Datarails FinanceOS agent skills for Claude Code, Cursor and RevampKey

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

Download RevampKey, free I have it: connect Datarails FinanceOS

Connect Datarails FinanceOS once and all 5 skills install themselves and stay up to date. Mac, Windows and Linux.

All 5 Datarails FinanceOS skills

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

Start hereRead-only22 Datarails FinanceOS tools

Use Datarails FinanceOS well with AI

Guides an AI assistant to confirm the organization and environment, choose the right read tool, aggregate rather than pulling raw rows, and handle permission and sign-in errors. It reads data only and asks before any change to scope.

Use it when

You have just connected Datarails FinanceOS and want to know what to ask first.
A Datarails query returned nothing or was refused and you need to know why.
You want financial totals from Datarails without the assistant pulling thousands of raw rows.

Tools it uses

get_connector_status
list_data_models
list_aliased_fields
list_business_metrics
get_fields_by_id
start_aggregation_by_alias
start_aggregation_by_id
get_aggregation_result_by_alias
get_aggregation_result_by_id
start_distinct_values_by_alias
start_distinct_values_by_id
get_data_by_alias
get_data_by_id
profile_numeric_fields
profile_categorical_fields
get_currency_rates
list_filebox
get_company_profile_sections
list_company_profile_sections
get_org_users
list_xl_functions
get_workflow_guide

Example

Using Datarails, what was our total marketing spend in EUR for Q2 in the UK entity, and can you confirm which environment that came from?

Organization: Acme Holdings, production environment. I aggregated the Marketing Spend alias for Q2, filtered to the UK entity, and converted from GBP using the Q2 average rate. Total: EUR 1.24 million. Coverage: complete for the filter applied, not checked for accrual adjustments posted after the rate date.

Use in RevampKeyRead the full skill →

Read-only15 Datarails FinanceOS tools

Find the right Datarails data before you analyse it

Maps which models, fields, dimensions and metrics in Datarails FinanceOS can answer a question, and checks them against a total you trust before any analysis. It is read-only and asks before switching environments.

Use it when

You need to know whether Datarails holds a figure before building a report
Two fields look similar and you need to know which one to use
You are starting a variance or reconciliation and need to confirm the source first

Tools it uses

get_connector_status
get_workflow_guide
list_data_models
list_aliased_fields
list_business_metrics
list_company_profile_sections
list_filebox
get_fields_by_id
profile_numeric_fields
profile_categorical_fields
start_distinct_values_by_id
start_distinct_values_by_alias
start_aggregation_by_id
start_aggregation_by_alias
get_org_users

Example

Which model and field should I use for gross margin by region for last quarter, and can you check it against our reported total?

Gross margin by region is covered by the Actuals model: the defined Gross Margin metric and the Region dimension, with 12 distinct region members. Ten match the plan master; two ("EMEA " and "Emea") are near-duplicates and need merging before totals reconcile. The aggregated total for last quarter is within 0.2% of the reported figure, so the source is usable once those two members are resolved.

Use in RevampKeyRead the full skill →

Read-only10 Datarails FinanceOS tools

Check the inputs behind a Datarails FinanceOS figure

Audits the fileboxes and currency rates behind a number before it is quoted, checking rate dates, bases and source file freshness, and flags anything stale or missing. It is read-only and changes no files or rates.

Use it when

Before a board or month-end figure goes out, to confirm its inputs are current
When someone asks which rate or file a number was built from
When a total looks off and you suspect a stale load, a double upload or the wrong rate basis

Tools it uses

list_data_models
list_aliased_fields
get_fields_by_id
list_filebox
list_xl_functions
get_currency_rates
start_distinct_values_by_id
start_distinct_values_by_alias
profile_numeric_fields
profile_categorical_fields

Example

Is the Q2 EUR revenue figure safe to quote? Check the rates and source files behind it.

Q2 revenue is safe to quote with one caveat. Both EUR/USD rates are present for April, May and June, and the rate basis is period average, which matches the income statement. The Q2 sales file was loaded on 9 July, after the source close, and covers 3 of 3 months. One entity's June rate was carried forward from May, so quote the figure with a note on that gap.

