Microsoft Dataverse agent skills for Claude Code, Cursor and RevampKey

3 ready-made playbooks that teach an AI agent how to do real Microsoft Dataverse work: which tools to call, what to check first, and when to stop and ask you.

Download RevampKey, free I have it: connect Microsoft Dataverse

Connect Microsoft Dataverse once and all 3 skills install themselves and stay up to date. Mac, Windows and Linux.

All 3 Microsoft Dataverse skills

Each skill is one job. You ask in plain words and the agent loads the skill that matches, then follows its steps.

Start hereAsks before writing11 Microsoft Dataverse tools

Work with Microsoft Dataverse data safely

Connects to your Dataverse environment to find tables, read bounded query results and make changes only after you approve each one. It confirms the environment before doing anything.

Use it when

Looking up records in a specific Dataverse table without flooding the conversation
Checking which environment and account an answer came from before acting on it
Making a row or table change with a clear preview and your explicit approval

Tools it uses

search
read_query
list_tables
describe_table
fetch
create_record
update_record
delete_record
create_table
update_table
delete_table

Example

In the Sales production environment, how many open opportunities were created this quarter, and show me the ten largest?

I'm working in the Sales production environment as your signed-in account. The opportunity table has 3,412 rows; 286 are open and created this quarter. Here are the ten largest by estimated revenue, with name, stage and owner. I read all matching pages, so the count is complete.

Use in RevampKeyRead the full skill →

Asks before writing5 Microsoft Dataverse tools

Review a Dataverse table's schema

Checks a Dataverse table's columns, lookups and relationships for naming, duplication and delete risks, then drafts any schema change as a plan. It asks before applying anything.

Use it when

Before adding a required column to a table that already has rows
When a lookup or relationship looks wrong and you want it checked
When a team asks whether a table's structure is ready for a new app

Tools it uses

search
read_query
update_table
create_table
delete_table

Example

Review the Account table in our production environment and tell me if its lookups are set up safely before we add a required column.

The Account table has 14 columns and 3 lookups. Two issues stand out: 'Region' is stored as free text in place of a lookup to the Region table, and the 'Parent Account' lookup has no delete behaviour set, so deleting a parent could orphan children. I have drafted a plan to add a 'Region' lookup and a default for the new required column. Nothing is applied until you approve.

Use in RevampKeyRead the full skill →

Asks before writing10 Microsoft Dataverse tools

Audit a Dataverse table's data quality

Profiles the records in one Microsoft Dataverse table, finds duplicates, blank required fields and orphaned lookups, and reports them read-only. It asks before changing any data.

Use it when

A table has duplicate customers and you need to know how many before cleaning up
You want to find required fields left blank after a data import
Lookups may point at deleted records and you need a count before fixing them

Tools it uses

list_tables
describe_table
read_query
search
update_record
create_record
delete_record
update_table
create_table
delete_table

Example

Audit the Contacts table in our Sales environment for duplicate emails and blank required fields, and don't change anything yet.

Contacts in the Sales environment: 5,200 rows in scope. 214 rows have a blank email, and 38 duplicate email groups cover 91 rows. Nothing has been changed. Merging the duplicates needs your decision on which record survives.

Use in RevampKeyRead the full skill →

Get all 3 without copying a file

RevampKey adds the skills when you connect Microsoft Dataverse, updates them for you and removes them when you disconnect.

Download RevampKey

How Microsoft Dataverse skills work

Connect Microsoft Dataverse
The Microsoft Dataverse MCP server gives the agent its tools.
Ask in plain words
“Review the Account table in our production environment and tell me if its lookups are set up safely before we add a required column.” Each SKILL.md says when it applies, so only the one that fits is loaded.
Approve any change
The agent calls the tools in order, checks its work, and shows you any change before it makes it.

How to install Microsoft Dataverse skills

In RevampKey the skills install themselves when you connect Microsoft Dataverse. In other tools each skill is one folder with a SKILL.md file, and you also need the Microsoft Dataverse MCP server connected there.

