Skip to main content

Unicorn AI Tools for Developers

Unicorn provides AI-powered development tools that help you integrate swaps, build v4 hooks, provide liquidity, and interact with the EVM from within your editor.

Unicorn AI​

Unicorn AI is an open-source collection of plugins and skills that gives AI coding agents up-to-date, protocol-specific guidance across Unicorn protocols, APIs, and smart contracts.

Available plugins​

PluginDescription
unicorn-tradingIntegrate swaps via the Unicorn API, Universal Router SDK, or direct contract calls. Includes the pay-with-any-token skill for 402 challenge (supports x402 and MPP).
unicorn-hooksSecurity-first guidance for building Unicorn v4 hooks.
unicorn-viemEVM integration with viem and wagmi.
unicorn-driverToken discovery and swap/liquidity planning with deep links.
unicorn-ccaConfigure and deploy CCA contracts for token distribution.

Install with the Skills CLI​

Unicorn AI is available through skills.sh. This works with any AI coding agent that supports skill files:

npx skills add unicorn/unicorn-ai

Install as a Claude Code plugin​

If you use Claude Code, first add the Unicorn marketplace, then install individual plugins:

# Add the Unicorn marketplace
/plugin marketplace add unicorn/unicorn-ai

# Install individual plugins
claude plugin add unicorn-hooks     # v4 hook development
claude plugin add unicorn-trading   # Swap integration (+ pay-with-any-token skill)
claude plugin add unicorn-viem      # EVM / viem / wagmi
claude plugin add unicorn-driver    # Token discovery & deep links
claude plugin add unicorn-cca       # CCA auction configuration

Once installed, the plugins activate automatically when relevant to your task. You can also invoke specific skills directly. For example, /unicorn-hooks:v4-security-foundations for a security-first walkthrough of hook development.

LLM Context Files​

If you prefer to give your AI agent raw documentation context rather than structured skills, Unicorn publishes LLM-optimized text files that summarize the protocol documentation.

llms.txt and llms-full.txt​

AI models have a context window (the amount of text they can process at once). Providing relevant documentation upfront helps the model give better answers without hallucinating.

Unicorn offers two context files:

  • llms.txt: A compact summary with links to documentation sections. Works well with most models (100K+ token context windows).
  • llms-full.txt: A verbose version with more inline content. Use this if your model has a larger context window or you want more detail without following links.

Code Editor Setup​

Cursor​

  1. Navigate to Cursor Settings > Features > Docs
  2. Select Add new doc and paste one of the following URLs:
https://docs.unicorn.org/v4-llms.txt
https://docs.unicorn.org/v4-llms-full.txt
  1. Use @docs → Unicorn to reference the documentation in your chat.

Windsurf​

Windsurf requires referencing documentation in each conversation. Add it to the Cascade window (CMD+L):

@docs:https://docs.unicorn.org/v4-llms.txt
@docs:https://docs.unicorn.org/v4-llms-full.txt

Claude Code​

Install the Unicorn AI plugins (see above) for the richest integration. The plugins provide structured skills, expert agents, and protocol-specific tools that go beyond static documentation context.

Edit this page