gog-sheets

Google Sheets operations through gog.

Quality

63%

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 ./.agents/skills/gog-sheets/SKILL.md

Quality

Content

87%

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

The body is a tight, highly actionable CLI reference: concrete safe-start commands, a complete command inventory, and explicit discovery guidance, with shared rules correctly deferred to the parent skill. Its main gap is the absence of an explicit validation/retry feedback loop for the destructive and batch operations it lists.

Suggestions

Add a short destructive/batch workflow with a feedback loop, e.g. run with --dry-run, inspect the diff/result, fix, then re-run, for commands like batch-update, delete-dimension, and clear.

Provide one end-to-end write example (e.g. get -> update -> re-get to verify) so the safe-start pattern extends from reads to mutations.

Note which commands are destructive vs read-only in the command table or a short legend to reinforce the confirm-before-write checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is lean: it never explains what Google Sheets or gog is, jumps to concrete commands, and every row of the command table carries a useful purpose, so each token earns its place and Claude's competence is assumed.	3 / 3
Actionability	The 'Safe start' block gives copy-paste-ready bash invocations, the command table enumerates every subcommand with purpose, and the closing line directs Claude to exact discovery commands (--help, schema --json), which is fully executable guidance.	3 / 3
Workflow Clarity	There is a clear safe-start sequence and explicit checkpoints (--readonly, --dry-run, confirm-before-write), but no validate->fix->retry feedback loop for the batch/destructive operations the skill exposes (batch-update, delete-dimension, clear), which the rubric caps at 2.	2 / 3
Progressive Disclosure	Content is split into well-organized sections (Safe start, Commands) with a single clearly-signaled one-level-deep reference ("Read ../gog/SKILL.md first for shared auth, output, safety, and live-write rules") and no nested reference chains.	3 / 3
	Total	11 / 12 Passed

Description

40%

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 correctly identifies the Google Sheets niche and tool, but it is too thin: no concrete actions, no trigger guidance, and phrasing that overlaps with sibling gog skills. It conveys what family the skill belongs to but not what specifically it does or when to reach for it.

Suggestions

Replace the abstract "operations" with concrete actions, e.g. 'Read, write, and format Google Sheets cells, tabs, and ranges via gog.'

Add an explicit 'when' clause, e.g. 'Use when working with Google Sheets, spreadsheets, or .xlsx-style tabular data.'

Include natural variations (spreadsheets, sheets, tabs, formulas) and distinct verbs to separate it from sibling gog-docs/gog-slides skills.

Dimension	Reasoning	Score
Specificity	The description names the domain and tool ("Google Sheets", "gog") but the only action word is the abstract "operations", with no concrete actions listed; per the guideline to score only what is explicit, this matches the vague/abstract anchor rather than the score-2 anchor which requires naming some actions.	1 / 3
Completeness	It states a thin 'what' ("Google Sheets operations through gog") but gives no 'when' guidance, and the rubric caps completeness at 2 when an explicit 'Use when...' trigger clause is missing.	2 / 3
Trigger Term Quality	"Google Sheets" is a natural term users would say, but the description omits common variations like spreadsheets, sheets, formulas, cells, or tabs, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	"Google Sheets" is a clear niche, but the generic "operations through gog" phrasing is shared across sibling gog-* skills (docs, slides, drive), creating overlap risk consistent with the 'somewhat specific but could overlap' anchor.	2 / 3
	Total	7 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: openclaw/gogcli
Path: .agents/skills/gog-sheets/SKILL.md
Commit: 1dbd820

Reviewed: about 23 hours 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.