agentmail

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

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

78%Weight 40%Scale 1-5

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

A highly actionable, lean API skill with excellent executable examples and well-sequenced common patterns. The main gaps are structural: everything lives inline in SKILL.md rather than being split into reference files, and the polling workflows lack timeout and error-recovery handling.

Suggestions

Move the full API reference table, TypeScript types, and SDK usage into a references/ file (e.g. references/api.md), keeping only the quick start and key patterns inline in SKILL.md.

Add timeout handling to the polling loops (e.g., break with an explicit failure message after the retry budget is exhausted) and a recovery step for HTTP 402 (check karma, top up or surface the failure).

Trim the duplication between the curl quick-start examples and the TypeScript SDK section, or explicitly frame one as the reference for the other.

Dimension	Reasoning	Score
Conciseness	The body is fact-dense (endpoint tables, karma rules, TypeScript types) with no explanation of concepts Claude already knows, but the curl quick-start and the TypeScript SDK section restate the same operations, a trimmable redundancy. Efficient with minor over-explanation fits anchor 4 rather than 5's every-token-earns-its-place.	4 / 5
Actionability	Copy-paste-ready curl commands with real payloads and response shapes, complete SDK snippets, concrete error handling ("console.log(e.status); // 402, 404, 401"), and realistic polling loops. Fully executable guidance covering the common cases matches anchor 5.	5 / 5
Workflow Clarity	Common-pattern workflows are clearly sequenced (create account → poll for verification; send → await reply) and "Always check balance before operations that cost karma" is an explicit checkpoint, but the polling loops lack timeout handling and there is no recovery loop after a 402. Clear sequence with minor validation gaps fits anchor 4, not 5's explicit feedback loops.	4 / 5
Progressive Disclosure	Section headers are clear, but the full API reference table, TypeScript types, and SDK usage (~100+ lines) are all inlined in SKILL.md with no bundle files or references — content that clearly belongs in a separate reference file is inline. This fits anchor 3's good-structure-but-should-be-separate, not 2 (structure is present, not minimal) and not 4 (nothing is split out).	3 / 5
	Total	16 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description with strong verb-led capability listing and clear niche identity. Its main weakness is the absence of any "Use when..." trigger clause, which both caps completeness and leaves some natural trigger terms unsurfaced.

Suggestions

Append a trigger clause such as "Use when an agent needs an email address to sign up for services, receive verification codes, or exchange email programmatically."

Surface natural user phrasings like "inbox", "verification code", and "email address" in the description to improve trigger matching.

Mention the @theagentmail.net domain convention so users referencing a specific address format can find the skill.

Dimension	Reasoning	Score
Specificity	"Create accounts, send/receive emails, manage webhooks, and check karma balance via the AgentMail API" lists multiple specific concrete actions covering the API's full surface in third-person voice. It fits anchor 5, not 4, because there are no minor coverage gaps across the service's capabilities.	5 / 5
Completeness	The "what" is clear and concrete (email infrastructure with enumerated actions), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines. Not 2 because the "what" is fully explicit rather than vague.	3 / 5
Trigger Term Quality	Natural phrases like "send/receive emails", "webhooks", and "karma balance" are present, but common user phrasings such as "inbox", "verification code", and "email address" are missing. Good coverage fits anchor 4 rather than 5's comprehensive synonym coverage, and exceeds anchor 3's partial keyword set.	4 / 5
Distinctiveness Conflict Risk	"via the AgentMail API" plus niche terms like "karma balance" and "webhooks" carve out a distinct trigger space with minimal overlap against generic email or messaging skills. It matches anchor 5's clear niche with distinct triggers.	5 / 5
	Total	17 / 20 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/agentic-awesome-skills
Path: skills/agentmail/SKILL.md
Commit: 7b534bc

Reviewed: 5 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.