Google Sheets logo

Google Sheets

Organization
hyperfx-ai
google-sheets

Safe workflow for reading, mapping, and writing Google Sheets without shifting columns or overwriting the wrong ranges. Use when the user wants to read, update, or append spreadsheet data, fix sheet structure, or sync data into Google Sheets.

Overview

Publisherhyperfx-ai
Repositorymarketing-skills
Skill namegoogle-sheets
Stars
107
Forks
21
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by hyperfx-ai on GitHub. Read the source before you install it.

Installation

Install the Google Sheets 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/hyperfx-ai/marketing-skills/tree/main/skills/google-sheets
  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/hyperfx-ai/marketing-skills.git /tmp/marketing-skills
mkdir -p .claude/skills
cp -r /tmp/marketing-skills/skills/google-sheets .claude/skills/google-sheets
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Google Sheets 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 Google Sheets 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 Google Sheets 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.

Google Sheets Writing

Use this skill whenever you need to write structured data into an existing spreadsheet.

Requirements

How to run the tools in this skill

Every tool in this skill is named by its canonical tool name. Run it with the call your surface gives you:

SurfaceFind a toolRun it
Hyper chatCall the tool by its name; search_tools(queries=["<provider> <action>"]) shows its parameters<name>(...)
MCP client (Claude, Cursor, Codex, ChatGPT)search("<what you want to do>"), then describe("<name>")call_read("<name>", {...}), call_write or call_destructive: the one that describe names in call_with
Hyper CLIhyperai search "<what you want to do>", then hyperai describe <name>hyperai call <name> --json '{...}'

If a tool is not found: in Hyper chat, find its toolkit id with discover_toolkits and pass it to enable_toolkit. On an MCP client or the CLI, tell the user which integration to connect in Hyper.

Core Rule

Always:

  1. inspect the workbook and target worksheet
  2. find the real header row
  3. map fields by header name
  4. verify the destination range
  5. write
  6. read back sample rows to confirm alignment

Critical Failure Modes To Avoid

  • Do not assume row 1 is the real header row.
  • Do not assume column A is the first business/data column.
  • Do not treat helper cells like Total, notes, formulas, merged labels, or spacer columns as real headers.
  • Do not overwrite a broad range before checking existing data and layout.
  • Do not claim success until you read back the written cells.

Required Workflow

Step 1: Inspect workbook structure

If the user gave a link, the spreadsheet_id is the part after /d/ in it. If the user gave only a name, call google_sheets_list and take the id whose title matches.

Start with:

  • google_sheets_get: it lists every worksheet with its size

Confirm:

  • worksheet title
  • row/column counts
  • whether there are multiple candidate tabs

Step 2: Read enough context to find the real headers

Read more than one row when structure is unknown.

Typical pattern:

  • google_sheets_values_get(..., range="Sheet1!A1:Z5")

Look for:

  • true column labels
  • helper columns before the real table
  • title rows, totals, formulas, blank separators

If the first row contains labels like Total, Notes, or other non-record metadata, do not anchor your write range to that row alone.

Step 3: Build a header map

Map your source fields to actual sheet headers by name, not memory.

Example:

  • source field business_name -> sheet header Business Name
  • source field contact_email -> sheet header Owner (s) Email

If a required header is missing or ambiguous, stop and ask the user instead of guessing.

Step 4: Choose the safest write strategy

Use:

  • google_sheets_values_update for one verified contiguous range
  • google_sheets_values_batch_update for multiple verified ranges

Prefer narrow writes over large blanket writes.

There is no append tool. To add rows, read the key column of the table (for example Sheet1!B:B) with google_sheets_values_get; the first empty row is the row after the last one it returns. Write from that row with google_sheets_values_update, in the mapped columns only. The sheet grows to fit by itself.

Write Rules

  • Only write columns you have positively mapped.
  • Leave unrelated columns untouched.
  • When a sheet contains helper columns before the table, start writing at the true mapped column, not column A.
  • If a field is intentionally blank, write a blank value only to that verified column.
  • Use RAW unless the user explicitly wants formulas or Sheets parsing behavior.

Verification Is Mandatory

Immediately after writing:

  1. read back the exact written range
  2. inspect at least 2-3 sample rows
  3. confirm each field landed under the intended header

If the read-back is misaligned, acknowledge it and correct it before reporting success.

Recommended Tool Pattern

  1. google_sheets_get
  2. google_sheets_values_get on a header-discovery range such as A1:Z5
  3. optional google_sheets_values_batch_get for existing data + destination area
  4. google_sheets_values_update or google_sheets_values_batch_update
  5. google_sheets_values_get on the written range for verification

Example Mindset

Bad:

  • “I saw Business Name near the start, so I will write A2:F51.”

Good:

  • “The first visible row includes Total: 7 in column A, while Business Name is actually in column B, so I will map the write range from B onward and verify it after writing.”

Frequently asked questions

What does the Google Sheets AI skill do?

Safe workflow for reading, mapping, and writing Google Sheets without shifting columns or overwriting the wrong ranges. Use when the user wants to read, update, or append spreadsheet data, fix sheet structure, or sync data into Google Sheets.

Why use Google Sheets on TypingMind?

Because you install it once and use it with any model. Google Sheets 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 Google Sheets in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hyperfx-ai/marketing-skills/tree/main/skills/google-sheets. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Google Sheets?

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 Google Sheets?

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

Is the Google Sheets AI skill free?

Yes. It is published on GitHub by hyperfx-ai under the MIT 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 👇