AI Coding Agents
Two steps: give it the skill, which teaches it how UQL code is well written, then let it look up the docs, over MCP or by URL.
1. Point it at the skill
Section titled “1. Point it at the skill”uql-orm ships an agent skill: how a query is shaped, how entities are declared, the mistakes agents make most, and where each detail lives in these docs. It lives inside the package, so point your agent at it once and every uql-orm upgrade brings the skill for that version with it. Add this line to your project’s AGENTS.md, which Claude Code, Codex, Cursor, GitHub Copilot and most other agents read on their own:
Before writing UQL code, read `node_modules/uql-orm/skills/uql-orm/SKILL.md`: it matches the installed uql-orm.2. Let it look up the docs
Section titled “2. Let it look up the docs”Over MCP
Section titled “Over MCP”The docs MCP server at https://uql-orm.dev/mcp adds search, so the agent finds the right page without knowing its URL: search_docs finds the pages for a topic, get_doc reads one, and read_skill reads the skill. It needs no key.
One click adds it to Cursor or VS Code. In Claude Code:
claude mcp add --transport http uql https://uql-orm.dev/mcpIn Codex:
codex mcp add uql --url https://uql-orm.dev/mcpIn Claude.ai or Claude Desktop, add it as a custom connector (Customize, then Connectors). Any other client takes the same URL in its MCP settings.
Or simply by URL, with nothing to set up
Section titled “Or simply by URL, with nothing to set up”Every page here answers with Markdown when an agent asks for it, as Claude Code and Cursor do on their own. It is also Markdown at its own URL plus .md, such as /querying/relations.md, and the index of them all is /llms.txt. An agent that can fetch URLs needs nothing more than that index:
Before writing UQL code, read https://uql-orm.dev/llms.txt and fetch the pages for the task.To load the whole site in one go instead, /llms-full.txt is every page in one file.