gws-chat

Google Chat: Manage Chat spaces and messages.

Quality

33%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/gws-chat/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 too terse and vague. While it correctly identifies the platform (Google Chat), it fails to enumerate specific capabilities and entirely omits trigger guidance for when Claude should select this skill. The word 'manage' is a catch-all that doesn't convey concrete actions.

Suggestions

Add a 'Use when...' clause with explicit trigger terms, e.g., 'Use when the user asks about Google Chat, sending chat messages, creating or listing Chat spaces, or managing Google Workspace conversations.'

Replace the vague 'Manage' with specific actions like 'Create and list Chat spaces, send and read messages, add members to rooms, search conversations.'

Include natural keyword variations users might say, such as 'Google Workspace chat', 'chat rooms', 'DMs', 'group conversations'.

Dimension	Reasoning	Score
Specificity	Names the domain (Google Chat) and two actions (manage spaces and messages), but 'manage' is vague and doesn't list specific concrete actions like creating spaces, sending messages, listing members, etc.	2 / 3
Completeness	Provides a brief 'what' (manage spaces and messages) but completely lacks a 'when should Claude use it' clause. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1.	1 / 3
Trigger Term Quality	Includes 'Google Chat', 'spaces', and 'messages' which are relevant keywords, but misses common variations like 'chat rooms', 'direct messages', 'DMs', 'send message', or 'Google Workspace chat'.	2 / 3
Distinctiveness Conflict Risk	'Google Chat' is fairly specific and distinguishes it from generic messaging skills, but 'messages' and 'spaces' are generic enough terms that could overlap with Slack or other messaging platform skills.	2 / 3
	Total	7 / 12 Passed

Implementation

35%

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

This skill is essentially an API reference dump with repetitive descriptions copied from Google's documentation, which wastes significant token budget. It lacks concrete usage examples and relies heavily on the user discovering commands themselves. The structure has some good elements (prerequisite reference, helper command table, discovery section) but the bulk of the content is verbose and low-value.

Suggestions

Remove or drastically condense the API resource descriptions to just resource and method names, since Claude can discover details via `gws schema` and `--help` commands.

Add 2-3 concrete, executable examples for common tasks (e.g., listing spaces, creating a space, sending a message) with actual `--params` flags.

For destructive operations like `spaces.delete` (cascading delete), add a validation/confirmation workflow step.

Eliminate the repeated boilerplate about Google Workspace requirements for custom emojis — mention it once at the resource level.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with repetitive boilerplate descriptions for each API method. The customEmojis section repeats nearly identical text about Google Workspace requirements four times. Most method descriptions are copied from API docs and add no value for Claude, who can discover these via the help commands shown at the bottom.	1 / 3
Actionability	The skill provides the basic command pattern and discovery commands (`gws schema`, `--help`), but lacks any concrete executable examples of actual API calls (e.g., creating a space, sending a message with specific params). The 'Discovering Commands' section is useful but insufficient on its own.	2 / 3
Workflow Clarity	There's a clear two-step discovery workflow (browse with --help, then inspect with gws schema), but no end-to-end workflow examples for common tasks. For operations like delete (which is destructive and cascading), there are no validation or confirmation steps mentioned.	2 / 3
Progressive Disclosure	Good reference to the shared skill file as a prerequisite and a link to the helper command (+send), but the main body dumps all API resource descriptions inline rather than keeping a lean overview. The resource listing could be much more compact with details discoverable via the schema command.	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: about 1 month 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.