google-sheets

Analyze and edit connected Google Sheets with range precision. Use when the user wants to create Google Sheets, find a spreadsheet, inspect tabs or ranges, search rows, plan formulas, create or repair charts, clean or restructure tables, write concise summaries, or make explicit cell-range updates.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

71%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 well-structured routing skill that defers detail to real one-level-deep reference files with a clear task-to-reference map and explicit validation checkpoints. Main weakness is conciseness: some sections repeat rules already stated elsewhere and carry meta-commentary that could be trimmed.

Suggestions

Deduplicate the .xlsx-don't-cite rule (stated in both 'Default Routing' rule 2 and 'Final Answer Requirement') and reconcile 'Required Read Order' with the 'Task To Reference Map' to remove overlapping guidance.

Trim meta-commentary in 'Canonical Workflow Bias' to the concrete preferred sequence; drop philosophical lines like 'Do not let accumulated edge-case guardrails turn a straightforward Sheets task into a long blocker-analysis exercise.'

Add one explicit error-recovery feedback loop inline (e.g., what to do when the post-import verification finds broken validation/chips) so workflow_clarity can reach 5.

Dimension	Reasoning	Score
Conciseness	Mostly efficient routing logic with no concept-explanation padding, but includes repetition ('Final Answer Requirement' restates Default Routing rule 2; 'Required Read Order' overlaps the 'Task To Reference Map') and meta-commentary ('Canonical Workflow Bias') that could be tightened, matching the score-3 anchor.	3 / 5
Actionability	Concrete routing decisions, specific reference-file targets, named plugin URIs, and exact knobs like 'upload_mode: native_google_sheets' give mostly executable guidance; the actual command shapes live in references, leaving only minor gaps, matching the score-4 anchor.	4 / 5
Workflow Clarity	A clear sequenced workflow (Canonical Workflow Bias steps 1-6) plus a Connector Load Checklist and explicit checkpoints (verify output spreadsheet ID differs, re-read before writing, verify clean/native/scannable) are present; explicit error-recovery feedback loops are largely delegated to references rather than inlined, matching the score-4 anchor and avoiding the batch/destructive cap at 3 since validation is present.	4 / 5
Progressive Disclosure	The body is a routing overview with a clear 'Task To Reference Map' table and well-signaled, one-level-deep references; all referenced files exist in references/ (verified), content is appropriately split with details in references, matching the score-5 anchor.	5 / 5
	Total	16 / 20 Passed

Description

92%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, third-person description that explicitly covers what the skill does and when to use it with concrete, natural trigger phrases and a distinct Google Sheets niche. The only minor gap is the absence of file-extension/colloquial synonyms like '.gsheet' or 'workbook'.

Suggestions

Add a file-extension or colloquial synonym (e.g., 'workbooks' or '.gsheet' links) to round out trigger-term coverage and push trigger_term_quality to 5.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'create Google Sheets, find a spreadsheet, inspect tabs or ranges, search rows, plan formulas, create or repair charts, clean or restructure tables, write concise summaries, or make explicit cell-range updates' — with comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' ('Analyze and edit connected Google Sheets with range precision') and 'when' ('Use when the user wants to...') with concrete trigger phrases, matching the score-5 anchor; third-person voice is used throughout.	5 / 5
Trigger Term Quality	Strong natural keywords and a synonym pair ('Google Sheets', 'spreadsheet') plus task verbs users say (search rows, charts, formulas), but no file-extension or 'workbook'/'sheets' colloquial variant, leaving a few natural terms missing per the score-4 anchor.	4 / 5
Distinctiveness Conflict Risk	'Google Sheets' is a clear niche with distinct, domain-specific triggers and minimal overlap risk with other skills, matching the score-5 anchor.	5 / 5
	Total	19 / 20 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
relative_links	Relative link issues: 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/google-drive/skills/google-sheets/SKILL.md
Commit: 1dc1958

Reviewed: 5 days 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.