Google Sheets: Read and write spreadsheets.
55
45%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/gws-sheets/SKILL.mdQuality
Discovery
32%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 is too terse—it identifies the domain (Google Sheets) and two high-level actions but lacks specific capabilities, natural trigger terms, and an explicit 'Use when...' clause. It would be difficult for Claude to confidently select this skill over similar spreadsheet-related skills given the minimal detail provided.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks to read, edit, or create Google Sheets, mentions gsheets, or references a Google Spreadsheet URL.'
List more specific concrete actions such as 'create formulas, format cells, add/remove sheets, read cell ranges, update values, and manage permissions.'
Include natural keyword variations users might say, such as 'gsheet', 'Google Spreadsheet', 'sheets API', or 'spreadsheet data'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Google Sheets) and two actions (read and write), but does not list more specific concrete actions like creating formulas, formatting cells, creating charts, or managing multiple sheets. | 2 / 3 |
Completeness | Describes what it does (read and write spreadsheets) but has no 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill, which per the rubric caps completeness at 2, and the 'what' is also quite thin, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes 'Google Sheets' and 'spreadsheets' which are relevant keywords, but misses common variations like 'gsheets', '.gsheet', 'Google Spreadsheet', 'cells', 'rows', 'columns', or 'tabular data'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Google Sheets' is fairly specific and distinguishes it from generic spreadsheet or Excel skills, but 'spreadsheets' is broad enough to potentially overlap with Excel or other spreadsheet-related skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill serves as a reasonable hub/overview for Google Sheets API operations, with good progressive disclosure through linked helper skills and a shared auth prerequisite. However, it lacks concrete executable examples of common operations and includes verbose API method descriptions that add little value. The skill would benefit from at least one end-to-end example and trimming the API resource descriptions.
Suggestions
Add 1-2 concrete, copy-paste-ready examples showing common operations (e.g., reading a range of cells or creating a spreadsheet) with actual `--params` flags.
Trim API resource descriptions to just method names and 5-word summaries — Claude can discover details via `gws schema`.
Add an explicit workflow sequence for a common task (e.g., 1. Inspect schema → 2. Build command → 3. Execute → 4. Verify output) to improve workflow clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient, but the long descriptions of API methods (e.g., batchUpdate, get, getByDataFilter) include verbose explanations that Claude already knows or could discover via `gws schema`. These could be trimmed to just method names with brief one-line descriptions. | 2 / 3 |
Actionability | Provides concrete CLI commands for discovery (`gws sheets --help`, `gws schema`) and references helper commands, but lacks executable examples of actual read/write operations. There are no copy-paste-ready examples showing how to actually create, get, or update a spreadsheet with specific flags and params. | 2 / 3 |
Workflow Clarity | The discovery workflow (browse → inspect → build command) is present but implicit. There's no explicit sequenced workflow for common tasks like reading or writing data, and no validation/verification steps for operations that modify spreadsheets. | 2 / 3 |
Progressive Disclosure | Well-structured with clear navigation: references the shared auth skill as a prerequisite, links to helper command skills (+append, +read) with clear descriptions, and keeps the main file as a concise overview with discovery commands. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
90%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 |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 10 / 11 Passed | |
c7c6646
Table of Contents
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.