CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/googlesheets-automation/SKILL.md

The canonical home for this skill is googlesheets-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

68%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sectioned reference whose main weaknesses are duplicated pitfall content, a filler 'When to Use' section, and missing post-write/delete validation loops for batch and destructive operations. Trimming the duplication and adding explicit verify steps would move two dimensions up a full point.

Suggestions

Consolidate the 'Known Pitfalls' section — it repeats ~6 items already stated in the per-workflow Pitfalls subsections — into a short index of pitfalls unique to cross-cutting concerns, or remove it.

Add explicit validation checkpoints for batch and destructive operations: a read-back after GOOGLESHEETS_BATCH_UPDATE writes, and a bounded re-read plus confirmation before GOOGLESHEETS_DELETE_DIMENSION.

Delete the empty 'When to Use' section ('This skill is applicable to execute the workflow or actions described in the overview.') which adds tokens without information.

DimensionReasoningScore

Conciseness

The body is mostly dense and useful (exact tool slugs, parameters, error strings), but the 'Known Pitfalls' section repeats ~6 items already covered per-workflow (locale-dependent tab names, quoted sheet names, unbounded ranges, 2D arrays, color floats, numeric sheetId, rate limits), and the closing 'When to Use' section ('This skill is applicable to execute the workflow or actions described in the overview.') is pure filler. This matches anchor 3 ('mostly efficient but could be tightened') rather than anchor 4, where over-explanation would be only minor.

3 / 5

Actionability

Fully actionable, copy-paste-ready guidance: exact tool slugs with per-step roles (Prerequisite/Required/Alternative), exact parameter names with formats ('red, green, blue: Background color as 0.0-1.0 floats (NOT 0-255 ints)', 'spreadsheet_id: Alphanumeric ID from the spreadsheet URL (between /d/ and /edit)'), and specific error strings ('Sheet X not found'). Matches anchor 5; the absence of literal code is not penalized for an MCP tool-orchestration skill whose guidance is concrete.

5 / 5

Workflow Clarity

Sequences are clearly labeled with some checkpoints ('Confirm connection status shows ACTIVE before running any workflows', 'use returned updatedRange to verify placement'), but batch write operations (GOOGLESHEETS_BATCH_UPDATE) lack a post-write verification loop and the destructive GOOGLESHEETS_DELETE_DIMENSION appears only in the Quick Reference table and a one-line caution with no validation workflow. Per the judging guidelines, missing validation in batch/destructive workflows caps this dimension at 3 even though sequencing itself is strong.

3 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so all content is appropriately inlined in a well-sectioned body: Prerequisites, Setup, five labeled workflows, Common Patterns, and a Quick Reference table. This matches anchor 4 ('good structure; most content appropriately placed; minor organization gaps') — not 5 because ~190 lines of per-tool parameter reference sit at the edge of what could be split into a separate reference file, though no such file exists.

4 / 5

Total

15

/

20

Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description with a clear niche and good natural trigger terms, undermined only by the complete absence of a 'when to use' clause and some minor redundancy (read/write mentioned twice). Adding an explicit 'Use when...' trigger sentence would raise completeness from the capped 3.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions Google Sheets, spreadsheets, tabs, or wants to read, write, format, or filter sheet data.'

Include a few more natural synonyms users would say — 'cells', 'columns', 'append rows', 'update a sheet' — to lift trigger term coverage to comprehensive.

Remove the redundant second sentence ('Read/write data, manage tabs, apply formatting, and search rows programmatically') which repeats items from the parenthetical list.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete actions — 'read, write, format, filter, manage spreadsheets' plus 'manage tabs, apply formatting, and search rows' — covering the operation surface comprehensively, matching the anchor-5 example. It exceeds anchor 4 ('several specific actions; minor gaps') because no meaningful operation category is missing.

5 / 5

Completeness

The 'what' is clear and detailed, but there is no 'Use when...' clause or any equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 4 because 'when' is entirely absent rather than merely under-specified.

3 / 5

Trigger Term Quality

Good keyword coverage with natural terms users would say: 'Google Sheets', 'spreadsheets', 'tabs', 'format', 'filter', 'search rows'. It falls short of anchor 5's synonym-level comprehensiveness — common user phrasings like 'cells', 'columns', 'append rows', or 'update a sheet' are missing.

4 / 5

Distinctiveness Conflict Risk

'Google Sheets operations ... via Rube MCP (Composio)' carves out a clear niche with distinct triggers and minimal overlap risk — only another Google Sheets skill could conflict. It is not a 4 because the domain qualifier (Google Sheets + specific MCP integration) leaves little ambiguity about when this skill applies.

5 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/googlesheets-automation/SKILL.md

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.