Gmail: Send an email.
72
66%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/gws-gmail-send/SKILL.mdQuality
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 is extremely terse, identifying only one action (sending email) via Gmail without any trigger guidance or comprehensive capability listing. While 'Gmail' provides some distinctiveness, the lack of a 'Use when...' clause and missing action variations significantly weaken its utility for skill selection among many options.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks to send, compose, or draft an email through Gmail.'
Expand the capability list to include related actions such as composing, replying, forwarding, adding attachments, or setting recipients.
Include natural keyword variations like 'compose email', 'mail', 'write an email', 'send a message via Gmail' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Gmail) and one specific action (send an email), but only describes a single capability rather than listing multiple concrete actions like composing, replying, attaching files, etc. | 2 / 3 |
Completeness | States what it does (send an email via Gmail) but has no 'Use when...' clause or explicit trigger guidance, which per the rubric caps completeness at 2, and the 'what' is also minimal, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes 'Gmail' and 'send an email' which are natural terms users would say, but misses common variations like 'compose', 'email message', 'mail', or 'write an email'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Gmail' provides some specificity that distinguishes it from generic email skills, but 'send an email' is broad enough that it could overlap with other email-sending skills (e.g., Outlook, SMTP-based tools). | 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 excellent CLI skill document that is concise, highly actionable, and well-structured. It provides comprehensive flag documentation, diverse executable examples, and appropriate safety guardrails (caution banner, dry-run, draft mode). The progressive disclosure is well-handled with clear references to shared infrastructure and related commands.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place: flags table is reference-dense, examples are varied but not redundant, tips add non-obvious information (RFC 5322, 25MB limit, HTML fragment guidance). No unnecessary explanation of what email is or how MIME works. | 3 / 3 |
Actionability | Fully copy-paste ready CLI commands with clear flag documentation. Seven concrete examples cover common use cases (plain text, CC, HTML, alias, attachments, multiple attachments, draft). The flags table provides all needed details. | 3 / 3 |
Workflow Clarity | This is a single-command skill, so complex multi-step workflows aren't needed. The write-command caution with user confirmation requirement serves as the validation checkpoint. The --dry-run and --draft flags provide safety mechanisms. Clear and unambiguous. | 3 / 3 |
Progressive Disclosure | Clean structure with prerequisite reference to shared auth/flags skill, well-organized sections (Usage → Flags → Examples → Tips → See Also), and one-level-deep references to related skills. Content is appropriately scoped to this single command. | 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 | |
c7c6646
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.