agentmail
Email infrastructure for AI agents. Create accounts, send/receive emails, manage webhooks, and check karma balance via the AgentMail API.
72
66%
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 ./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 itself to the AgentMail API. However, it lacks an explicit 'Use when...' clause which caps completeness, and could benefit from additional natural trigger terms users might use when needing email infrastructure for agents.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user needs to set up email for AI agents, interact with the AgentMail API, or manage programmatic email sending and receiving.'
Include additional natural trigger terms like 'inbox', 'mail', 'email automation', 'programmatic email', or 'agent email setup' to improve discoverability.
| 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
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid API reference skill with excellent actionability — concrete curl commands and TypeScript examples cover all endpoints. However, it's longer than necessary for a SKILL.md, with redundant information between the Quick Start and API reference table, and the types/SDK sections could be offloaded to separate files. Workflow clarity would benefit from explicit karma-checking steps before operations and error recovery in polling patterns.
Suggestions
Add explicit karma balance checks before account creation and send operations in the common patterns (e.g., check balance, abort if insufficient), and add timeout/failure handling to polling loops.
Move the full API reference table, TypeScript SDK section, and Types section into separate referenced files (e.g., API_REFERENCE.md, SDK.md) to keep SKILL.md as a concise overview.
Remove the generic Limitations section — it's boilerplate that doesn't add AgentMail-specific value and wastes tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly efficient but includes some redundancy — the full API reference table duplicates information already shown in the Quick Start examples, and the Types section could be omitted since Claude can infer these from the code examples. The Limitations section is boilerplate that adds no value. | 2 / 3 |
Actionability | Excellent actionability with fully executable curl commands and TypeScript SDK examples that are copy-paste ready. Every API endpoint is demonstrated with concrete code, including authentication headers, request bodies, and response formats. | 3 / 3 |
Workflow Clarity | The common patterns section shows multi-step workflows (signup + verification polling, send + wait for reply) with clear sequencing, but lacks validation checkpoints — there's no karma balance check before operations, no error handling in the polling loops, and no guidance on what to do when polling times out or when karma is insufficient mid-workflow. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's a long monolithic file (~200 lines) where the full API reference table, TypeScript SDK examples, types, and common patterns could be split into separate referenced files. The Quick Start section works well as an overview, but everything else is inline. | 2 / 3 |
Total | 9 / 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
1a9f5ac
- 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.