uni-sendgrid
SendGrid transactional email via uni CLI. Use when user wants to send emails, including HTML emails and dynamic templates. Requires SENDGRID_API_KEY and verified sender email.
83
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skill/skills/uni-sendgrid/SKILL.mdQuality
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.
This description has good structure with an explicit 'Use when' clause and mentions the specific tool (SendGrid, uni CLI). However, it lacks comprehensive action verbs and could benefit from more natural trigger terms that users would actually say. The requirements note about API key is helpful context but doesn't aid skill selection.
Suggestions
Add more specific concrete actions like 'send transactional emails, use dynamic templates, send HTML-formatted messages, handle email delivery'
Expand trigger terms to include variations users might say: 'email notification', 'mail', 'SendGrid', 'transactional messages', 'email API'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (SendGrid transactional email) and mentions some capabilities (HTML emails, dynamic templates), but doesn't list comprehensive concrete actions like 'send bulk emails, track delivery status, manage templates'. | 2 / 3 |
Completeness | Clearly answers both what (SendGrid transactional email via uni CLI) and when (Use when user wants to send emails, including HTML emails and dynamic templates). Has explicit 'Use when' clause with trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural terms like 'send emails', 'HTML emails', and 'dynamic templates', but missing common variations users might say like 'email notification', 'mail', 'transactional messages', or 'email API'. | 2 / 3 |
Distinctiveness Conflict Risk | Mentions SendGrid specifically which helps distinguish it, but 'send emails' is generic enough that it could conflict with other email-related skills. The 'uni CLI' reference adds some distinctiveness but may not be meaningful to users. | 2 / 3 |
Total | 9 / 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, concise skill that provides immediately actionable CLI commands for SendGrid email operations. The examples cover common use cases effectively. The main gap is the lack of any verification or error handling guidance, which would help Claude confirm successful email delivery or troubleshoot failures.
Suggestions
Add a brief section on verifying email was sent (e.g., checking command exit codes or expected output)
Include common error scenarios and their solutions (e.g., unverified sender, invalid API key)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose with no unnecessary explanation of what SendGrid is or how email works. Commands are shown directly with minimal commentary. | 3 / 3 |
Actionability | All examples are copy-paste ready bash commands covering authentication, plain text, HTML, multiple recipients, CC/BCC, and dynamic templates. Includes the actual URL for API key retrieval. | 3 / 3 |
Workflow Clarity | Authentication and sending are clearly separated, but there's no validation step to verify emails were sent successfully or error handling guidance. For a transactional email skill, knowing how to confirm delivery or handle failures would be valuable. | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose CLI skill under 50 lines, the content is well-organized with clear sections (Authentication, Send Email, Notes). No external references needed for this scope. | 3 / 3 |
Total | 11 / 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 |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- shockz09/uni-cli
- Commit
f1dfc90
- 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.