agentmail-cli

Operate AgentMail from a shell with the official CLI. Use when the user wants commands for listing or creating inboxes, reading or searching mail, sending or replying, managing drafts, or scripting JSON/YAML output; do not use for SDK code, MCP setup, or framework adapters.

Quality

86%

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

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.

A tight, executable command reference with clear section organization and appropriate safety notes on the destructive path. The only real gaps are the missing search example promised by the description and the absence of a verify-then-check loop for domain verification.

Suggestions

Add a message search example (e.g., a `--query`/search flag on `inboxes messages list`) since the description advertises 'searching mail'.

After `agentmail domains verify`, show how to check verification status before proceeding.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: every section is a copy-paste command block with one-line practical notes ("Pods group inboxes together", the nested-subcommand/colon-form warning) that encode CLI-specific knowledge Claude would not know. No padding or explanation of known concepts, matching the 'every token earns its place' anchor.	5 / 5
Actionability	Commands are fully executable with concrete placeholders and cover the common cases (list/get/create/delete, send with text and HTML, reply, forward, drafts, pods, webhooks, domains, flags, formats). A minor gap: the description promises "searching mail" but no search command or flag is shown anywhere in the body.	4 / 5
Workflow Clarity	The destructive operation has an explicit checkpoint ("Confirm the exact inbox before running the destructive delete command") and message handling has verification guidance ("Fetch the full message before relying on body content"), so the destructive-cap-at-3 rule does not apply. Falls just short of anchor 5 because there is no feedback loop around domain verification (no status check after `domains verify`).	4 / 5
Progressive Disclosure	No bundle files exist and none are needed: at ~3.8KB the command reference is appropriately self-contained, cleanly sectioned by resource (Inboxes, Messages and threads, Drafts, Pods, Webhooks, Domains, Global flags, Output formats), and it delegates the long tail to the CLI itself ("Run `agentmail <resource> --help`"). Easy to navigate with no nested or buried references.	5 / 5
	Total	18 / 20 Passed

Description

87%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 strong description: third-person, concrete, with explicit 'what', 'when', and negative boundary clauses. Only minor gaps — unmentioned capability areas (pods, webhooks, domains) and the missing 'email' synonym keep trigger quality and specificity at 4.

Suggestions

Add the 'email' synonym (e.g., 'reading or searching email') since users commonly say 'email' rather than 'mail'.

Mention the remaining capability areas (pods, webhooks, domains) in the action list to close the coverage gap.

Dimension	Reasoning	Score
Specificity	Lists several specific concrete action groups — "listing or creating inboxes, reading or searching mail, sending or replying, managing drafts, or scripting JSON/YAML output" — with only minor coverage gaps (pod, webhook, and domain management supported by the CLI are not mentioned). Fits the 'several specific actions; minor gaps' anchor rather than the comprehensive 5.	4 / 5
Completeness	Explicitly answers both questions: what ("Operate AgentMail from a shell with the official CLI" plus a concrete action list) and when ("Use when the user wants commands for...") with concrete trigger phrases, and adds negative boundaries ("do not use for SDK code, MCP setup, or framework adapters"). Matches the anchor 5 example structure closely.	5 / 5
Trigger Term Quality	Good natural keyword coverage — "inboxes", "mail", "sending or replying", "drafts", "commands", "JSON/YAML output" — that users would plausibly say. Missing common synonyms like "email" and "e-mail", keeping it just below the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche (AgentMail CLI specifically) with distinct triggers and an explicit exclusion clause separating it from SDK, MCP, and framework-adapter skills. Minimal conflict risk, matching anchor 5.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: stevenknowswhy/ProfessionalBuyer
Path: .claude/skills/agentmail-cli/SKILL.md
Commit: 92cff92

Reviewed: 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.