gws-sheets-read
Google Sheets: Read values from a spreadsheet.
72
66%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/gws-sheets-read/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 very terse—it identifies the platform and a single action but lacks a 'Use when...' clause, multiple concrete capabilities, and sufficient trigger terms. It would be difficult for Claude to reliably select this skill over similar spreadsheet-related skills in a large skill library.
Suggestions
Add an explicit 'Use when...' clause with trigger terms like 'read Google Sheet', 'get spreadsheet data', 'fetch cell values', 'Google Sheets API'.
List additional specific capabilities if applicable, such as reading ranges, fetching specific tabs/sheets, or handling different value formats.
Include common user phrasing variations like 'pull data from a Google Sheet', 'access spreadsheet values', or 'gsheet' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Google Sheets) and one action (read values from a spreadsheet), but only describes a single capability rather than listing multiple concrete actions. | 2 / 3 |
Completeness | Answers 'what' (read values from a spreadsheet) but completely lacks any 'when' clause or explicit trigger guidance, which per the rubric caps completeness at 2, and the 'what' is also quite thin—so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes 'Google Sheets' and 'spreadsheet' which are natural terms users would say, but misses common variations like 'gsheet', 'cells', 'ranges', 'fetch data', or '.gsheet' file references. | 2 / 3 |
Distinctiveness Conflict Risk | Specifying 'Google Sheets' and 'read values' provides some distinctiveness from general spreadsheet or Excel skills, but could overlap with other Google Sheets skills that also read data (e.g., analyze, query, export). | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent simple skill that is concise, actionable, and well-structured. It provides exactly what's needed—usage, flags, examples—without any unnecessary explanation, and appropriately delegates shared concerns (auth, global flags) to a referenced file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every token earns its place. No unnecessary explanations of what Google Sheets is or how APIs work. The content is lean and assumes Claude's competence. | 3 / 3 |
Actionability | Provides exact CLI commands with flags, a clear flag table with required/default info, and concrete examples that are copy-paste ready. | 3 / 3 |
Workflow Clarity | This is a simple, single-purpose read-only skill with no multi-step process or destructive operations. The single action is unambiguous with clear usage and flags. | 3 / 3 |
Progressive Disclosure | Clean overview with well-signaled one-level-deep references to shared auth/config (gws-shared) and the parent sheets skill. The prerequisite callout is clear and appropriately structured. | 3 / 3 |
Total | 12 / 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 | |
- Repository
- googleworkspace/cli
- Commit
c7c6646
- Reviewed
Table of Contents
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.