CtrlK
BlogDocsLog inGet started
Tessl Logo

agentmail

Use when an agent needs AgentMail CLI email inboxes.

54

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/email/agentmail/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 an exemplary lean overview: executable setup and verification commands, a numbered procedure with a validation checkpoint, concrete pitfalls, and clean one-level-deep progressive disclosure to five real, purpose-annotated reference files. Its only weakness is the absence of a single inline example of the core send/reply commands and of error-recovery guidance in the Procedure.

DimensionReasoningScore

Conciseness

The ~75-line body is lean and assumes Claude's competence throughout — no padding, no explanation of what email or CLI tools are, and every line either instructs or navigates ('Install the CLI', 'Export an API key', 'Use --format json whenever another command or script needs IDs'). This matches the anchor 'Lean and efficient; every token earns its place'.

5 / 5

Actionability

Setup and verification are copy-paste executable ('npm install -g agentmail-cli@latest', 'export AGENTMAIL_API_KEY="am_..."', 'agentmail inboxes list --format json'), and pitfalls give concrete rules ('Prefer AGENTMAIL_API_KEY over --api-key', 'React to message.received'). Minor gap: no inline example of the core send/reply commands, though these are delegated to core.md — fits 'Mostly executable guidance with minor gaps', not 5.

4 / 5

Workflow Clarity

The Procedure is a clearly sequenced 4-step path with an explicit validation checkpoint ('verify agentmail inboxes list --format json') plus a dedicated Verification section. It falls short of the 5 anchor because there is no error-recovery/feedback loop (e.g. what to do when install or signup fails), though operations here are not destructive or batch, so no cap applies.

4 / 5

Progressive Disclosure

The body is a concise overview with well-signaled, one-level-deep references, each annotated with its purpose in both Quick Reference and Procedure ('signup.md: self-signup and OTP verification', 'webhooks.md: events to a public HTTPS server'). Verified against the actual bundle: all five referenced files exist in references/ and are flat (they cross-link only to siblings, never nesting a second level).

5 / 5

Total

18

/

20

Passed

Description

40%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 has an explicit 'Use when...' trigger and a clearly distinct product name, but it is a 'when'-only statement: it never says what the skill does. Adding 2-3 concrete capability verbs (send mail, receive replies, complete email OTP flows) would raise specificity and completeness substantially at negligible token cost.

Suggestions

Add a 'what' clause before the 'Use when' clause, e.g. 'Send and receive email from agent-owned inboxes via the AgentMail CLI: create inboxes, reply in threads, complete email OTP flows, and subscribe to inbound mail via webhooks or WebSockets.'

Include natural trigger synonyms users would say — 'send email', 'email address for the agent', 'email OTP/verification code', 'read replies' — so the skill surfaces for those phrasings.

Keep the distinctive 'AgentMail' and 'agent-owned inbox' framing while adding a contrast (e.g. 'not a user's existing IMAP/SMTP mailbox') to further reduce overlap with generic email skills.

DimensionReasoningScore

Specificity

The description names the domain ('AgentMail CLI email inboxes') but states no concrete actions — nothing about sending mail, receiving replies, completing OTP flows, or webhook delivery, all of which the body clearly supports. This matches the anchor 'Names the domain but actions are minimal or generic'; a score of 3 would require 1-2 concrete actions, which are absent.

2 / 5

Completeness

The 'when' clause is explicit ('Use when an agent needs AgentMail CLI email inboxes') but the 'what' is only weakly implied — no capabilities are stated. This fits the anchor 'only when is present without what' (borderline toward 3, where a clear 'what' would be required, which the description lacks); not 4 because the 'what' is far too vague to pair with the 'when'.

2 / 5

Trigger Term Quality

'email inboxes' and 'agent' are relevant natural terms, but common user phrasings like 'send email', 'reply', 'email verification', 'OTP', or file-format terms are missing. This fits 'Some relevant keywords but missing common variations or synonyms'; not 4, since several natural trigger phrases users would actually say are absent.

3 / 5

Distinctiveness Conflict Risk

'AgentMail CLI' names a specific product with distinct triggers, so overlap risk with generic email skills is minor. This matches 'Mostly distinct; minor overlap risk with closely related skills'; not 5, since the bare word 'inboxes' could compete with other email/mail-related skills given no capability verbs narrow the niche.

4 / 5

Total

11

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

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
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.