google-sheets-automation

Lightweight Google Sheets integration with standalone OAuth authentication. No MCP server required. Full read/write access.

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/google-sheets-automation/SKILL.md

Quality

Content

64%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill excels at actionability with fully executable, copy-paste ready commands covering all CRUD operations for Google Sheets. However, it suffers from including reference material that Claude already knows (A1 notation, output format examples) and lacks validation/verification steps for write operations. Trimming informational sections and adding read-back verification after writes would significantly improve the skill.

Suggestions

Remove or drastically shorten the A1 Notation Examples, Output Formats, and Value Input Options sections—Claude already knows these concepts and can infer format output from flags.

Add a verification step after write operations, e.g., 'After updating, verify with: python scripts/sheets.py get-range SPREADSHEET_ID "Sheet1!A1:B2"' to prevent silent failures.

Move reference material (token management, A1 notation, output format details) into a separate REFERENCE.md file and link to it from the main skill.

Remove the generic 'When to Use' boilerplate section at the end—it adds no value.

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient with good command examples, but includes some unnecessary sections like the Output Formats examples (Claude can infer these from format flags), the A1 Notation Examples (Claude already knows this), the Value Input Options explanation, and the Token Management section which is informational but not actionable. The final 'When to Use' section is boilerplate filler.	3 / 5
Actionability	Every command is fully executable and copy-paste ready with concrete examples covering all common operations (read, write, append, clear, batch update). The JSON array syntax for write operations is explicitly shown, and both ID and URL input formats are documented.	5 / 5
Workflow Clarity	The skill is organized by operation type (setup, read, write) which provides a logical sequence. However, for write operations—which are destructive/batch—there are no validation or verification steps (e.g., read-back after write, dry-run, or confirmation). Per rubric rules, missing validation for destructive/batch operations caps this at 3.	3 / 5
Progressive Disclosure	The content is structured with clear section headers, but several sections (Output Formats examples, A1 Notation reference, Value Input Options, Token Management) could be split into a reference file to keep the main skill lean. No bundle files are provided, so everything is inlined in a single file that's longer than it needs to be.	3 / 5
	Total	14 / 20 Passed

Description

36%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description identifies the domain (Google Sheets) but relies heavily on implementation details (OAuth, no MCP server) rather than describing concrete user-facing capabilities. It lacks a 'Use when...' clause entirely and provides no specific actions beyond generic 'read/write access', making it difficult for Claude to reliably select this skill in the right contexts.

Suggestions

Add a 'Use when...' clause with natural trigger phrases like 'Use when the user asks to read, edit, or create Google Sheets spreadsheets, or mentions Google Sheets, spreadsheet data, or .gsheet files.'

Replace 'Full read/write access' with specific concrete actions such as 'Read cell data, write values, create new spreadsheets, format cells, manage sheets and tabs.'

Move implementation details like 'standalone OAuth authentication' and 'No MCP server required' out of the description or de-emphasize them, as they don't help with skill selection.

Dimension	Reasoning	Score
Specificity	Names the domain (Google Sheets) but actions are minimal and generic. 'Full read/write access' is vague — it doesn't specify concrete actions like creating spreadsheets, formatting cells, inserting formulas, etc. The mention of 'standalone OAuth authentication' and 'No MCP server required' describe implementation details rather than capabilities.	2 / 5
Completeness	The 'what' is vaguely present ('Google Sheets integration' with 'read/write access') but lacks specifics. There is no 'when' clause at all — no 'Use when...' or equivalent trigger guidance. Per rubric guidelines, missing 'Use when...' caps completeness at 3, and the weak 'what' brings it down to 2.	2 / 5
Trigger Term Quality	'Google Sheets' is a strong natural keyword users would say, but it's missing synonyms and related terms like 'spreadsheet', '.gsheet', 'Google Spreadsheet', 'tabular data', or specific actions like 'pivot table', 'chart'. The terms 'OAuth' and 'MCP server' are technical jargon unlikely to appear in user requests.	3 / 5
Distinctiveness Conflict Risk	'Google Sheets' is somewhat specific and distinguishes it from generic document or spreadsheet skills, but 'read/write access' is so broad it could overlap with any Google Sheets-related skill. The lack of specific action triggers increases conflict risk with other spreadsheet or data manipulation skills.	3 / 5
	Total	10 / 20 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/google-sheets-automation/SKILL.md
Commit: 57c135b

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.