tableau-to-sigma

tableau-to-sigma is a skill for Claude Code from twells89/sigma-migration-skills. It costs 77 tokens per session (5,489 once invoked), scanned A, original, MIT.

A migration tool for converting Tableau data sources or workbooks into Sigma data models and matching dashboards. Tableau is a business-intelligence platform; a data source contains connections and field definitions, while a workbook contains visual analyses.

In plain words
What is it for?
Use it to migrate Tableau TDS or workbook files, create Sigma data models and workbooks, and verify data and layout parity.
Why use it?
It translates calculated fields, dashboard elements, filters, and layouts so the Sigma result can be compared with the Tableau source.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ruby scripts/migrate-tableau.rb --workbook "<name>" --connection <id>.

Part of the tableau-to-sigma plugin — 3 skills shipped together

Good fit Use it to migrate Tableau TDS or workbook files, create Sigma data models and workbooks, and verify data and layout parity.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/twells89/sigma-migration-skills
agentmods
npx agentmods add skills/twells89/sigma-migration-skills/tableau-to-sigma

Made for: Claude Code.

Or install tableau-to-sigma, the plugin that ships this one along with the rest of its 3 skills.

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-to-sigma

README.md
[![agentmods](https://agentmods.dev/badge/skills/twells89/sigma-migration-skills/tableau-to-sigma/github.svg)](https://agentmods.dev/skills/twells89/sigma-migration-skills/tableau-to-sigma)
Your own site
<a href="https://agentmods.dev/skills/twells89/sigma-migration-skills/tableau-to-sigma"><img src="https://agentmods.dev/badge/skills/twells89/sigma-migration-skills/tableau-to-sigma/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for tableau-to-sigma

Your own site · 80×15
<a href="https://agentmods.dev/skills/twells89/sigma-migration-skills/tableau-to-sigma"><img src="https://agentmods.dev/badge/skills/twells89/sigma-migration-skills/tableau-to-sigma.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,489 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00077 $0.05489
Opus 5 $0.00039 $0.02745
Sonnet 5 $0.00015 $0.01098
Haiku 4.5 $0.00008 $0.00549

Measured 8d ago against content hash 3f84cf4c1840, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tableau-to-sigma scanned grade A with 1 finding 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (converter/tableau.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> **⛔ NEVER hand-roll a signin `curl` — for Sigma OR Tableau.** The scripts
plugins/tableau-to-sigma/skills/tableau-to-sigma/SKILL.md · 306 lines

How it starts

The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tableau → Sigma Conversion

⛔ STEP 0 — MANDATORY environment bootstrap (before any other step)

On the first run on a machine, run the ONE bootstrap command — idempotent, non-interactive, no admin, never echoes credentials:

  • macOS / Linux / Git Bash: bash scripts/bootstrap.sh --workdir <WORK>
  • Windows PowerShell: powershell -ExecutionPolicy Bypass -File scripts\bootstrap.ps1 -WorkDir <WORK>

It resolves a supported runtime profile from runtime-capabilities.json, installs only that profile's missing dependencies (user-scoped, never admin), persists credentials with the matching setup script, ends in a doctor run (doctor.json), and writes the bootstrap sentinel (bootstrap.json). Both orchestrators REFUSE to start without sentinel + doctor-green. NEVER hand-install a runtime or edit PATH yourself — if bootstrap reports no admin-free route, surface its message to the user and stop. Dry run: --check / -Check. Details: refs/environment.md.

⛔ STEP 1 — THE ONE PATH (a single entry point; do not improvise one)

After the bootstrap, always run the orchestrator — it chains every phase in one process and self-gates:

# Use the entrypoint selected in doctor.json:
ruby scripts/migrate-tableau.rb --workbook "<name>" --connection <id>
# or, when selectedProfile=python:
python3 scripts/migrate-tableau.py --workbook "<name>" --connection <id> …
  • Pass the Tableau /#/views/… share URL straight to --workbook (quote it). The orchestrator resolves the workbook LUID from the URL's contentUrl slug in process. Display names diverge from slugs, so never hand-roll name:eq: filters or page the workbook list — that field-cost a 500-workbook scan. Give it the URL.
  • Flag cheatsheet — use the EXACT flags for the selected entrypoint: migrate-tableau.rb --out DIR (the workdir flag is --out, not --workdir); migrate-tableau.py --out DIR uses the same workdir flag; validate-spec.rb <spec.json> --type dm|workbook (spec is a positional arg, no --spec); put-layout.rb --workbook ID (not --workbook-id), reading SIGMA_API_TOKEN from the env.
  • Do NOT hand-drive the per-phase scripts or hand-author DM/workbook JSON UNLESS an orchestrator STOP explicitly routes you there (e.g. "CONVERTER STOP", the exit-4 handoff). The script map is not a menu — à-la-carte scripts are the #1 way runs go inconsistent.
  • "Done" is not something you decide — it is a file on disk. The migration is complete only when the selected runtime's completion gate (verify-complete.rb or verify-complete.py) exits 0 / prints ✅ DONE. A clean PASS 1 (exit 12) is NOT done — it means "run --finalize". Never report success or write a completion summary before. Completion also requires complete accounting: every formula in formula-audit.json and every object in source-object-census.json has one terminal disposition in MIGRATION_REPORT.md / migration-result.json.
  • This is a PRODUCTION migration, not a demo. The bar is EXACT parity against the same warehouse, always. At a wall: follow the printed STOP/handoff, or surface the blocker plainly and stop — NEVER a third "lighter/simplified" path; only the user may descope. Verbatim rule: refs/operating-contract.md §Never negotiate fidelity down.
  • An orchestrator STOP is an instruction to YOU (the agent), not a handoff to a human — keep going. A routing exit authorizes you to do the next step yourself and re-enter the gated spine; the only finish line is verify-complete.rb exit 0. Verbatim rule: refs/gates.md.
  • At the exit-4 handoff, PATCH the auto-built <WORK>/wb-spec.json — do NOT rewrite it (a from-scratch rewrite drifts controlIds and fails control-lint wholesale — the #1 way this handoff spirals; prefer --master-col for master-level calcs). Full handoff discipline: refs/gates.md §Exit-4.
  • Credentials: the orchestrator stops at step 0 telling you to run the selected runtime's scripts/setup.rb or scripts/setup.py once — do that rather than working around auth (refs/environment.md §Credentials).

Read the full file on GitHub · 306 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago Changed · +18 lines · +3 tokens per session 3f84cf4c1840
  2. 12d ago First seen · 288 lines · 74 tokens per session scan A bf6fa52b0a6c

Subscribe to this mod's changes

tableau-to-sigma is a skill published in the GitHub repository twells89/sigma-migration-skills (16 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 5,489 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens