Automate Google Sheets operations (read, write, format, filter, manage spreadsheets) via Rube MCP (Composio). Read/write data, manage tabs, apply formatting, and search rows programmatically.
Install with Tessl CLI
npx tessl i github:Lingjie-chen/MT5 --skill googlesheets-automation67
Quality
52%
Does it follow best practices?
Impact
95%
2.87xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./.trae/skills/googlesheets-automation/SKILL.mdDiscovery
42%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 excels at listing specific capabilities for Google Sheets automation but critically lacks any 'Use when...' guidance to help Claude know when to select this skill. The technical implementation detail (Rube MCP/Composio) adds some distinctiveness but doesn't help with user-facing trigger matching. Adding explicit trigger conditions would significantly improve skill selection accuracy.
Suggestions
Add a 'Use when...' clause with trigger terms like 'Google Sheets', 'gsheets', 'spreadsheet automation', 'Composio', or when users mention reading/writing to Google Sheets specifically.
Include common user phrasings such as 'update my Google Sheet', 'pull data from sheets', or 'format my spreadsheet' to improve trigger term coverage.
Differentiate more clearly from Excel/generic spreadsheet skills by emphasizing Google-specific features or the Composio integration context.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'read, write, format, filter, manage spreadsheets', 'Read/write data, manage tabs, apply formatting, and search rows programmatically'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly describes WHAT the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance for WHEN Claude should select this skill. Per rubric guidelines, missing explicit trigger guidance caps completeness at 2, and this has no 'when' component at all. | 1 / 3 |
Trigger Term Quality | Includes 'Google Sheets', 'spreadsheets', 'tabs', 'formatting', 'rows' which are relevant keywords. However, missing common variations like 'gsheets', '.gsheet', 'cells', 'columns', or phrases users might say like 'update my spreadsheet'. | 2 / 3 |
Distinctiveness Conflict Risk | Specifies 'Google Sheets' and 'Rube MCP (Composio)' which helps distinguish from generic spreadsheet skills. However, could still overlap with Excel skills or other spreadsheet automation tools without clearer trigger boundaries. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides comprehensive coverage of Google Sheets automation with well-structured workflows and clear sequencing. However, it lacks executable code examples (only tool names and parameters), contains some redundancy between inline pitfalls and the dedicated pitfalls section, and could benefit from splitting reference material into separate files.
Suggestions
Add executable code examples showing actual MCP tool invocations with sample data, not just parameter lists
Consolidate pitfalls into a single location to eliminate redundancy between workflow-specific pitfalls and the Known Pitfalls section
Move the Quick Reference table to a separate REFERENCE.md file and link to it from the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy - pitfalls are listed both within workflows and in a separate 'Known Pitfalls' section with overlap. The Quick Reference table duplicates information already covered in workflows. | 2 / 3 |
Actionability | Provides tool names and parameter lists but lacks executable code examples. The guidance is specific about parameters but pseudocode-level - no actual API call examples showing how to invoke these tools with real data. | 2 / 3 |
Workflow Clarity | Workflows are clearly sequenced with numbered steps, labeled as [Prerequisite], [Required], [Optional], or [Alternative]. Includes validation steps like confirming connection status is ACTIVE before proceeding and checking tab existence before operations. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but everything is in one monolithic file. The Quick Reference table and Known Pitfalls could be separate reference files. The external link to Composio docs is good but internal structure could benefit from splitting. | 2 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
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.