google-sheets

Automate Google Sheets interactions through browser automation - create spreadsheets, enter data, apply formulas, and format cells.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./apps/desktop/bundled-skills/google-sheets/SKILL.md

Quality

Content

77%

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

The body is highly actionable with a clear, validated workflow and concrete commands throughout. Its main weaknesses are minor redundancy across sections and a fully inline monolithic structure with no progressive disclosure of reference material.

Suggestions

De-duplicate the keyboard shortcuts between the navigation table (§3) and the shortcuts table (§9), keeping one canonical reference and cross-linking.

State the canvas-app / DOM-unreliability caveat once (Overview) and reference it rather than repeating it in §12.

Consider moving the large reference tables (menus §8, shortcuts §9, formulas §5) into a bundled reference file to better separate quick-start guidance from lookup material.

Dimension	Reasoning	Score
Conciseness	Largely token-efficient reference tables and command lists, but it repeats some content across sections (e.g., shortcuts in both navigation and shortcuts tables, the canvas-app caveat stated twice) and could be tightened.	2 / 3
Actionability	Provides fully executable, copy-ready guidance: exact shortcuts (Cmd+Home, Cmd+End), menu paths (Format > Number), numbered entry patterns, and concrete formula examples (=SUM(A1:A10)).	3 / 3
Workflow Clarity	An explicit ordered "Agent Workflow" with a Verify checkpoint plus a dedicated error-recovery feedback loop (Undo → screenshot → re-orient → re-read → retry) gives clear sequencing with validation.	3 / 3
Progressive Disclosure	A single well-organized monolithic file with no bundle files; at ~280 lines the inline reference tables (menus, shortcuts, formulas) could be split out, so structure is good but content that could be separate stays inline.	2 / 3
	Total	10 / 12 Passed

Description

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 is specific and clearly niche-targeted, but it omits any explicit "when to use" trigger guidance and only covers a single natural trigger term. Adding a Use-when clause with broader keyword variations would lift the weaker dimensions.

Suggestions

Append a "Use when..." clause naming natural triggers, e.g. "Use when automating Google Sheets, spreadsheets, or .xlsx files — entering data, applying formulas, or formatting cells."

Broaden trigger term coverage to include common variations users say: "spreadsheets", "sheets", ".xlsx", "formulas", "cell formatting".

Keep the concrete action list but pair it with the explicit when-to-use guidance so both 'what' and 'when' are answered.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("create spreadsheets, enter data, apply formulas, and format cells") rather than vague language, matching the highest anchor.	3 / 3
Completeness	Clearly states what the skill does but provides no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Includes the natural term "Google Sheets" but lacks common variations users might say (spreadsheets, sheets, .xlsx) and has no explicit trigger keyword list, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The product-specific "Google Sheets interactions through browser automation" framing carves a clear niche with distinct triggers, unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: accomplish-ai/coworker
Path: apps/desktop/bundled-skills/google-sheets/SKILL.md
Commit: 2cf74d0

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.