Google Sheets

Google Sheets

Tools for working with Google Sheets against the Google Sheets API v4 (https://sheets.googleapis.com/v4/), with spreadsheet discovery via the Google Drive API. 26 tools across two complementary surfaces: a record surface — rows as objects keyed by their column headers (the "log this expense", "update the status to Done", "look up last quarter's total" jobs) — and a cell surface — raw A1-addressed values for formulas, precise numeric/text control, and arbitrary ranges. Plus spreadsheet/worksheet structure and presentation (formatting, sorting, validation).

Independent, unofficial connector for Google Sheets. Not affiliated with, endorsed by, or sponsored by Google Sheets. "Google Sheets" is a trademark of its owner, used only to identify the service this connector works with.

When to use this

• Read or find data inside a spreadsheet — look up a row by a column value (lookupRow), find all matching rows (findRows), list a window of rows (listRows), or read a raw range (getValues).
• Write data — append a row or many rows (createRow / createRows), update specific columns of a row without disturbing the others (updateRow / updateRows), or write a raw range / formula (updateValues).
• Clear or delete — clear a row's contents but keep the row (clearRows / clearValues) or remove rows entirely (deleteRows).
• Manage structure — create a spreadsheet (createSpreadsheet), add / list / copy / rename / hide / delete worksheets, add columns.
• Format & validate — number/date/currency formats, text styling, sort a range, copy a range, dropdowns and number/date validation, conditional formatting.

Setup

This is an agentskills.io skill.

If the connector has not been installed as a skill yet, install it first with npx skills add zapier/connectors --skill google-sheets (or your harness's own skill-install mechanism), then continue here. Installing the skill copies these files, not dependencies. Before running the CLI, a local MCP server, or zapier-sdk auth commands, run npm install --omit=dev here once. Importing the published package as a dependency in your own project instead? That npm install already resolves everything — see references/use-as-sdk.md.

Want the actual repo source instead — to browse references/, run this connector's tests, or hack on it? See README.md for a scoped git clone.

The connector runs on Node.js 22.18+. Pick the reference that matches how you're running it, and load it before doing anything else:

Scripts

All scripts use the single google-sheets connection.

Disambiguation & refusals

Disambiguation before a write. Before writing to a row you found by a column value (e.g. update a row located via lookupRow, or act on a spreadsheet found via listSpreadsheets), count the exact case-insensitive matches:

• Exactly one match — act on it. Don't over-ask; a single unambiguous match is the answer.
• Two or more that tie — stop. List the tied rows (or spreadsheets) with a distinguishing field (another column value, the spreadsheet's modified time / URL) and ask which one. Don't pick arbitrarily, and don't write to all of them.

Row numbers are not stable — they shift on insert/delete/sort. To target the same logical record across runs, match on a unique key column with lookupRow, not a remembered row number.

Confirm before destructive or bulk-overwrite operations. deleteWorksheet, deleteRows, clearRows, and clearValues remove data; updateValues can overwrite it. Confirm the exact target with the user first, and never delete / clear / overwrite more than asked.

Unsupported operations — say so and stop; don't fake it with another tool. This catalog deliberately does not:

• Create or manage charts, pivot tables, named ranges, protected ranges, or filters. There is no tool for these; don't approximate them with formatting.
• Find-or-create in one step. Compose it: lookupRow → if not found, createRow.
• Permanently delete a whole spreadsheet. Worksheet deletion (deleteWorksheet) is the only structural delete.

If asked for any of these, tell the user it's unsupported and stop.

Auth

Every shape passes auth as one connection selector, not the secret — a [<resolver>:]<value> string. Every connector accepts zapier:<connection-id> (Zapier-managed auth — routes through Zapier's auth, retries, and governance layer); some also accept one or more direct-token resolvers (naming and count vary per connector) — check this connector's own resolvers rather than assuming. The <resolver>: prefix is optional; a bare value goes to the first resolver that claims it — a UUID-shaped bare value always claims zapier:. Each script declares the connections it needs and the resolvers each accepts. The exact syntax for passing a connection (and how to see this connector's resolver list) differs by shape — see the reference you loaded above.

Checking what's already configured first? Don't dump environment values to do it — env or env | grep <name> prints the value along with the name, leaking a live credential into the transcript if one is set. Check names only (env | cut -d= -f1 | grep -i <name>) or test a known name directly ([ -n "$VAR_NAME" ]).

No connection yet? Pick one — and follow the reference's own flow to obtain it; never just ask the user for a connection id or token as if they already have one memorized:

Output format

Every script returns a { data, meta } envelope:

• data — the script's result (the shape its outputSchema declares; see the reference you loaded above for how to inspect a script's exact schema in your shape).
• meta.outputDataValidation — what validating data did:
  • { skipped: false, droppedPaths: null } — validated, nothing removed.
  • { skipped: false, droppedPaths: [...], instruction } — validated, but those paths were stripped from data: fields the script returned from the API that the outputSchema doesn't declare. If you need them, re-run with output validation skipped.
  • { skipped: true } — validation was bypassed; data is the raw, unchecked script output.

Reading dropped fields / skipOutputDataValidation. To receive the raw, unvalidated result, opt out of output validation (the exact syntax differs by shape — see the reference you loaded above). Input validation is never skipped.

Trimming the result / filterOutputData. To shrink a large result down to the fields you need, pass a jq expression that post-processes data (again, exact syntax per shape). The jq runs against data only, NOT the { data, meta } envelope, so write it rooted at data (run the script's --help — or your shape's equivalent — to see its output schema). The transformed value replaces data, meta is preserved, and the result is NOT re-validated against the output schema.

References

Load the matching reference file before working in that area: