gmickel

sheets-cli

15
2
# Install this skill:
npx skills add gmickel/sheets-cli

Or install specific skill: npx add-skill https://github.com/gmickel/sheets-cli

# Description

Read, write, and update Google Sheets data via CLI. Use when the user asks to read spreadsheet data, update cells, append rows, or work with Google Sheets. Triggers on mentions of spreadsheets, sheets, Google Sheets, tabular data in the cloud, or specific sheet names like "Projects" or "Tasks".

# SKILL.md


name: sheets-cli
description: Read, write, and update Google Sheets data via CLI. Use when the user asks to read spreadsheet data, update cells, append rows, or work with Google Sheets. Triggers on mentions of spreadsheets, sheets, Google Sheets, tabular data in the cloud, or specific sheet names like "Projects" or "Tasks".


sheets-cli

CLI for Google Sheets primitives. Read tables, append rows, update cells by key or index, batch operations.

Installation: sheets-cli is already installed and available in the user's PATH. Run commands directly—no installation needed.

Quick Reference

# Find spreadsheet by name
sheets-cli sheets find --name "Projects"

# List sheets/tabs
sheets-cli sheets list --spreadsheet <id-or-url>

# Read table data
sheets-cli read table --spreadsheet <id> --sheet "Sheet1" --limit 100

# Update by key column (preferred - rows can shift)
sheets-cli update key --spreadsheet <id> --sheet "Projects" \
  --key-col "Name" --key "Acme" --set '{"Status":"Done"}'

# Append row
sheets-cli append --spreadsheet <id> --sheet "Projects" \
  --values '{"Name":"NewCo","Status":"Active"}'

Workflow Pattern

Always follow read → decide → dry-run → apply:

# 1. Understand current state
sheets-cli read table --sheet "Tasks" --limit 100

# 2. Dry-run first
sheets-cli update key --sheet "Tasks" --key-col "ID" --key "TASK-42" \
  --set '{"Status":"Complete"}' --dry-run

# 3. Apply if dry-run looks correct
sheets-cli update key --sheet "Tasks" --key-col "ID" --key "TASK-42" \
  --set '{"Status":"Complete"}'

Commands

Auth (Setup)

sheets-cli auth login --credentials <oauth-client.json>
sheets-cli auth status
sheets-cli auth logout

Find Spreadsheet by Name

sheets-cli sheets find --name "<query>" [--limit 10]

Searches Google Drive for spreadsheets matching the name. Returns ID, name, URL.

Requires Google Drive API enabled in the project.

List Sheets/Tabs

sheets-cli sheets list --spreadsheet <id>

Sheet Info

sheets-cli sheet info --spreadsheet <id> --sheet "<name>"
sheets-cli sheet info --spreadsheet <id> --gid <gid>

Get sheet metadata by name or GID.

Get Header Row

sheets-cli header --spreadsheet <id> --sheet "<name>" [--header-row N]

Returns column headers. Auto-detects header row if not specified.

Read Table Data

sheets-cli read table --spreadsheet <id> --sheet "<name>" [--limit N] [--raw]

Returns { headers: ["_row", ...], rows: [{_row: N, ...}, ...], headerRow: N }.

Each row includes _row - the absolute sheet row number for use with update row.

Read Raw Range

sheets-cli read range --spreadsheet <id> --range "Sheet1!A1:B10"

Append Row

sheets-cli append --spreadsheet <id> --sheet "<name>" \
  --values '<json>' [--dry-run]

JSON object with column names as keys. Column matching is case-insensitive with normalized whitespace.

Update by Key (Preferred)

sheets-cli update key --spreadsheet <id> --sheet "<name>" \
  --key-col "<column>" --key "<value>" --set '<json>' \
  [--allow-multi] [--dry-run]

Finds rows where key-col equals key, updates columns from --set. Throws if multiple matches unless --allow-multi.

Update by Row Index

sheets-cli update row --spreadsheet <id> --sheet "<name>" \
  --row <n> --set '<json>' [--dry-run]

Updates specific row by 1-indexed row number. Use _row from read table output directly.

Row Numbering

  • read table returns headerRow and rows with _row field
  • _row is the absolute sheet row number - use directly with update row --row
  • Example: headerRow: 2 means headers on row 2, first data row is _row: 3
  • Never calculate row numbers manually - always use _row from read output

Set Range

sheets-cli set range --spreadsheet <id> --range "Sheet1!A1:B2" \
  --values '<2d-json-array>' [--dry-run]

Batch Operations

sheets-cli batch --spreadsheet <id> --ops '<json-array>' [--dry-run]

Operations: append, updateRow, updateKey, setRange.

Global Options

Option Description
--spreadsheet <id> Spreadsheet ID or full URL
--dry-run Preview without applying
--header-row <n> Header row (auto-detects if omitted)
--value-input <mode> USER_ENTERED (default) or RAW

Output Format

All commands return JSON:

{
  "ok": true,
  "cmd": "update key",
  "spreadsheetId": "...",
  "sheet": "Projects",
  "result": { "matchedRows": 1, "updatedCells": 2 }
}

Errors:

{
  "ok": false,
  "cmd": "update key",
  "error": { "code": "VALIDATION_ERROR", "message": "..." }
}

Best Practices

  1. Use sheets find to get spreadsheet ID from name
  2. --spreadsheet accepts URLs - paste full Google Sheets URL directly
  3. Prefer key-based updates over row indices - rows shift on insert/delete
  4. Always dry-run before writes
  5. Check ok field in response before proceeding
  6. Batch related operations for atomicity
  7. Column names match case-insensitively with normalized whitespace
  8. Header row auto-detects - skips empty rows to find first data row
  9. Headerless sheets: read table returns columns as A, B, ...; use column letters for --set / --key-col
  10. Empty sheets: append can bootstrap by writing a header row from JSON keys
  11. read table --range accepts A1:Z (auto-prefixed with the sheet)

Exit Codes

Code Meaning
0 Success
10 Validation error
20 Auth error
30 Permission error
40 API/transient error

# README.md

sheets-cli

sheets-cli

Composable Google Sheets primitives for humans and agents

InstallationQuick StartCommandsFor Agents

Bun TypeScript Google Sheets
Claude Code OpenAI Codex


📢 New Project: Check out GNO — local hybrid search for your documents (Markdown, PDF, Word, Excel). Combines BM25 + vector search with MCP integration for AI agents. Great companion to sheets-cli: search your local docs, query your cloud sheets.


Fast, deterministic CLI for Google Sheets. Read tables, append rows, update cells by key or index, batch operations—all with JSON output for programmatic consumption.

# Read a sheet as structured data
sheets-cli read table --sheet "Projects" --limit 10

# Update by key column (no fragile row indices)
sheets-cli update key --sheet "Projects" --key-col "Name" --key "Acme" --set '{"Status":"Done"}'


🆕 Agent Skills — Install as a skill for Claude Code, OpenAI Codex, or VS Code (Insiders preview; enable chat.useAgentSkills). The agent automatically discovers sheets-cli when you mention spreadsheets. See For Agents.


Installation

Prerequisites: Bun runtime

git clone https://github.com/gmickel/sheets-cli.git
cd sheets-cli
bun install
bun run build

# Binary at ./dist/sheets-cli
Add to PATH
# Symlink
ln -s "$(pwd)/dist/sheets-cli" /usr/local/bin/sheets-cli

# Or add to shell config
echo 'export PATH="$PATH:/path/to/sheets-cli/dist"' >> ~/.zshrc


Quick Start

1. Enable APIs

  1. Go to Google Cloud Console → APIs
  2. Enable Google Sheets API
  3. Enable Google Drive API (required for sheets find command)

2. Create OAuth Credentials

  1. Go to Google Cloud Console → Credentials
  2. Create OAuth 2.0 Client ID → Desktop app
  3. Download the JSON file

Desktop apps auto-allow localhost redirects. CLI captures OAuth code via http://localhost:3847.

3. Authenticate

sheets-cli auth login --credentials ./client_secret.json

Browser opens → authorize → done.

4. Set Default Spreadsheet (optional)

# Set env var to avoid passing --spreadsheet every time
export SHEETS_CLI_DEFAULT_SPREADSHEET_ID="your-spreadsheet-id"

Get the ID from your sheet URL: docs.google.com/spreadsheets/d/<ID>/edit

5. Use

sheets-cli sheets list --spreadsheet <id>
sheets-cli read table --spreadsheet <id> --sheet "Sheet1" --limit 5
sheets-cli append --spreadsheet <id> --sheet "Sheet1" --values '{"Name":"New Item","Status":"Active"}'


Commands

Auth

sheets-cli auth login --credentials <file> [--token-store <path>]
sheets-cli auth status
sheets-cli auth logout

Metadata

sheets-cli sheets list [--spreadsheet <id>]
sheets-cli sheets find --name "<query>" [--limit 10]  # Search by name
sheets-cli sheet info --sheet "<name>" [--spreadsheet <id>]
sheets-cli sheet info --gid <gid> [--spreadsheet <id>]
sheets-cli header --sheet "<name>" [--header-row 1]

Read

sheets-cli read table --sheet "<name>" [--limit 500] [--range "A1:Z500"] [--raw]
sheets-cli read range --range "<sheet>!A1:Z50"

