CtrlK
BlogDocsLog inGet started
Tessl Logo

google-sheets

Google Sheets via gws: read/write cells, append rows, structured batch edits.

68

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

87%Weight 40%Scale 1-3

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

A tight, highly actionable reference with executable commands throughout and well-organized navigation, held back only by the absence of an explicit verification step for its destructive and batch operations.

Suggestions

Add an explicit verify step for destructive/batch ops, e.g. after `values.clear` or `spreadsheets.batchUpdate`, re-read the affected range to confirm the result before reporting success.

Tighten the recurring "managed/hosted deployment" caveat so it is stated once in Prerequisites and referenced rather than repeated in Selecting a Google account.

DimensionReasoningScore

Conciseness

The body is lean reference material that assumes Claude's competence — it never explains what a spreadsheet is or how APIs work, and each command example earns its place; not the level below, which would include unnecessary explanation.

3 / 3

Actionability

Every section gives copy-paste-ready, executable `gws sheets ...` commands with real flags and JSON payloads (e.g. `+read`, `values.update`, `spreadsheets.batchUpdate`), fully meeting the executable-and-specific anchor.

3 / 3

Workflow Clarity

The setup onboarding is numbered and there are error-recovery loops (PERMISSION_DENIED, scope-required, atomic-batch "check the reply"), but destructive/batch operations lack an explicit verify-then-proceed checkpoint, which caps this at 2 per the batch-ops guideline.

2 / 3

Progressive Disclosure

No bundle files exist, so this scores the body's own structure: clearly organized sections with explicit deferral pointers ("use google-drive", "run gws schema ...") and easy navigation; not the level below, which would bury should-be-separate content inline without signaling.

3 / 3

Total

11

/

12

Passed

Description

82%Weight 40%Scale 1-3

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 crisp, specific, third-person description that names concrete actions and is clearly distinguishable, but it lacks an explicit use-when trigger clause so it does not fully answer when Claude should reach for it.

Suggestions

Append a trigger clause such as "Use when the user asks to read or update cells, append rows, or run structured edits on a Google Spreadsheet." to explicitly cover the "when" half.

Keep "Google Sheets" as the lead term, but consider dropping or de-emphasizing the tool-internal "via gws" so the opening reads as a user-facing trigger phrase.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "read/write cells, append rows, structured batch edits" — rather than vague language, matching the anchor for naming several specific actions.

3 / 3

Completeness

It clearly states what the skill does but omits any "Use when..." trigger clause, so the "when" half is only implied — capped at 2 per the missing-trigger guideline.

2 / 3

Trigger Term Quality

"Google Sheets", "cells", "append rows", and "batch edits" are terms users naturally say; the technical "via gws" qualifier does not displace these natural keywords.

3 / 3

Distinctiveness Conflict Risk

"Google Sheets via gws" carves a clear niche centered on a specific product and tool, making it unlikely to trigger for the wrong skill.

3 / 3

Total

11

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
Open-Curiosity/gini-agent
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.