superhuman-mail

Use Superhuman Mail MCP for email and calendar workflows such as searching inboxes, reading threads, drafting or sending mail, managing labels, checking read statuses, finding availability, and creating or updating events.

Quality

91%

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

100%Weight 40%Scale 1-3

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

A well-structured, concise MCP orchestration skill that gives concrete behavioral guardrails with explicit confirmation checkpoints for risky actions. It assumes Claude's competence and avoids unnecessary explanation while staying actionable.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no concept explanations Claude already knows; each section (Workflow, Common Capabilities, Safety Notes) earns its place and assumes Claude's competence.	3 / 3
Actionability	Provides concrete, specific guidance — 'summarize the intended action and get user confirmation before calling the tool', 'Prefer creating or updating drafts before sending', 'ask which account to use' — which is actionable for an instruction-only MCP skill where code is not applicable.	3 / 3
Workflow Clarity	The numbered Workflow sequence includes explicit validation checkpoints for destructive operations (confirmation before sending/trashing/unsubscribing and authorization gates on sensitive reads), satisfying the destructive-ops feedback-loop requirement.	3 / 3
Progressive Disclosure	A short, self-contained skill under 50 lines with no need for external references, organized into clearly labeled sections — meeting the simple-skill allowance for full progressive disclosure credit.	3 / 3
	Total	12 / 12 Passed

Description

82%Weight 40%Scale 1-3

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 that names concrete email and calendar actions and natural trigger terms. Its main gap is the absence of an explicit 'Use when…' trigger clause, which leaves the invocation condition implied rather than stated.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks to search, read, send, or label email, check read statuses, find availability, or manage calendar events in Superhuman.'

Mirror the natural phrasings a user would say (e.g. 'find a time to meet', 'mark thread as done', 'check who read my email') to strengthen trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'searching inboxes, reading threads, drafting or sending mail, managing labels, checking read statuses, finding availability, and creating or updating events' — matching the anchor for listing several concrete actions rather than vague domain references.	3 / 3
Completeness	It clearly states what the skill does via the capability list, but there is no explicit 'Use when…' trigger clause; the 'when' is only implied through the 'such as' scenarios, so per the guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Covers natural terms users would actually say — 'email', 'calendar', 'inboxes', 'threads', 'labels', 'read statuses', 'availability', 'events' — giving good coverage of common phrasings rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	Tied to the product-specific 'Superhuman Mail MCP', giving it a clear niche with distinct triggers unlikely to conflict with unrelated skills.	3 / 3
	Total	11 / 12 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: openai/plugins
Path: plugins/superhuman/skills/superhuman-mail/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.