Write

sheets-cli append --sheet "<name>" --values '<json>' [--value-input USER_ENTERED|RAW] [--dry-run]
sheets-cli update row --sheet "<name>" --row 12 --set '<json>' [--dry-run]
sheets-cli update key --sheet "<name>" --key-col "Col" --key "Val" --set '<json>' [--dry-run] [--allow-multi]
sheets-cli set range --range "<sheet>!M2:M2" --values '<json_2d_array>' [--dry-run]
sheets-cli batch --ops '<json>' [--dry-run]
All flags | Flag | Description | Default | |:-----|:------------|:--------| | `--spreadsheet ` | Spreadsheet ID or full URL | env var or required | | `--dry-run` | Preview without applying | `false` | | `--value-input ` | `USER_ENTERED` or `RAW` | `USER_ENTERED` | | `--header-row ` | Header row number | Auto-detect | | `--limit ` | Max rows to return | unlimited | | `--raw` | Return unformatted values | `false` | | `--allow-multi` | Update multiple matching rows | `false` |


JSON Formats

Append/Update values

{"Name": "Acme Corp", "Status": "Active", "Start Date": "2025-01-15"}

Headerless sheets (column letters):

{"A": "Acme Corp", "C": "Active"}

Set range (2D array)

[["Value1", "Value2"], ["Value3", "Value4"]]

Batch operations

[
  {"op": "append", "sheet": "Tasks", "values": {"Name": "New Task"}},
  {"op": "updateRow", "sheet": "Tasks", "row": 5, "set": {"Status": "Done"}},
  {"op": "updateKey", "sheet": "Tasks", "keyCol": "ID", "key": "TASK-123", "set": {"Status": "Active"}},
  {"op": "setRange", "range": "Tasks!A1:B1", "values": [["Col1", "Col2"]]}
]


Output Format

All commands return JSON to stdout:

{
  "ok": true,
  "cmd": "read table",
  "spreadsheetId": "1abc...",
  "sheet": "Projects",
  "result": {
    "headers": ["Name", "Status", "Date"],
    "rows": [{"Name": "Alpha", "Status": "Active", "Date": "2025-01-15"}],
    "headerRow": 1
  }
}

Errors:

{
  "ok": false,
  "cmd": "update key",
  "error": {"code": "VALIDATION_ERROR", "message": "...", "details": {}}
}

Exit Codes

Code Meaning
0 Success
10 Validation error
20 Auth error
30 Permission error
40 API/transient error


For Agents

Install Skill

# Claude Code
sheets-cli install-skill           # Project: ./.claude/skills/sheets-cli/SKILL.md
sheets-cli install-skill --global  # Personal: ~/.claude/skills/sheets-cli/SKILL.md

# OpenAI Codex
sheets-cli install-skill --codex   # ~/.codex/skills/sheets-cli/SKILL.md

Installs an Agent Skill that teaches the agent how to use sheets-cli. After installing, the agent automatically discovers sheets-cli when you mention spreadsheets, Google Sheets, or sheet names.

Codex: Requires skills = true in ~/.codex/config.toml under [features].
VS Code: Agent Skills support is in preview and only available in VS Code Insiders. Enable chat.useAgentSkills to use Agent Skills.

Restart the agent after installing to load the skill.

Workflow Pattern

Follow read → decide → dry-run → apply:

# 1. Understand current state
sheets-cli read table --sheet "Tasks" --limit 100

# 2. Dry-run
sheets-cli update key --sheet "Tasks" --key-col "ID" --key "TASK-42" --set '{"Status":"Complete"}' --dry-run

# 3. Apply
sheets-cli update key --sheet "Tasks" --key-col "ID" --key "TASK-42" --set '{"Status":"Complete"}'

Best Practices

  1. Use sheets find to get spreadsheet ID from name
  2. Prefer key-based updates over row indices—rows shift on insert/delete
  3. Always dry-run before writes
  4. Check ok field before proceeding
  5. Batch related operations for atomicity
  6. Column names match case-insensitively with normalized whitespace
  7. Header row auto-detects—skips empty rows to find first row with data
  8. Headerless sheets: read table returns columns as A, B, ...; use column letters for --set / --key-col
  9. Empty sheets: append can bootstrap by writing a header row from JSON keys
  10. read table --range accepts A1:Z (auto-prefixed with the sheet)
  11. --spreadsheet accepts URLs—paste full Google Sheets URL directly


Development

bun run dev          # Hot-reload
bun run build        # Compile binary
bun run typecheck    # Type check
bun run lint         # Lint
bun run test         # Tests


License

MIT


Built with Bun • Styled for machines and humans alike

# Supported AI Coding Agents

This skill is compatible with the SKILL.md standard and works with all major AI coding agents:

Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.