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 a Gmail unread inbox summary with sender, subject, and date. Its main weakness is the absence of an explicit 'Use when...' clause, which limits completeness and trigger term coverage. Adding trigger guidance and common user phrasings like 'check email' or 'new messages' would strengthen it.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user asks to check Gmail, view unread emails, or see new messages.'
Include common trigger term variations such as 'email', 'messages', 'new mail', 'check mail', 'unread messages' to improve keyword 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 'when should Claude use it' clause. Per the rubric, a missing 'Use when...' clause caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes natural keywords like 'Gmail', 'unread', 'inbox', and 'summary' which users would likely say. However, it's missing common variations like 'email', 'messages', 'new mail', 'check mail', or a 'Use when...' clause with additional trigger terms. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche: Gmail unread inbox summary. The combination of 'Gmail' and 'unread inbox summary' is distinct 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 does exactly what it needs to. It provides clear CLI usage, well-documented flags, practical examples, and appropriate cross-references without any unnecessary verbosity. The read-only safety note and prerequisite callout are well-placed.
| 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 — never modifies your mailbox' note appropriately signals safety. No multi-step workflow or validation is needed. | 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 | |
a3768d0
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.