Skip to main content
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

Install the ones you need. oviond is the general guide; the other two are task-shaped and load when the work matches them.

​
What the skill covers

The oviond skill helps your agent:
  • understand the shape of an account — client → report → 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_report re-run it, and that query_data reads live figures for any period without touching a report
  • 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.

​
The task skills

​
fix-broken-report

For “this report looks wrong”, “it’s showing the wrong numbers”, or “the email never arrived”. Walks the four causes in the order worth checking them: an unlinked datasource (which renders demo numbers by design, and is the usual answer), a failed fetch, stale numbers nothing has refreshed, and a paused automation. It also says what not to do — rebuilding widgets whose configuration was never the problem.

​
write-executive-summary

For the prose beside the numbers. Summarises from get_widget_data, so the words agree with the charts underneath rather than being pulled from a separate query that will eventually disagree. Covers the Markdown a text widget renders, the merge tags that survive an edit, and never summarising a widget that is showing demo data.

​
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:

​
Install notes

  • After installing, restart your AI tool if it does not pick up the new skill immediately
  • Pair it with the MCP connector — 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.