agentmail
Email infrastructure for AI agents. Create accounts, send/receive emails, manage webhooks, and check karma balance via the AgentMail API.
55
62%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/antigravity-awesome-skills-claude/skills/agentmail/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.
The description is strong in specificity and distinctiveness, clearly listing concrete actions and anchoring to the AgentMail API. However, it lacks an explicit 'Use when...' clause, which limits its completeness score, and could benefit from additional natural trigger terms users might use when needing this skill.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user needs to send or receive emails programmatically, manage email accounts for AI agents, or interact with the AgentMail API.'
Include additional natural trigger terms like 'inbox', 'mail', 'email automation', 'programmatic email', or 'agent email' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Create accounts, send/receive emails, manage webhooks, and check karma balance via the AgentMail API.' These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific actions, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the capability listing. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'email', 'send/receive emails', 'webhooks', 'AgentMail API', and 'accounts', but misses common user variations like 'inbox', 'mail', 'SMTP', or 'email automation'. The term 'karma balance' is domain-specific and may not be naturally used by most users. | 2 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to the AgentMail API specifically, with distinct concepts like 'AI agents', 'karma balance', and 'AgentMail' that make it unlikely to conflict with generic email or communication skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive and highly actionable API reference skill with excellent executable examples in both curl and TypeScript. However, it suffers from being a monolithic document that would benefit significantly from progressive disclosure — splitting the types, full API reference, common patterns, and SDK examples into separate files. Workflow clarity could be improved with explicit karma-checking validation steps before costly operations.
Suggestions
Split content into multiple files: keep Quick Start and API overview table in SKILL.md, move TypeScript SDK examples to SDK.md, common patterns to PATTERNS.md, and types to TYPES.md with clear references from the main file.
Add an explicit karma validation step before send/create operations, e.g., 'Always check karma balance first; if balance < required, abort and inform user' as a workflow checkpoint.
Add failure/timeout handling to the polling patterns — what should the agent do if no verification email arrives after 60 seconds or no reply after 5 minutes?
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of code examples and tables, but it's quite long (~200+ lines) with some redundancy between the curl examples, SDK examples, and API reference table. The types section and some common patterns could be in separate files. The introductory explanation of what AgentMail is and the 'When to Use' section add modest overhead. | 2 / 3 |
Actionability | Excellent actionability with fully executable curl commands and TypeScript SDK examples that are copy-paste ready. Includes complete code for common patterns like polling for verification emails, webhook signature verification, and error handling with specific error codes. | 3 / 3 |
Workflow Clarity | The common patterns section provides clear multi-step workflows (sign up + verify, send + wait for reply), but there's no explicit validation checkpoint for karma balance before operations despite the document warning about HTTP 402 errors. The polling patterns lack timeout/failure handling guidance. | 2 / 3 |
Progressive Disclosure | All content is in a single monolithic file with no references to external files. The types section, full API reference table, common patterns, and SDK examples could all be split into separate referenced documents. For a skill of this length and complexity, the lack of any content splitting is a significant organizational weakness. | 1 / 3 |
Total | 8 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
a4d3e3a
- 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.