CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gog-cli

Use this skill whenever the user wants to operate Google Workspace from the command line with gog/gogcli, including Gmail, Calendar, Drive, Docs, Sheets, Slides, Forms, Apps Script, Chat, Classroom, Contacts, Tasks, People, Groups, Admin, Keep, auth, configuration, scripting, or agent-safe Google automation. Prefer this skill for Google account/file/mail/calendar work when the user mentions gog, gogcli, Google CLI, Gmail search/send, Calendar events, Drive files, Docs/Sheets/Slides editing, Forms, Apps Script, Workspace admin, or command-line Google automation.

74

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

An excellent command-first skill body: executable examples covering every service, clear guardrails, and a clean one-level-deep reference structure that was verified against the actual bundle. It falls just short of top marks on conciseness (version/date line, editorial aside, slightly redundant reference map) and workflow clarity (no explicit failure-recovery loop for auth or write errors).

Suggestions

Move the "refreshed against upstream gog v0.13.0 (2026-04-20)" version/date line into a dedicated 'Version / deprecated patterns' section (or drop the editorial aside) so time-sensitive information doesn't pad the intro.

Trim the closing Reference map or the per-section inline pointers — keeping one of the two would remove redundancy without losing navigability.

Add a short failure-recovery loop for the auth and scripting workflows, e.g. "If commands fail with an auth error, run `gog auth list --check` and re-authenticate before retrying" to make the feedback loop explicit rather than implicit.

DimensionReasoningScore

Conciseness

The body is lean and command-first with essentially no explanation of concepts Claude already knows, but a few tokens could be trimmed: the time-sensitive "gog v0.13.0 (2026-04-20)" refresh line is not in a deprecated/old-patterns section, the aside "rather inconveniently for anyone fond of stale notes" is editorial, and the closing Reference map partially duplicates each section's inline "Read references/..." pointer.

4 / 5

Actionability

Fully executable, copy-paste-ready commands throughout — install/auth, the global-flag table, per-service workflows, and jq/xargs scripting patterns — with specific examples covering the common cases; placeholders like <fileId> and <threadId> are the appropriate form.

5 / 5

Workflow Clarity

Sequences are clear and checkpoints are mostly present ("Inspect shape first", "--dry-run", "gog auth list --check", "Batch with xargs after checking output", "--fail-empty"), so the destructive/batch cap does not apply; however there is no explicit error-recovery feedback loop (e.g., what to do when auth or a write fails and how to retry).

4 / 5

Progressive Disclosure

The body is a well-scoped overview and all eight referenced files exist as real, substantive, one-level-deep references (authentication.md, gmail.md, calendar.md, drive-docs.md, sedmat.md, other-services.md, configuration.md, command-reference.md), each clearly signaled inline per section and indexed in a closing Reference map for easy navigation.

5 / 5

Total

18

/

20

Passed

Description

96%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 description with explicit what-and-when triggers, comprehensive concrete capability coverage, and good synonym/alias coverage. Its only weakness is that the broad product-level trigger list creates some overlap risk with non-CLI Google skills.

DimensionReasoningScore

Specificity

The description enumerates concrete, specific actions across the full Google Workspace surface — "Gmail search/send, Calendar events, Drive files, Docs/Sheets/Slides editing, Forms, Apps Script, Workspace admin, command-line Google automation" — with no notable coverage gaps, matching the comprehensive anchor.

5 / 5

Completeness

It explicitly answers what ("operate Google Workspace from the command line with gog/gogcli, including Gmail, Calendar, Drive...") and when ("whenever the user wants to..." and "when the user mentions gog, gogcli, Google CLI, Gmail search/send...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

It covers both the natural product terms users would say (Gmail, Calendar, Drive, Sheets, Forms) and tool aliases/synonyms ("gog, gogcli, Google CLI, command-line Google automation"), giving comprehensive trigger coverage.

5 / 5

Distinctiveness Conflict Risk

The niche is mostly distinct, being anchored to gog/gogcli and CLI scope, but the second sentence ("Prefer this skill for Google account/file/mail/calendar work when the user mentions... Gmail search/send, Calendar events") could fire for generic Google/Gmail skills when no CLI intent is expressed — minor overlap risk.

4 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

intellectronica/agent-skills

Path

skills/gog-cli/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.