Read data from two tabs in a Google Sheet to compare and identify differences.
56
46%
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/recipe-compare-sheet-tabs/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 communicates a clear but narrow use case—comparing two tabs in a Google Sheet—without providing explicit trigger guidance or comprehensive action details. It lacks a 'Use when...' clause, which significantly hurts completeness, and the trigger terms could be broader to capture natural user language variations.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to compare two tabs, sheets, or worksheets in a Google Spreadsheet to find mismatches or discrepancies.'
Include more natural trigger terms and variations such as 'spreadsheet', 'worksheet', 'diff', 'discrepancies', 'mismatches', and 'Google Sheets'.
List more specific concrete actions, e.g., 'Reads data from two tabs in a Google Sheet, compares rows or columns, highlights mismatches, and reports added, removed, or changed entries.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Google Sheets) and some actions (read data, compare, identify differences), but doesn't list specific concrete actions like highlighting mismatches, generating diff reports, or specifying what kinds of differences it detects. | 2 / 3 |
Completeness | Describes what it does (read and compare data from two tabs) but has no explicit 'Use when...' clause or trigger guidance, which per the rubric should cap completeness at 2, and the 'what' is also somewhat thin, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes 'Google Sheet' and 'tabs' which are natural terms, but misses common variations like 'spreadsheet', 'worksheet', 'compare columns', 'diff', 'discrepancies', or file extensions like '.gsheet'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'Google Sheet' + 'two tabs' + 'compare differences' is fairly specific, but could overlap with general spreadsheet analysis or data comparison skills. The scope is narrow enough to avoid major conflicts but not explicitly carved out. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
60%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is concise and well-structured but critically incomplete. The first two steps provide actionable commands for reading data, but the third step—the actual comparison which is the entire point of the skill—is left as a vague instruction with no concrete guidance, examples, or expected output format. This makes the skill only partially useful.
Suggestions
Expand step 3 with concrete guidance on how to compare the data: specify an approach (e.g., row-by-row comparison by key column), provide example code or logic, and define what the output should look like (e.g., a list of added/removed/changed rows).
Add an example showing sample input from both tabs and the expected comparison output to make the skill fully actionable.
Consider adding a validation step or note about handling mismatched schemas between tabs (e.g., different column headers or row counts).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. No unnecessary explanations of what Google Sheets are or how comparisons work. Every line serves a purpose. | 3 / 3 |
Actionability | Steps 1 and 2 provide concrete, executable commands with clear syntax, but step 3 ('Compare the data and identify changes') is vague and lacks any concrete guidance on how to actually perform the comparison—no code, no specific approach, no output format. | 2 / 3 |
Workflow Clarity | The three steps are listed but step 3 is essentially undefined, leaving the core task (comparison) without any clear process, validation, or expected output. There's no guidance on what 'differences' look like or how to handle edge cases. | 1 / 3 |
Progressive Disclosure | For a simple skill under 50 lines, the structure is appropriate: a clear prerequisite callout, a brief description, and numbered steps. The reference to the gws-sheets skill is well-signaled and one level deep. | 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.