Tessl • The package manager for agent skills

SkillPublic

google-workspace

Google Workspace CLI operations: setup diagnostics, security audit, recipe discovery, and output analysis. Usage: /google-workspace <setup|audit|recipe|analyze> [options]

Quality

68%

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 ./.gemini/skills/google-workspace/SKILL.md

Quality

Content

65%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.

The body is highly actionable — every command is executable with concrete worked examples — but it repeats command syntax and long paths redundantly, provides no validation or error-recovery workflow for its batch operations, and its file references point outside the skill bundle (including a confusing self-reference to another SKILL.md) rather than to well-organized bundled files.

Suggestions

Add validation checkpoints to the workflow: run `gws_doctor.py` before audit/recipe execution, interpret `--dry-run` output before a real `--run`, and describe what to do when auth setup fails.

Define the script base path once (e.g., "Scripts live in engineering-team/…/scripts/ — run as `python3 <scripts>/gws_doctor.py`") instead of repeating the full ~85-character path 12+ times, and drop the duplicated syntax between Usage, Examples, and Subcommands.

Replace the arrow-style "Skill Reference -> …/SKILL.md" self-reference with proper bundled structure: move scripts into the skill's own scripts/ directory and use standard markdown links so references are one clean level deep.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — no concept over-explanation — but full command syntax is repeated three times across Usage, Examples, and Subcommands, and the ~85-character script path "engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/…" is repeated verbatim 12+ times instead of being defined once. This is more than the minor trimmable instances of anchor 4, though far from the padded explanations of anchor 2.	3 / 5
Actionability	Every subcommand has fully executable, copy-paste-ready commands with flags (e.g., "python3 …/gws_recipe_runner.py --run <name> --dry-run") and the Examples section covers each common case with concrete values ("--services gmail,drive --json", "--filter \"mimeType=pdf\" --select \"name,size\""). No pseudocode or missing steps.	5 / 5
Workflow Clarity	Each subcommand's steps are individually clear, but there are no validation checkpoints or error-recovery guidance anywhere — no "run setup first, fix auth errors before auditing", no interpretation of --dry-run output before a real recipe run. Audit and recipe run are batch operations; per the judging guidelines, missing validation/verification steps in batch workflows caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Sections (Usage, Examples, Scripts, Subcommands) are well organized and each script gets a one-line description, but navigation is undermined by the arrow-notation self-reference "-> `engineering-team/…/SKILL.md`" which defers to another SKILL.md (a nested, two-level reference pattern), and the scripts live at long external repo paths rather than a bundled scripts/ directory. Structure exists but is not cleanly signaled or organized, matching anchor 3 more than 4.	3 / 5
	Total	14 / 20 Passed

Description

58%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.

The description clearly states what the skill does with four named capabilities, but it is capability-list oriented rather than trigger-oriented: it lacks any "Use when…" guidance and misses the natural domain vocabulary (Gmail, Drive, Calendar, admin) users would say when needing this skill.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks to check Google Workspace setup, run a Workspace security audit, or manage Gmail/Drive/Calendar data via the gws CLI."

Include the natural synonyms and service names users would say — Gmail, Drive, Calendar, Google Workspace admin — alongside "Google Workspace".

Briefly clarify what "recipes" means in this context (43 built-in gws operation templates) so the term is not mistaken for unrelated skills.

Dimension	Reasoning	Score
Specificity	The description lists four concrete actions — "setup diagnostics, security audit, recipe discovery, and output analysis" — covering the skill's scope with minor gaps (e.g., what "recipes" are is never explained). It falls short of anchor 5 because "recipe discovery" and "output analysis" are somewhat abstract, but exceeds anchor 3 by naming several specific actions rather than just 1-2.	4 / 5
Completeness	The "what" is clear ("Google Workspace CLI operations: setup diagnostics, security audit, recipe discovery, and output analysis") but there is no "Use when…" clause or equivalent trigger guidance — the "Usage:" line only shows invocation syntax, not when Claude should reach for the skill. Per the judging guidelines, a missing 'Use when…' clause caps completeness at 3.	3 / 5
Trigger Term Quality	"Google Workspace" and "security audit" are natural, relevant terms, but the description omits the everyday vocabulary users would actually say — Gmail, Drive, Calendar, admin, G Suite — so keyword coverage has clear gaps. Not 4 because coverage beyond the product name is thin; not 2 because "Google Workspace" plus the operation names are more than one or two generic keywords.	3 / 5
Distinctiveness Conflict Risk	"Google Workspace CLI operations" carves out a clear, narrow niche with minimal conflict risk against other skills. Not 5 because the generic sub-terms "setup", "audit", and especially "recipe" could overlap with unrelated skills (e.g., cooking or CI recipes); not 3 because the domain qualifier makes accidental triggering unlikely.	4 / 5
	Total	14 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/google-workspace/SKILL.md
Revision: 27cfcd0

Reviewed: 5 hours ago

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.

google-workspace

Table of Contents

Is this your skill?