tableau-dashboard-workflow

tableau-dashboard-workflow is a cursor rule for coding agents from TomerMoskov/tableau-ai-skill. It costs 24 tokens per session (2,992 once invoked), scanned A, original, MIT.

A step-by-step process for creating Tableau dashboard workbooks in the .twb format. Tableau is a tool for exploring data and building interactive charts and dashboards.

In plain words
What is it for?
Use it to gather requirements, define KPIs and formulas, choose worksheets, and validate a Tableau dashboard created programmatically.
Why use it?
It makes the required information and checks explicit before a dashboard is built. This helps prevent incorrect data sources, metric definitions, or visualizations from reaching the final workbook.

Cursor rule

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/tomermoskov/tableau-ai-skill/tableau-dashboard-workflow
Clone the repo
git clone --depth 1 https://github.com/TomerMoskov/tableau-ai-skill

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tableau-dashboard-workflow

README.md
[![agentmods](https://agentmods.dev/badge/rules/tomermoskov/tableau-ai-skill/tableau-dashboard-workflow.svg)](https://agentmods.dev/rules/tomermoskov/tableau-ai-skill/tableau-dashboard-workflow)
Your own site
<a href="https://agentmods.dev/rules/tomermoskov/tableau-ai-skill/tableau-dashboard-workflow"><img src="https://agentmods.dev/badge/rules/tomermoskov/tableau-ai-skill/tableau-dashboard-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,992 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.02992
Opus 5 $0.00012 $0.01496
Sonnet 5 $0.00005 $0.00598
Haiku 4.5 $0.00002 $0.00299

Measured 4d ago against content hash 6d3da820dda4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tableau-dashboard-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

tableau-dashboard-workflow.mdc · 282 lines

How it starts

The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tableau Dashboard Creation Workflow

Use this workflow when the user asks to create a new Tableau dashboard (.twb workbook). Follow the phases in order — do not skip ahead without explicit user approval at each gate.


Phase 1: Examine Requirements

Goal: Gather all inputs needed before design begins.

1a. Identify the Data Source

  • Ask or determine: published data source (sqlproxy) or direct connection (Databricks, Excel, etc.)?
  • If published: get the data source name, server, site, revision from Tableau MCP (list-datasources, get-datasource-metadata) or from context/dashboard_context/.
  • If direct: identify the catalog, schema, and table/model (e.g. your-catalog.marts.order_items_status).
  • Read the relevant domain rule (see AGENTS.md Section 4) and any context files (Section 5) for metric definitions.

1b. Define KPIs and Metrics

  • List each KPI/metric the dashboard must show.
  • Cross-reference context/kpi_glossary.md for official definitions, formulas, and filter rules.
  • For each metric, note: name, formula/aggregation, data type, format (currency, %, integer).

1c. Define Visualizations

For each worksheet planned, capture:

# Worksheet name Chart type Rows (dimensions) Cols (measures/dates) Filters Mark type
1 e.g. "Revenue Trend" Line SUM(Revenue) Month Date range Line

Supported mark types: Bar, Line, Area, Circle, Text, Map, Pie, Gantt, Square, Shape, Polygon, Density, Automatic.

1d. Define Filters

  • Which fields should appear as dashboard filter controls?
  • Filter types: categorical (checkdropdown), date (relative-date), quantitative (range).
  • Default values or "all" selection.

1e. Define Calculated Fields

  • Any calculated fields needed? (e.g. % change, period comparison, LOD expressions)
  • Reference calculated-fields-xml-guide.md and calculated-fields-lod-ban-dashboards.md from the tableau-twb skill.

Read the full file on GitHub · 282 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 282 lines · 24 tokens per session scan A 6d3da820dda4

Subscribe to this mod's changes

tableau-dashboard-workflow is a cursor rule published in the GitHub repository TomerMoskov/tableau-ai-skill (13 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 2,992 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.