gws-gmail-triage
Gmail: Show unread inbox summary (sender, subject, date).
86
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
67%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 specific about what it does—showing Gmail unread inbox summaries with sender, subject, and date. Its main weakness is the absence of an explicit 'Use when...' clause and missing common trigger term variations like 'email' or 'new messages'. Adding these would make it more robust for skill selection.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user asks to check Gmail, view unread emails, or see new messages.'
Include additional natural trigger terms like 'email', 'new messages', 'check mail', 'Google mail' to improve matching coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists specific concrete actions: showing unread inbox summary with explicit detail about what's included (sender, subject, date). This is precise about what the skill does. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (show unread inbox summary with sender, subject, date), but lacks an explicit 'Use when...' clause or trigger guidance for when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes natural keywords like 'Gmail', 'unread', 'inbox', 'summary' which users would likely say. However, it's missing common variations like 'email', 'messages', 'new mail', 'check mail', or 'Google mail'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche: Gmail unread inbox summaries. The combination of 'Gmail' + 'unread' + 'inbox summary' is highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 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 excellent, concise skill that clearly documents a single-purpose CLI command. It provides concrete examples, appropriate flags documentation, and well-structured references to related skills. The read-only safety note and prerequisite callout are valuable additions without being verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every token earns its place. No unnecessary explanations of what Gmail is or how email works. The content is lean, structured, and assumes Claude's competence. | 3 / 3 |
Actionability | Provides concrete, copy-paste ready CLI commands with clear flag descriptions and multiple usage examples covering different scenarios including piping to jq. | 3 / 3 |
Workflow Clarity | This is a simple, single-purpose read-only skill with a single action (show unread inbox summary). The usage is unambiguous, and the read-only safety note is appropriately included. No multi-step workflow or destructive operations require validation checkpoints. | 3 / 3 |
Progressive Disclosure | Clear overview with well-signaled one-level-deep references to shared auth/config (gws-shared) and the parent gmail skill. Content is appropriately scoped to this specific subcommand without inlining unrelated details. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
90%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
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.