googlesheets-automation
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.
71
58%
Does it follow best practices?
Impact
95%
2.87xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/googlesheets-automation/SKILL.mdQuality
Discovery
67%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 does a good job listing specific capabilities for Google Sheets automation and is clearly distinguishable from other skills. However, it lacks an explicit 'Use when...' clause which caps completeness, and the trigger terms could be broader to capture more natural user language. The technical reference to 'Rube MCP (Composio)' adds distinctiveness but doesn't help with user-facing discoverability.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to read, update, or manage Google Sheets, mentions spreadsheet automation, or needs to interact with Google Sheets programmatically.'
Include more natural user trigger terms such as 'cells', 'columns', 'Google Spreadsheet', 'sheet data', or 'spreadsheet formulas' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: read, write, format, filter, manage spreadsheets, manage tabs, apply formatting, search rows. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific operations, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the capabilities listed. | 2 / 3 |
Trigger Term Quality | Includes good terms like 'Google Sheets', 'spreadsheets', 'read', 'write', 'format', 'filter', but misses common user variations like '.gsheet', 'cells', 'columns', 'rows', 'Google Spreadsheet', or 'Sheets API'. The mention of 'Rube MCP (Composio)' is technical jargon unlikely to be used by end users. | 2 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Google Sheets specifically (not Excel, not generic spreadsheets), and the mention of Rube MCP (Composio) as the integration mechanism further distinguishes it. Unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a competent reference skill for Google Sheets automation via Rube MCP, with good structural organization and useful pitfall documentation. Its main weaknesses are the lack of concrete executable examples (actual tool call payloads), missing validation/verification steps in workflows, and redundancy between per-section pitfalls and the consolidated pitfalls section that inflates token cost.
Suggestions
Add at least one concrete, copy-paste-ready example per core workflow showing an actual MCP tool call with realistic parameters (e.g., a complete GOOGLESHEETS_BATCH_UPDATE call with sample spreadsheet_id, range, and values).
Add explicit validation/verification steps to workflows—especially 'read back after write' for data operations and 'confirm range before executing' for DELETE_DIMENSION.
Consolidate pitfalls into a single section or keep them only per-workflow to eliminate the significant duplication between per-workflow pitfalls and the 'Known Pitfalls' section.
Consider extracting the Quick Reference table and detailed per-workflow parameter lists into a separate REFERENCE.md file to reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-organized but includes some redundancy—pitfalls are listed per-workflow AND again in a consolidated 'Known Pitfalls' section with significant overlap. The quick reference table duplicates information already covered in the workflows. Some trimming would improve token efficiency, though it avoids explaining basic concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides specific tool names, parameter names, and clear descriptions of what each parameter expects (e.g., '0.0-1.0 floats, NOT 0-255 integers'). However, there are no concrete executable examples showing actual MCP tool calls with sample payloads—everything is described rather than demonstrated with copy-paste-ready invocations. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with labeled steps (Prerequisite, Required, Optional, Alternative), which is helpful. However, there are no explicit validation checkpoints or feedback loops—for example, after writing data there's no 'read back to verify' step, and the destructive DELETE_DIMENSION operation lacks a verification workflow. The 'always read before writing' advice is buried in Common Patterns rather than integrated into workflows. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a useful quick reference table, but it's a monolithic ~180-line file with no bundle files to offload detail into. The per-workflow pitfalls, consolidated pitfalls, common patterns, and quick reference table could benefit from being split into separate reference files, especially given the repetition between sections. | 2 / 3 |
Total | 8 / 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 | |
- Repository
- davepoon/buildwithclaude
- Commit
d065ead
- 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.