Use in RevampKeyRead the full skill →

Read-only13 Datarails FinanceOS tools

Build a month-end metric pack from Datarails FinanceOS

Assembles the recurring management KPI pack from your Datarails data, with consistent definitions, one currency basis and a data-as-of date on every figure. Read-only: it reports and does not publish or change anything in Datarails.

Use it when

Preparing the monthly KPI summary for leadership or the board
Refreshing the same management metrics each close so periods are comparable
Checking that a month-end figure set is complete and currency-consistent before it goes out

Tools it uses

get_connector_status
list_company_profile_sections
list_business_metrics
list_data_models
list_aliased_fields
start_aggregation_by_alias
start_aggregation_by_id
get_aggregation_result_by_alias
get_aggregation_result_by_id
start_distinct_values_by_alias
start_distinct_values_by_id
get_currency_rates
get_company_profile_sections

Example

Build the March month-end metric pack for the UK entity: revenue, gross margin and cash burn, in GBP, against February.

Here is the March pack, provisional as of the 3rd cut-off. Revenue is £4.2m against £3.9m in February (+7.7%). Gross margin is 58.1%, recomputed from summed revenue and cost, against 56.9% last month. Cash burn is £0.6m against £0.5m. The USD-denominated sales were converted at the March month-average rate, and I have used the same rate policy for February. Two metrics had no agreed definition and are excluded: customer acquisition cost and net retention.

Use in RevampKeyRead the full skill →

Read-only9 Datarails FinanceOS tools

Explain variances in Datarails FinanceOS

Works out why actuals differ from budget, forecast or last period, ranks the drivers by size and states what remains unexplained. Read-only, and it asks before switching accounts or environments.

Use it when

Actuals missed budget and you need the drivers ranked by size
Revenue or margin moved against last quarter and you want the cause
A forecast is off and you need to know which cost centre or product is responsible

Tools it uses

list_data_models
list_aliased_fields
start_aggregation_by_alias
start_aggregation_by_id
get_aggregation_result_by_alias
get_aggregation_result_by_id
start_distinct_values_by_alias
get_distinct_values_result_by_alias
get_currency_rates

Example

Why is Q2 opex $1.2M over budget? Break it down by department and show what's still unexplained.

Q2 opex is $1.2M over the approved budget. Three departments explain $1.0M of it: Engineering contractors ($540k), Sales commissions ($320k) and Cloud hosting ($140k). The commission overrun is mostly timing: $210k of Q1 bookings were accrued in Q2. The residual is $200k, which I've flagged as open because no single breakdown accounts for it; a journal listing from the Operations owner would close it.

Use in RevampKeyRead the full skill →

Get all 5 without copying a file

RevampKey adds the skills when you connect Datarails FinanceOS, updates them for you and removes them when you disconnect.

Download RevampKey

How Datarails FinanceOS skills work

Connect Datarails FinanceOS
The Datarails FinanceOS MCP server gives the agent its tools.
Ask in plain words
“Which model and field should I use for gross margin by region for last quarter, and can you check it against our reported total?” 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 Datarails FinanceOS skills

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

About 1 minute · nothing to copy

Download RevampKey for Mac, Windows or Linux and sign in.
Open Connectors and connect Datarails FinanceOS. All 5 skills come with it and stay up to date; they go away when you remove the connector.
Ask in plain language, for example “Which model and field should I use for gross margin by region for last quarter, and can you check it against our reported total?”
Download RevampKeyConnect Datarails FinanceOS · 1 click
Get RevampKey to connect Datarails FinanceOS
RevampKey is a free desktop app for Mac, Windows and Linux. Install it, sign in, and Datarails FinanceOS is one click away with its skills already attached.
Download RevampKey
Not now? Use the skills in your current tool
for s in essentials data-model-discovery filebox-and-currency-check month-end-metric-pack variance-review; do curl -fsSL --create-dirs -o .claude/skills/datarails-financeos-$s/SKILL.md https://revampkey.com/marketplace/datarails-financeos/skills/$s/SKILL.md done
Other tools

Into this project’s .claude/skills folder

Connect the Datarails FinanceOS MCP server in Claude Code.

