gws-gmail-watch

Gmail: Watch for new emails and stream them as NDJSON.

Quality

56%

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-watch/SKILL.md

Quality

Discovery

40%

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 concise and identifies a clear, distinctive niche (Gmail email watching with NDJSON streaming), which helps avoid conflicts with other skills. However, it lacks an explicit 'Use when...' clause, uses technical jargon (NDJSON) that users wouldn't naturally say, and could benefit from more natural trigger terms related to email monitoring.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to monitor a Gmail inbox, watch for incoming emails, or stream email data.'

Include more natural trigger terms users would say, such as 'inbox', 'email notifications', 'monitor emails', 'incoming mail', alongside the technical 'NDJSON' term.

Briefly expand on what 'stream as NDJSON' means in practical terms, e.g., 'outputs each email as a newline-delimited JSON record for processing.'

Dimension	Reasoning	Score
Specificity	Names the domain (Gmail) and two specific actions (watch for new emails, stream as NDJSON), but the scope is narrow and doesn't list multiple concrete capabilities beyond these two.	2 / 3
Completeness	Describes what it does (watch for new emails and stream as NDJSON) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2, and the 'when' is entirely missing, not just implied, bringing it to 1.	1 / 3
Trigger Term Quality	Includes 'Gmail', 'new emails', and 'NDJSON' as keywords. However, it misses common user variations like 'inbox', 'email notifications', 'email monitoring', 'email stream', or 'watch inbox'. 'NDJSON' is fairly technical jargon most users wouldn't naturally say.	2 / 3
Distinctiveness Conflict Risk	The combination of 'Gmail', 'watch for new emails', and 'NDJSON streaming' creates a very specific niche that is unlikely to conflict with other skills. The domain and output format are highly distinctive.	3 / 3
	Total	8 / 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 CLI reference skill that is concise and well-organized with good progressive disclosure to related skills. Its main weaknesses are the lack of expected output examples (what does the NDJSON stream look like?) and missing workflow guidance for the setup path, particularly around when to use --project vs --subscription and how to handle common errors.

Suggestions

Add an example of the expected NDJSON output format so Claude knows what the streamed data looks like and can help users parse it.

Add a brief workflow section clarifying the two paths: fresh setup (--project creates resources) vs. existing setup (--subscription reuses resources), with a note on what to check if things fail.

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient. Every section serves a purpose — flags table, examples, tips — with no unnecessary explanation of what Gmail or Pub/Sub is. Assumes Claude's competence throughout.	3 / 3
Actionability	Provides concrete CLI examples and a clear flags table, but the skill is essentially a reference for a CLI tool rather than providing executable code or step-by-step guidance on what happens under the hood. The examples are copy-paste ready commands, but there's no indication of expected output format (NDJSON structure) or how to handle the streamed data.	2 / 3
Workflow Clarity	The workflow for using the command is implicit rather than explicit. There's no clear sequence for the setup flow (e.g., when you need --project vs --subscription, what happens first). The tips mention watch expiration and cleanup but there's no validation checkpoint or error recovery guidance for common failure modes like auth issues or Pub/Sub permission problems.	2 / 3
Progressive Disclosure	Excellent use of progressive disclosure — references the shared skill for auth/global flags via prerequisite, links to related skills in 'See Also', and keeps this file focused solely on the +watch subcommand. One level deep, clearly signaled.	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: 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.