gws-gmail-triage
Gmail: Show unread inbox summary (sender, subject, date).
Install with Tessl CLI
npx tessl i github:googleworkspace/cli --skill gws-gmail-triage76
Quality
66%
Does it follow best practices?
Impact
100%
2.04xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/gws-gmail-triage/SKILL.mdDiscovery
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 concise and clearly identifies the Gmail domain with specific output details (sender, subject, date), which is good. However, it lacks explicit trigger guidance ('Use when...') and misses common user language variations for checking email, significantly limiting Claude's ability to reliably select this skill.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user wants to check Gmail, see new emails, view inbox, or asks about unread messages'
Include natural language variations users might say: 'email', 'messages', 'check mail', 'new mail', 'what's in my inbox'
Consider expanding capabilities if the skill does more than just showing summaries (e.g., 'read emails', 'search messages')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Gmail) and describes a specific action (show unread inbox summary) with concrete details (sender, subject, date), but only describes one action rather than multiple capabilities. | 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', 'unread', 'inbox', and 'summary' which are relevant keywords, but misses common variations like 'email', 'messages', 'check mail', or 'new emails' that users might naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | 'Gmail' provides some distinctiveness from generic email skills, but without explicit triggers it could overlap with other email-related skills or miss being selected when users ask about 'checking email' without mentioning Gmail. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exemplary simple skill. It's maximally concise, provides executable examples, clearly documents flags in a table, and appropriately references related skills without over-explaining. The read-only nature is explicitly stated, removing any need for validation workflows.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. No unnecessary explanations—assumes Claude knows what Gmail, inbox, and triage mean. Every section serves a purpose with no padding. | 3 / 3 |
Actionability | Provides concrete, copy-paste ready commands with clear flag documentation. Examples show real usage patterns including piping to jq. | 3 / 3 |
Workflow Clarity | This is a simple, single-purpose read-only command. The workflow is unambiguous: run the command, get output. Explicitly notes it's read-only (no destructive operations requiring validation). | 3 / 3 |
Progressive Disclosure | Clear structure with prerequisite reference, concise main content, and well-signaled one-level-deep references to related skills (gws-shared, gws-gmail). | 3 / 3 |
Total | 12 / 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 | |
- Reviewed
Table of Contents
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.