Gmail: Watch for new emails and stream them as NDJSON.
Install with Tessl CLI
npx tessl i github:googleworkspace/cli --skill gws-gmail-watch70
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 93%
↑ 2.06xAgent success when using this skill
Validation for skill structure
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 identifies a clear domain (Gmail) and specific technical capability (streaming emails as NDJSON), but fails to provide explicit trigger guidance for when Claude should use this skill. The technical term 'NDJSON' may not match natural user language, and the description lacks common email-related trigger terms users would actually say.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user wants to monitor Gmail, watch for incoming emails, or needs real-time email streaming'
Include more natural trigger terms users would say: 'inbox', 'new mail', 'email notifications', 'monitor messages'
Clarify the use case for NDJSON output or rephrase in user-friendly terms like 'stream emails in real-time for processing'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Gmail) and two specific actions (watch for new emails, stream as NDJSON), but lacks comprehensive coverage of capabilities beyond these two functions. | 2 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'Gmail' and 'emails' which are natural terms, but 'NDJSON' is technical jargon. Missing common variations like 'inbox', 'mail', 'messages', or 'notifications'. | 2 / 3 |
Distinctiveness Conflict Risk | Gmail is specific enough to distinguish from generic email skills, but could overlap with other Gmail-related skills (reading, sending, searching). The streaming/NDJSON aspect adds some distinction but isn't a natural user trigger. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
87%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-crafted CLI reference skill that is concise, actionable, and properly structured. The flag table and examples provide clear guidance for immediate use. Minor weakness is the lack of explicit validation or troubleshooting guidance for the Pub/Sub setup workflow, which could help users verify their watch is functioning correctly.
Suggestions
Add a brief validation step or expected output example showing what successful watch output looks like (e.g., sample NDJSON line)
Consider adding a troubleshooting note for common Pub/Sub permission issues since this involves cross-service setup
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, presenting only essential information. No unnecessary explanations of what Gmail or Pub/Sub are—assumes Claude's competence with these concepts. | 3 / 3 |
Actionability | Provides concrete, copy-paste ready bash commands with clear flag documentation. The examples cover common use cases and are immediately executable. | 3 / 3 |
Workflow Clarity | This is a single-command tool, but the workflow for setting up Pub/Sub resources vs using existing ones is implicit. No validation steps mentioned for verifying the watch is working or troubleshooting common failures. | 2 / 3 |
Progressive Disclosure | Appropriately structured with clear sections. References to prerequisite shared skill and related skills are well-signaled and one level deep. Content is right-sized for a command reference. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
Table of Contents
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.