gws-gmail

Gmail: Send, read, and manage email.

Quality

52%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/gws-gmail/SKILL.md

Quality

Discovery

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 is extremely terse—it identifies the domain (Gmail) and a few high-level actions but lacks specificity in capabilities, omits a 'Use when...' clause entirely, and misses many natural trigger terms users might employ. While 'Gmail' provides some distinctiveness, the description needs significant expansion to be effective for skill selection among many options.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to send, read, search, or organize emails, or mentions Gmail, inbox, or email attachments.'

Expand the list of concrete actions beyond 'manage' to include specific capabilities like 'search emails, label/archive messages, handle attachments, reply, forward'.

Include more natural trigger terms and variations such as 'inbox', 'compose', 'reply', 'forward', 'attachment', 'mail', and 'e-mail'.

Dimension	Reasoning	Score
Specificity	Names the domain (Gmail/email) and lists some actions (send, read, manage), but 'manage' is vague and doesn't specify concrete actions like searching, labeling, archiving, or deleting.	2 / 3
Completeness	Answers 'what' briefly but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill, which per the rubric caps completeness at 2, and the 'what' is also quite thin, warranting a 1.	1 / 3
Trigger Term Quality	Includes 'Gmail' and 'email' which are natural trigger terms users would say, but misses common variations like 'e-mail', 'inbox', 'compose', 'reply', 'forward', 'attachment', or 'mail'.	2 / 3
Distinctiveness Conflict Risk	'Gmail' is fairly distinctive and points to a specific service, but 'manage email' could overlap with other email-related skills (e.g., Outlook, generic email tools). The mention of Gmail helps but isn't fully disambiguating.	2 / 3
	Total	7 / 12 Passed

Implementation

72%

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

This is a well-structured hub skill that effectively delegates to specialized sub-skills via clear navigation. Its main weakness is the lack of concrete executable examples for direct API usage — the API resources section lists available resources but doesn't show how to actually call them. The discovery workflow could be more explicit with a worked example.

Suggestions

Add 1-2 concrete executable examples of common API calls (e.g., listing recent messages: `gws gmail users.messages list --params 'maxResults=5,q=is:unread'`)

Make the discovery workflow more explicit with a numbered sequence showing how to go from browsing to executing an API call with a real example

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient. No unnecessary explanations of what Gmail is or how email works. Every section serves a clear purpose: helper commands, API resources, and discovery commands.	3 / 3
Actionability	Provides concrete CLI commands for discovery (`gws gmail --help`, `gws schema`) and links to helper command skills, but lacks executable examples of actual API calls (e.g., listing messages, getting a specific message). The API resources section is descriptive rather than instructive.	2 / 3
Workflow Clarity	The discovery workflow (browse → inspect → build params) is present but implicit. There's no explicit sequence for common tasks like 'find and read a message' or validation steps for operations like sending. For a hub/overview skill this is acceptable but could be clearer.	2 / 3
Progressive Disclosure	Excellent progressive disclosure structure. The skill serves as a clear hub with well-signaled one-level-deep references to helper command skills (send, triage, reply, etc.) and a prerequisite link to shared auth/security docs. Navigation is easy via the helper commands table.	3 / 3
	Total	10 / 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: c7c6646

Reviewed: about 7 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.