agentmail

Give the agent its own dedicated email inbox via AgentMail. Send, receive, and manage email autonomously using agent-owned email addresses (e.g. hermes-agent@agentmail.to).

Quality

85%

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

Quality

Content

87%

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

The content is actionable and well-structured with strong progressive disclosure and lean token usage. The main gap is the absence of validation/confirmation checkpoints around destructive or irreversible email operations.

Suggestions

Add a confirmation/validation step before destructive actions (e.g., 'Confirm inbox_id before calling delete_inbox; deletions are irreversible').

Include a post-send verification checkpoint (e.g., check the sent thread via get_thread/list_threads after send_message) to close the feedback loop on irreversible outbound actions.

Trim the minor overlap between the 'Available Tools' table and the 'Procedure' section, which re-describes several of the same tools.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence: a tight tool table, numbered procedures, and short pitfalls with no concept-padding, and every section earns its tokens despite minor repetition between the tool table and procedure sections.	3 / 3
Actionability	Provides fully executable, copy-paste-ready guidance including a complete MCP YAML config, exact commands (hermes, pip install mcp, npx -y agentmail-mcp), a verification command, and tool calls with named parameters.	3 / 3
Workflow Clarity	Multi-step procedures are clearly sequenced, but destructive/irreversible operations (delete_inbox, send_message) lack validation checkpoints, which caps workflow clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	Well-organized sections with clearly signaled one-level-deep external references (docs, console, repo, pricing) and no nested file references; appropriately self-contained single-file overview.	3 / 3
	Total	11 / 12 Passed

Description

82%

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 distinctive with strong natural trigger terms, but it lacks an explicit 'Use when...' trigger clause, which caps its completeness. Adding a sentence on when to invoke the skill would round it out.

Suggestions

Add a 'Use when...' clause stating the trigger conditions (e.g., 'Use when the agent needs its own email address to send, receive, or sign up for services').

Reduce reliance on the product name in favor of more user-natural phrasing like 'give the agent an email address' or 'set up an inbox for the agent'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Send, receive, and manage email autonomously', 'Give the agent its own dedicated email inbox') plus a concrete example address, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers 'what' but has no 'Use when...' or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Uses natural everyday terms a user would say ('email', 'inbox', 'email addresses', 'send...receive') with good coverage; the concrete address example reinforces triggers, though it leans slightly on the product name.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche (agent-owned email inboxes via AgentMail) distinct from personal-email skills, with the product name and example address making conflicts unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/email/agentmail/SKILL.md
Commit: 4c9628e

Reviewed: about 14 hours 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.