectives, flashcards, quizzes, and source links.
  • learn: Help users learn topics through adaptive tutoring, practice exercises, study plans, and feedback.
  • llm-council: Orchestrate multiple open-weight LLMs via Fireworks AI to deliberate on queries using the LLM Council approach.
  • survey-generator: Generate polished, single-file HTML survey papers on any AI/ML topic, powered by Kimi K2.6 on Fireworks AI.
  • youtube-notetaker: Turn YouTube talks into local study deep-dives with extracted slides, timestamped transcripts, editable notes, and a bundled markdown-backed viewer.
  • wiki-builder: Start, structure, grow, query, and maintain reusable research wikis with per-wiki configurable structure and flavors.
  • x-agent-intelligence: Build readable AI and agent intelligence feeds from the official X MCP server.

Related

  • Project
    Shopify/Shopify-AI-Toolkit

    A plugin for AI coding agents that provides direct access to Shopify documentation, API schema validation, and store management tools to streamline Shopify app and theme development.

  • Project
    coldteadotai/abide

    A rule-enforcement tool for AI coding agents that catches and forces repairs for project-specific rule violations that standard linters cannot detect.

  • Project
    ramziddin/solid-skills

    A collection of professional software engineering skills for AI coding agents to transform junior-level code into senior-quality software using SOLID, TDD, and clean code practices.

  • Project
    agentty-org/agentty

    agentty is a native, single‑binary terminal coding assistant written in C++26. It talks to any LLM (Claude, GPT, Ollama, etc.), retrieves only the relevant parts of your repository via a hybrid BM25 + embedding RAG engine, runs shell/build commands inside OS sandboxes, and offers an optional Smart Mode that routes easy tasks to cheap models and complex planning to a flagship model. The tool starts in under 1 ms, has zero runtime dependencies, works on Linux/macOS/Windows/Android, and can operate in an air‑gapped SSH‑relay mode.