Run this in your project folder to add all 5 skills:

for s in essentials data-model-discovery filebox-and-currency-check month-end-metric-pack variance-review; do
  curl -fsSL --create-dirs -o .claude/skills/datarails-financeos-$s/SKILL.md https://revampkey.com/marketplace/datarails-financeos/skills/$s/SKILL.md
done

Ask in plain language, for example “Which model and field should I use for gross margin by region for last quarter, and can you check it against our reported total?”

Into the shared .agents/skills folder

Connect the Datarails FinanceOS MCP server in Cursor.

Run this in your project folder to add all 5 skills:

for s in essentials data-model-discovery filebox-and-currency-check month-end-metric-pack variance-review; do
  curl -fsSL --create-dirs -o .agents/skills/datarails-financeos-$s/SKILL.md https://revampkey.com/marketplace/datarails-financeos/skills/$s/SKILL.md
done

Ask in plain language, for example “Which model and field should I use for gross margin by region for last quarter, and can you check it against our reported total?”

Into the shared .agents/skills folder

Connect the Datarails FinanceOS MCP server in Codex.

Run this in your project folder to add all 5 skills:

for s in essentials data-model-discovery filebox-and-currency-check month-end-metric-pack variance-review; do
  curl -fsSL --create-dirs -o .agents/skills/datarails-financeos-$s/SKILL.md https://revampkey.com/marketplace/datarails-financeos/skills/$s/SKILL.md
done

Ask in plain language, for example “Which model and field should I use for gross margin by region for last quarter, and can you check it against our reported total?”

Into the shared .agents/skills folder

Connect the Datarails FinanceOS MCP server in VS Code.

Run this in your project folder to add all 5 skills:

for s in essentials data-model-discovery filebox-and-currency-check month-end-metric-pack variance-review; do
  curl -fsSL --create-dirs -o .agents/skills/datarails-financeos-$s/SKILL.md https://revampkey.com/marketplace/datarails-financeos/skills/$s/SKILL.md
done

Ask in plain language, for example “Which model and field should I use for gross margin by region for last quarter, and can you check it against our reported total?”

RevampKey or copy the files?

In RevampKey

One click when you connect Datarails FinanceOS
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 Datarails FinanceOS MCP server yourself
Works in Claude Code, Cursor, Codex and VS Code

See the command

Datarails FinanceOS skills FAQ

What is a Datarails FinanceOS agent skill?

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

Do the Datarails FinanceOS skills change anything on their own?

5 of the 5 only read. The others tell the agent to show you the change and wait for a yes before it creates, edits or deletes anything in Datarails FinanceOS.

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 Datarails FinanceOS; elsewhere you copy the folders into your project or skills directory.

Do I need the Datarails FinanceOS MCP server too?

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

Datarails FinanceOS MCP server setup · This page as Markdown

Put Datarails FinanceOS’s best workflows in your agent

Download RevampKey, connect Datarails FinanceOS and ask your first question in about a minute.

Download RevampKey Connect Datarails FinanceOS · 1 click

All 5 Datarails FinanceOS skills

Use Datarails FinanceOS well with AI

Use it when

Tools it uses

Find the right Datarails data before you analyse it

Use it when

Tools it uses

Check the inputs behind a Datarails FinanceOS figure

Use it when

Tools it uses

Build a month-end metric pack from Datarails FinanceOS

Use it when

Tools it uses

Explain variances in Datarails FinanceOS

Use it when

Tools it uses

Get all 5 without copying a file

How Datarails FinanceOS skills work

How to install Datarails FinanceOS skills

RevampKey or copy the files?

In RevampKey

Copy into your project

Datarails FinanceOS skills FAQ

Put Datarails FinanceOS’s best workflows in your agent

Skills for related tools