agent-ready
Agent-ready: build for the agentic web
Agents now choose and act on a user's behalf: booking, buying, integrating, configuring. An agent does not show a list of options for a human to pick from. It picks one product and uses it end to end. A product an agent cannot find, read, operate, or pay is invisible to that decision and fails silently.
This skill is a build-time companion. Bake the plumbing in while you write the code, so the product works the first time an agent arrives instead of being retrofitted later. Each layer has a reference file with the full build patterns. Read the reference for the layer you are working on before writing code.
Division of labor with Ora's live API. This skill holds the durable part: build patterns, templates, and the habit of thinking about agents while you code. Greenfield work needs that before any URL exists to scan. The live part lives in Ora's MCP server and API: the current check catalog, the exact fix for each check, and the score impact on a deployed product. Build with this skill, then scan for what is actually broken. The skill deliberately does not copy the catalog, so it cannot go stale against it.
When to use
Load this skill when the task touches any public-facing or integration surface of a product an agent might use:
- Designing or adding an API (REST or GraphQL), SDK, or CLI
- Building or changing auth (sign-up, API keys, OAuth, token scopes)
- Building an MCP server, or an MCP App that renders UI for a human inside the agent
- Building checkout, billing, subscriptions, or any flow where money changes hands
- Writing or restructuring developer docs, a landing page, or pricing
- Adding
llms.txt, structured data, or a/.well-known/file - Any request to "make this agent-ready" or "expose this to AI agents"