About 1 minute · nothing to copy

Download RevampKey for Mac, Windows or Linux and sign in.
Open Connectors and connect Microsoft Dataverse. All 3 skills come with it and stay up to date; they go away when you remove the connector.
Ask in plain language, for example “Review the Account table in our production environment and tell me if its lookups are set up safely before we add a required column.”
Download RevampKeyConnect Microsoft Dataverse · 1 click
Get RevampKey to connect Microsoft Dataverse
RevampKey is a free desktop app for Mac, Windows and Linux. Install it, sign in, and Microsoft Dataverse is one click away with its skills already attached.
Download RevampKey
Not now? Use the skills in your current tool
for s in essentials schema-review table-data-audit; do curl -fsSL --create-dirs -o .claude/skills/dataverse-$s/SKILL.md https://revampkey.com/marketplace/dataverse/skills/$s/SKILL.md done
Other tools

Into this project’s .claude/skills folder

Connect the Microsoft Dataverse MCP server in Claude Code.

Run this in your project folder to add all 3 skills:

for s in essentials schema-review table-data-audit; do
  curl -fsSL --create-dirs -o .claude/skills/dataverse-$s/SKILL.md https://revampkey.com/marketplace/dataverse/skills/$s/SKILL.md
done

Ask in plain language, for example “Review the Account table in our production environment and tell me if its lookups are set up safely before we add a required column.”

Into the shared .agents/skills folder

Connect the Microsoft Dataverse MCP server in Cursor.

Run this in your project folder to add all 3 skills:

for s in essentials schema-review table-data-audit; do
  curl -fsSL --create-dirs -o .agents/skills/dataverse-$s/SKILL.md https://revampkey.com/marketplace/dataverse/skills/$s/SKILL.md
done

Ask in plain language, for example “Review the Account table in our production environment and tell me if its lookups are set up safely before we add a required column.”

Into the shared .agents/skills folder

Connect the Microsoft Dataverse MCP server in Codex.

Run this in your project folder to add all 3 skills:

for s in essentials schema-review table-data-audit; do
  curl -fsSL --create-dirs -o .agents/skills/dataverse-$s/SKILL.md https://revampkey.com/marketplace/dataverse/skills/$s/SKILL.md
done

Ask in plain language, for example “Review the Account table in our production environment and tell me if its lookups are set up safely before we add a required column.”

Into the shared .agents/skills folder

Connect the Microsoft Dataverse MCP server in VS Code.

Run this in your project folder to add all 3 skills:

for s in essentials schema-review table-data-audit; do
  curl -fsSL --create-dirs -o .agents/skills/dataverse-$s/SKILL.md https://revampkey.com/marketplace/dataverse/skills/$s/SKILL.md
done

Ask in plain language, for example “Review the Account table in our production environment and tell me if its lookups are set up safely before we add a required column.”

RevampKey or copy the files?

In RevampKey

One click when you connect Microsoft Dataverse
Updated for you when a skill improves
Removed when you disconnect
The MCP server is set up for you
800+ other connectors, same way

Download free

Copy into your project

One command per project
Run it again to get updates
You connect the Microsoft Dataverse MCP server yourself
Works in Claude Code, Cursor, Codex and VS Code

See the command

Microsoft Dataverse skills FAQ

What is a Microsoft Dataverse agent skill?

A SKILL.md file: a short playbook an AI agent loads when your request matches it. Each Microsoft Dataverse skill describes one job, which Microsoft Dataverse tools to use in which order, what to check first and when to stop and ask you.

Do the Microsoft Dataverse skills change anything on their own?

The others tell the agent to show you the change and wait for a yes before it creates, edits or deletes anything in Microsoft Dataverse.

Which tools can use these skills?

Any agent that reads the open Agent Skills format: Claude Code, Cursor, Codex, VS Code with Copilot and RevampKey. In RevampKey they are attached when you connect Microsoft Dataverse; elsewhere you copy the folders into your project or skills directory.

Do I need the Microsoft Dataverse MCP server too?

Yes. The skills tell the agent how to do the work; the Microsoft Dataverse MCP server gives it the tools to do it. The Microsoft Dataverse MCP setup guide covers every client.

Microsoft Dataverse MCP server setup · This page as Markdown

Put Microsoft Dataverse’s best workflows in your agent

Download RevampKey, connect Microsoft Dataverse and ask your first question in about a minute.

Download RevampKey Connect Microsoft Dataverse · 1 click

All 3 Microsoft Dataverse skills

Work with Microsoft Dataverse data safely

Use it when

Tools it uses

Review a Dataverse table's schema

Use it when

Tools it uses

Audit a Dataverse table's data quality

Use it when

Tools it uses

Get all 3 without copying a file

How Microsoft Dataverse skills work

How to install Microsoft Dataverse skills

RevampKey or copy the files?

In RevampKey

Copy into your project

Microsoft Dataverse skills FAQ

Put Microsoft Dataverse’s best workflows in your agent

Skills for related tools