agentmail

Email infrastructure for AI agents. Create accounts, send/receive emails, manage webhooks, and check karma balance via the AgentMail API.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/agentmail/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable curl and SDK examples, but it over-covers the same endpoints across multiple sections and keeps a large API reference inline without splitting it into separate reference files.

Suggestions

Consolidate endpoint coverage: keep one primary quick-start form (curl or SDK) and move the full reference table and types into a separate REFERENCE.md rather than repeating endpoints three ways inline.

Add an explicit validation/checkpoint step before destructive operations such as account deletion, and define recovery behavior when polling loops find no matching message.

Trim the generic Limitations boilerplate ('Do not treat the output as a substitute for environment-specific validation...') to skill-specific guidance only.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient proprietary API content Claude would not know, but it triple-covers the same endpoints (curl quick-start, TypeScript SDK, and a full API reference table) and includes generic boilerplate in the Limitations section, so it could be tightened rather than earning a lean score 3.	2 / 3
Actionability	It provides fully executable, copy-paste-ready curl commands and TypeScript SDK code with real paths, headers, JSON payloads, and a complete webhook signature-verification function, matching the anchor for specific executable guidance.	3 / 3
Workflow Clarity	Multi-step patterns (signup-then-verify, send-then-await-reply) are sequenced with poll loops, but the destructive account-deletion step lacks a validation checkpoint and the polling loops exit silently on no-result with no error-recovery feedback, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	There are no bundle files and all content sits inline in a ~250-line document; the full API reference, SDK examples, and types could be split into reference files, so while sections are well-organized, content that should be separate is inline rather than in one-level-deep references.	2 / 3
	Total	9 / 12 Passed

Description

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 specific and well-branded with concrete actions, but it lacks an explicit 'Use when...' trigger clause and its keywords lean technical rather than natural, leaving completeness and trigger-term quality at the mid level.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when an agent needs a real inbox for signups, verification codes, or transactional email.'

Weave in natural user phrasing such as 'inbox', 'verification email', and 'sign up for services' to broaden trigger-term coverage.

Keep the concrete action list but trim product jargon ('karma balance') in favor of user-facing language.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions ('Create accounts, send/receive emails, manage webhooks, and check karma balance'), matching the anchor for listing several specific concrete actions rather than naming a domain with only some actions.	3 / 3
Completeness	It clearly states what the skill does but omits any 'Use when...' clause or equivalent explicit trigger guidance for when to invoke it, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	It includes some relevant natural keywords ('send/receive emails', 'accounts') but leans on product jargon ('webhooks', 'karma balance', 'AgentMail API') and misses common variations like 'inbox', 'sign up', or 'verification email' that users would naturally say.	2 / 3
Distinctiveness Conflict Risk	The branded 'AgentMail API' plus the specific AI-agent email niche gives it a clear, distinct domain unlikely to trigger for unrelated skills, rather than the generic overlap of a 'somewhat specific but could overlap' score 2.	3 / 3
	Total	10 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/agentmail/SKILL.md
Commit: 07da495

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.