Read data from a Google Sheet and create a formatted Google Docs report.
61
52%
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/recipe-generate-report-from-sheet/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 identifies a clear pipeline (Google Sheets → Google Docs report) but is too terse. It lacks explicit trigger guidance ('Use when...'), detailed capability listing, and natural keyword variations, making it hard for Claude to reliably select this skill from a large pool.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to generate a report from a Google Sheet, convert spreadsheet data into a document, or create a Google Docs summary from Sheets data.'
Include natural keyword variations such as 'spreadsheet', 'Sheets', 'Docs', 'report generation', 'data summary', and 'formatted document'.
Expand the capability list with specifics, e.g., 'Reads rows and columns from a Google Sheet, applies formatting (headings, tables, charts), and outputs a structured Google Docs report.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Google Sheets, Google Docs) and describes two actions (read data, create report), but lacks detail on what 'formatted' means or what kinds of reports are generated. | 2 / 3 |
Completeness | Describes what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2, and the 'what' itself is also thin—so this lands at 1. | 1 / 3 |
Trigger Term Quality | Includes 'Google Sheet' and 'Google Docs report' which are natural terms, but misses common variations like 'spreadsheet', 'Sheets', 'Docs', 'generate report from data', or file-type references. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of Google Sheets input and Google Docs output is somewhat distinctive, but 'read data' and 'create report' are generic enough to overlap with other reporting or data-processing skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a concise, well-structured recipe skill that clearly sequences the steps for reading sheet data and creating a report. Its main weaknesses are the lack of validation checkpoints between steps and the disconnect between the data read in step 1 and the hardcoded report content in step 3, which makes the data transformation aspect unclear.
Suggestions
Show how to capture the document ID from the create response and use it in subsequent steps (e.g., 'Save the returned documentId for use in the next step').
Add a brief validation step after reading sheet data (e.g., 'Verify the response contains expected columns before proceeding') and after document creation.
Demonstrate how to transform the sheet data from step 1 into the report content in step 3, rather than using entirely hardcoded values.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It assumes Claude knows what Google Sheets and Docs are, provides no unnecessary explanation, and every line serves a purpose. | 3 / 3 |
Actionability | The commands are concrete and copy-paste ready, but the example uses hardcoded placeholder data (DOC_ID, SHEET_ID) without showing how to capture and pass the document ID from step 2 into step 3. The report content is also hardcoded rather than showing how to transform the sheet data into the report text. | 2 / 3 |
Workflow Clarity | The steps are clearly sequenced, but there are no validation checkpoints—no verification that the sheet read returned data, no check that the document was created successfully before writing, and no confirmation that sharing succeeded. For a multi-step workflow involving external API calls, this is a gap. | 2 / 3 |
Progressive Disclosure | For a short recipe-style skill, the structure is appropriate: a prerequisite note pointing to dependent skills, a clear steps section, and no unnecessary nesting. The references to prerequisite skills are one level deep and clearly signaled. | 3 / 3 |
Total | 10 / 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 | |
a3768d0
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.