Excel Generator logo

Excel Generator

Organization
sandbaseai
excel-generator

Create, edit, analyze, and verify professional Excel workbooks for general business and operational use. Use when the deliverable is an .xlsx file; use a finance-specific modeling workflow for valuation or regulated financial models.

Overview

Publishersandbaseai
Repositorysandbase-skills
Skill nameexcel-generator
Stars
200
Forks
21
Bundled files
1
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by sandbaseai on GitHub. Read the source before you install it.

Installation

Install the Excel Generator AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/sandbaseai/sandbase-skills/tree/main/marketing/excel-generator
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/sandbaseai/sandbase-skills.git /tmp/sandbase-skills
mkdir -p .claude/skills
cp -r /tmp/sandbase-skills/marketing/excel-generator .claude/skills/excel-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Excel Generator in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Excel Generator on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Excel Generator is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Excel Generator

Create a workbook that is useful immediately on open: accurate, navigable, editable where appropriate, and visually clear. Workbook generation is local and deterministic. SandBase is optional only when the user asks for current external data and no authorized dedicated source is already available.

Read the SandBase API map only when external data retrieval is required.

Define the workbook contract

Infer reasonable defaults from the request, but resolve missing choices that change the result:

  • intended decisions and audience;
  • input data, source, freshness, units, and missing-value meaning;
  • required sheets, calculations, filters, charts, and editable inputs;
  • locale, currency, date system, time zone, and decimal conventions;
  • delivery path, Excel compatibility, print or PDF requirements, and whether macros are allowed.

Never introduce macros, external workbook links, hidden tracking, or network-refresh behavior unless the user explicitly requests them and understands the implications.

Design before styling

Choose a structure that matches the task rather than a fixed template. For a multi-sheet analytical workbook, a useful default is:

  • an Overview sheet with purpose, freshness, headline metrics, and navigation;
  • one or more clean input or source-data sheets;
  • calculation or analysis sheets when formulas should remain inspectable;
  • notes or definitions when methodology needs explanation.

Keep raw/source data distinct from calculated output. Use Excel tables or well-bounded ranges for data users will filter or extend. Freeze headers on long sheets and add navigation when the workbook has several sheets.

Preserve data meaning

  • Keep identifiers as text when leading zeros matter.
  • Use true date, time, Boolean, and numeric cell types rather than formatted strings.
  • Distinguish blank, zero, not applicable, and unavailable values.
  • State units in headers and apply consistent precision within a field.
  • Use formulas when users should be able to change inputs and see results update.
  • Avoid volatile or version-specific formulas unless they provide clear value and the target Excel version supports them.
  • Record source URLs, retrieval dates, time ranges, transformations, and assumptions near the affected data or in a notes sheet.

For finance, valuation, tax, audit, or regulated reporting, preserve the user's domain template and standards. Do not apply decorative styling that obscures model inputs, formula lineage, review controls, or required conventions.

Use restrained visual hierarchy

Use one coherent theme and let formatting communicate structure:

  • descriptive title and subtitle;
  • clear table headers and section boundaries;
  • consistent number formats for both values and formula results;
  • meaningful conditional formatting tied to defined thresholds;
  • charts only when they make a comparison, distribution, composition, or trend easier to see;
  • accessible contrast and readable sizing.

Avoid merged cells inside data tables, rainbow palettes, unexplained icons, 3D charts, clipped labels, and decorative elements that compete with the data. Ensure charts do not overlap tables or each other.

Optional external data through SandBase

Prefer user-provided files, existing authorized connectors, and dedicated APIs the user already has. Do not use SandBase for purely local workbook creation or for data already present in the workspace.

When SandBase is the appropriate source:

  1. Call sandbase_discover with a narrow capability query for the required data.
  2. Call sandbase_inspect for viable candidates and compare coverage, freshness, schema, price, limits, and execution mode.
  3. Explain what source is being queried and how its fields will map into the workbook.
  4. Before any paid call, show the endpoint, important arguments, current price, call count, and total estimate or uncertainty, then obtain confirmation.
  5. Use sandbase_account before an approved multi-call batch and call sandbase_run only with live schema-defined arguments.
  6. Poll asynchronous work with sandbase_run_get using the same run ID; do not resubmit a pending request.
  7. Use sandbase_runs only to recover status or reconcile observed cost.

Treat retrieved values as evidence, not truth. Preserve provider attribution and timestamps, flag estimates, and never silently convert missing data to zero.

Verify the file

After writing the workbook:

  1. reopen it with an independent reader when available;
  2. verify sheet names, dimensions, tables, filters, panes, validations, named ranges, formulas, links, and charts;
  3. scan formulas for broken references and error values;
  4. confirm numeric and date formats on both input and formula cells;
  5. render or preview representative sheets and inspect clipping, overlaps, unreadable text, excess blank space, and print boundaries;
  6. confirm the final file exists at the promised path and opens without a repair warning.

Formula-writing libraries often do not calculate formulas. If no calculation engine is available, say that formula results will calculate when opened in Excel and do not invent cached results.

Return the workbook, a short sheet map, key assumptions, source and freshness notes, validation performed, and any limitations.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Excel Generator AI skill do?

Create, edit, analyze, and verify professional Excel workbooks for general business and operational use. Use when the deliverable is an .xlsx file; use a finance-specific modeling workflow for valuation or regulated financial models.

Why use Excel Generator on TypingMind?

Because you install it once and use it with any model. Excel Generator is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Excel Generator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sandbaseai/sandbase-skills/tree/main/marketing/excel-generator. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Excel Generator?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Excel Generator?

As many as you like. As long as a model supports skills, you can use Excel Generator with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Excel Generator AI skill free?

Yes. It is published on GitHub by sandbaseai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