agentmail

Give the agent its own inbox: send and receive email.

Quality

68%

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 ./optional-skills/email/agentmail/SKILL.md

Quality

Content

75%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.

The body is lean, well-structured, and actionable with concrete config and verification commands plus clearly sequenced workflows. The main gaps are prose-described (rather than executable) tool-call syntax and the absence of explicit error-recovery loops and split reference files.

Suggestions

Show at least one tool invocation as fully executable call syntax (e.g. an example `send_message` call with real argument values) to push actionability toward 5.

Add an explicit validation/feedback step in the send workflow (e.g. confirm the inbox exists before sending, and handle send failures by retrying).

Move time-sensitive tier/pricing details into a clearly marked section or keep them in one place only to trim redundancy between Requirements and Pitfalls.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no explanation of email/MCP/API keys) and is well-structured, with only minor trimmable bits like the free-tier detail repeated in both Requirements and Pitfalls and time-sensitive pricing/version notes not isolated in a deprecated section.	4 / 5
Actionability	The MCP config YAML and the `hermes --toolsets mcp -q ...` verification command are copy-paste ready, and tool calls are named with their parameters; it falls short of 5 because the tool invocations are described in prose rather than shown as fully executable call syntax.	4 / 5
Workflow Clarity	Create/send, check-incoming, and reply procedures are clearly numbered, and the Verification section plus the "check for replies" step provide checkpoints; it misses 5 because there are no explicit error-recovery feedback loops within the workflows.	4 / 5
Progressive Disclosure	Sections are well-organized (Requirements, Setup, Tools table, Procedure, Workflows, Pitfalls, Verification, References) with one-level-deep external links clearly signaled; it is not 5 because no bundle files exist and all content is inline in a single monolithic file rather than split across references.	4 / 5
	Total	16 / 20 Passed

Description

61%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.

The description is concise and names a distinctive niche with two concrete actions, but it lacks an explicit "Use when..." trigger clause, which caps completeness and limits trigger guidance. Adding a when-to-use phrase would lift the weaker dimensions.

Suggestions

Append a "Use when..." trigger clause, e.g. "Use when the agent needs its own email address to send, receive, or reply to messages."

Add one or two more concrete actions (e.g. manage threads, download attachments) to raise specificity from 1-2 actions to several.

Include natural synonyms such as "mail" or "messages" alongside "email" to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"send and receive email" names the domain plus two concrete actions (send, receive), but does not cover threads, attachments, or inbox management, so it stops at the 1-2-actions anchor rather than the 'several specific actions' level.	3 / 5
Completeness	The description gives a clear "what" ("Give the agent its own inbox: send and receive email") but contains no "Use when..." trigger clause, and the rubric caps completeness at 3 when explicit trigger guidance is missing.	3 / 5
Trigger Term Quality	"inbox", "send and receive email", and "email" are natural phrases a user would say, giving good coverage; it falls short of 5 only because synonyms like "mail" or "messages" are absent.	4 / 5
Distinctiveness Conflict Risk	"the agent its own inbox" carves a clear niche distinct from personal-email skills, but "send and receive email" leaves minor overlap risk with general mail skills, so it sits at mostly-distinct rather than minimal-conflict.	4 / 5
	Total	14 / 20 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: 6680afb

Reviewed: about 4 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.