> ## Documentation Index
> Fetch the complete documentation index at: https://docs.oviond.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Skills

> Install Oviond as a reusable skill for AI agents

You can install Oviond as a reusable skill for AI agents that support the `skills`
ecosystem. This gives your agent a versioned workflow guide for operating Oviond
instead of leaving it to infer how the pieces fit together each time.

## Install

```bash theme={null}
npx skills add oviond/skills --skill oviond
```

## What the skill covers

The `oviond` skill helps your agent:

* understand the shape of an account — client → project → page → widget, and where
  a datasource connection sits
* discover a datasource's data views, metrics and dimensions before configuring a
  widget, rather than guessing field ids
* know that data is fetched **server-side after a widget is written**, and that
  `refresh_widgets` / `refresh_project` re-run it — there is no ad-hoc query tool
* connect a datasource by API key, and recognise which datasources need a browser
  sign-in and must be handed back to the app
* build the four widget types that are not vendor datasources — static value,
  goals, uploaded data, calculated metrics — each of which binds differently
* treat a date range as a preset that re-resolves ("Last 30 Days" keeps meaning
  the last 30 days), not a fixed pair of dates
* create automations paused, send a test, and wait for confirmation before
  activating

It also names the behaviours that read as failures but are not: demo data on a
datasource the client has not connected, a widget briefly in `loading` while the
fetch runs, and datasources like Stripe that have no accounts to choose from.

## Why use a skill

Without one, your agent has to work out Oviond's workflows from tool descriptions
alone. A description says what one tool does; it cannot say what order to do
things in. With a skill you give it:

* a stable reference for how the product fits together
* use-case driven guidance instead of tool-by-tool guessing
* explicit caveats for what MCP cannot do and should hand back to the app
* a versioned source of truth you can update as Oviond evolves

## Repository

The public source lives here:

* [Oviond Skills on GitHub](https://github.com/oviond/skills)

## Install notes

* After installing, restart your AI tool if it does not pick up the new skill
  immediately
* Pair it with the [MCP connector](/mcp/connect) — the skill explains the
  workflows, the connector executes them
* The skills ecosystem is supported by Claude Code and claude.ai. If you use
  Oviond through another client, the connector still ships the essentials in its
  own instructions

## Documentation index

Agents can discover every page in these docs at
[docs.oviond.com/llms.txt](https://docs.oviond.com/llms.txt).