markusdowne/agentmail
Give AI agents their own email inboxes using the AgentMail API. Use when building email agents, sending/receiving emails programmatically, managing inboxes, handling attachments, organizing with labels, creating drafts for human approval, or setting up real-time notifications via webhooks/websockets. Supports multi-tenant isolation with pods.
100
100%
Does it follow best practices?
Impact
100%
1.20xAverage score across 1 eval scenario
Advisory
Suggest reviewing before use
Quality
Discovery
100%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 is a well-crafted skill description that excels across all dimensions. It clearly identifies the specific API (AgentMail), lists comprehensive concrete capabilities, includes an explicit 'Use when...' clause with natural trigger terms, and carves out a distinct niche for AI agent email infrastructure that won't conflict with general email handling skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'sending/receiving emails programmatically, managing inboxes, handling attachments, organizing with labels, creating drafts for human approval, setting up real-time notifications via webhooks/websockets, multi-tenant isolation with pods.' | 3 / 3 |
Completeness | Clearly answers both what ('Give AI agents their own email inboxes using the AgentMail API') and when ('Use when building email agents, sending/receiving emails programmatically, managing inboxes...') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'email agents', 'sending/receiving emails', 'inboxes', 'attachments', 'labels', 'drafts', 'webhooks', 'websockets'. These are terms developers would naturally use when seeking email automation capabilities. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: specifically targets AI agent email infrastructure via AgentMail API, not general email clients or SMTP libraries. The 'AI agents' and 'AgentMail API' framing creates a distinct identity unlikely to conflict with generic email skills. | 3 / 3 |
Total | 12 / 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 skill file that demonstrates best practices across all dimensions. It provides comprehensive, executable code examples in both TypeScript and Python without unnecessary verbosity. The inclusion of validation checkpoints, error handling patterns, batch operation guidance, and trust boundary considerations shows mature workflow design.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, providing code examples without unnecessary explanations of what email is or how SDKs work. Every section delivers actionable information without padding. | 3 / 3 |
Actionability | All code examples are fully executable and copy-paste ready in both TypeScript and Python. Specific method calls, parameters, and return values are clearly demonstrated. | 3 / 3 |
Workflow Clarity | The Multi-Step Workflow Example section includes explicit validation checkpoints with error handling. Batch Operations section demonstrates proper error isolation and retry guidance. Trust Boundary section provides clear safety constraints. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections for each feature. Advanced topics (webhooks, websockets) are appropriately referenced to separate files with one-level-deep navigation. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents