gws-shared

gws CLI: Shared patterns for authentication, global flags, and output formatting.

Quality

48%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/gws-shared/SKILL.md

Quality

Content

64%

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

This is a solid reference skill with good actionability through concrete commands, useful tables, and practical shell tips. Its main weaknesses are the inclusion of unnecessary community etiquette content, lack of explicit validation workflows for destructive operations, and missed opportunities for progressive disclosure to service-specific guides.

Suggestions

Remove or significantly trim the 'Community & Feedback Etiquette' section — this is not actionable skill content and wastes tokens on social norms Claude already understands.

Add an explicit workflow sequence for destructive operations: dry-run → review output → confirm with user → execute → verify result, to strengthen the security rules into an actionable checklist.

Add references to service-specific skill files (e.g., 'For Drive operations see [gws-drive.md], for Sheets see [gws-sheets.md]') to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with good use of tables and code blocks, but the 'Community & Feedback Etiquette' section is unnecessary filler that Claude doesn't need instruction on (encouraging users to star repos, issue etiquette). The shell tips section is valuable but could be slightly tighter.	2 / 3
Actionability	Provides concrete, executable commands for authentication, CLI syntax, and shell workarounds. The flag tables are specific and copy-paste ready, and the shell tips include both wrong and correct examples which is highly actionable.	3 / 3
Workflow Clarity	Security rules mention confirming before write/delete and preferring --dry-run, but there's no explicit validation workflow or feedback loop for destructive operations. The skill describes flags and syntax but doesn't sequence a multi-step process with checkpoints (e.g., dry-run -> confirm -> execute -> verify).	2 / 3
Progressive Disclosure	Content is reasonably organized with clear section headers, but everything is inline in a single file. For a shared reference skill, it would benefit from pointing to service-specific skill files or a separate detailed API reference rather than being a flat document.	2 / 3
	Total	9 / 12 Passed

Description

32%

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 identifies a specific tool (gws CLI) and names three capability areas, but remains at a high level without concrete actions or explicit trigger guidance. It reads more like a section heading than a skill description, lacking both the specificity of actions and the 'when to use' clause needed for effective skill selection.

Suggestions

Add a 'Use when...' clause specifying triggers, e.g., 'Use when the user is working with the gws CLI, asks about gws authentication, configuring global flags, or formatting gws command output.'

List specific concrete actions instead of abstract categories, e.g., 'Configure OAuth and API key authentication for gws commands, set global flags like --project and --region, format command output as JSON, table, or CSV.'

Include natural keyword variations users might say, such as 'gws login', 'gws auth', 'gws output format', '--format flag', 'gws credentials'.

Dimension	Reasoning	Score
Specificity	Names the domain ('gws CLI') and mentions some areas (authentication, global flags, output formatting), but these are categories rather than concrete actions. It doesn't list specific things like 'authenticate with OAuth tokens', 'format output as JSON or table', etc.	2 / 3
Completeness	Describes what at a high level ('shared patterns for authentication, global flags, and output formatting') but completely lacks any 'Use when...' clause or explicit trigger guidance. Per rubric guidelines, missing 'Use when' should cap completeness at 2, and the 'what' is also weak, so this scores 1.	1 / 3
Trigger Term Quality	Includes 'gws CLI', 'authentication', 'global flags', and 'output formatting' which are somewhat relevant but fairly technical. Missing natural user phrases like 'gws command', 'login', 'auth', 'format output', or specific flag names users might ask about.	2 / 3
Distinctiveness Conflict Risk	'gws CLI' is a specific tool which helps with distinctiveness, but 'authentication' and 'output formatting' are very broad concepts that could overlap with other CLI tools or authentication-related skills. The 'shared patterns' framing is ambiguous about scope.	2 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	10 / 11 Passed

Repository: googleworkspace/cli
Commit: a3768d0

Reviewed: 3 months 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.