CtrlK
BlogDocsLog inGet started
Tessl Logo

morning-briefing

Generates a morning briefing that triages your inbox and previews your day using the Superhuman Mail MCP server — acting as an AI chief of staff. Use this skill whenever someone asks to "brief me on my day", "triage my inbox", "what's important in my email", "summarize my unread emails", "what do I need to deal with today", "chief of staff briefing", "morning update", "inbox summary", "what emails need my attention", "clear my inbox", or any variation of wanting a prioritized view of their email and calendar before they start working. Also trigger when someone says "I just woke up, what's going on" or "catch me up on my inbox". Trigger broadly — if someone wants to understand the state of their inbox or day at a glance, this skill should activate.

69

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 well-structured, highly actionable instruction skill with concrete MCP calls, parameters, and a clear output template. Its only gaps are minor: a little definitional prose could be trimmed, and no technical error-recovery loop is specified for MCP call failures.

Suggestions

Tighten the FYI/Noise definitions and the 'trusted executive assistant' tone line to lift conciseness toward 5.

Add a brief error-recovery note for MCP call failures (e.g., retry once, then surface the failure to the user) to give the workflow an explicit feedback loop.

Since the skill is a single self-contained file slightly over 50 lines, consider extracting the briefing output template into a referenced file only if the body grows; otherwise keep as-is.

DimensionReasoningScore

Conciseness

Lean and purposeful for an instruction skill — it does not over-explain concepts Claude already knows, and the briefing template and category definitions all earn their place. A few definitions ('FYI', 'Noise', tone guidance) could be trimmed slightly, keeping it just below a 5.

4 / 5

Actionability

Fully actionable: names exact MCP calls with concrete parameters (Superhuman_Mail.list_threads with is_unread: true, labels: ["INBOX"], limit: 50; update_thread with mark_done: true; create_or_update_draft with instructions) and provides a copy-ready output structure plus specific action offers.

5 / 5

Workflow Clarity

Clearly sequenced four-step process (gather → categorize → present → offer actions) with a human-in-the-loop validation gate ('Never send an email without explicit user approval'; archiving offered only after user confirmation), satisfying the batch-operation checkpoint requirement. Missing only technical error-recovery guidance for MCP failures.

4 / 5

Progressive Disclosure

Well-organized single file with clear section headers (How it works, Step 1–4, Important notes) and no external references needed for this single-purpose skill. Slightly over the ~50-line simple-skill threshold and monolithic, so it sits at 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

86%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, trigger-rich description that clearly states what the skill does and when to use it, with excellent natural-language trigger coverage. The main weakness is second-person voice and slightly composite action verbs, which cost it on specificity.

Suggestions

Rewrite in third person ('Generates a morning briefing that triages the user's inbox...') to avoid the second-person voice penalty.

Break composite verbs into more atomic concrete actions (e.g., 'lists unread threads, categorizes by urgency, drafts replies, archives noise') to lift specificity.

Narrow the broadest triggers ('clear my inbox', 'inbox summary') or qualify them with the morning/briefing context to reduce overlap with generic email skills.

DimensionReasoningScore

Specificity

Lists several concrete actions ('triages your inbox and previews your day', 'Generates a morning briefing', 'prioritized view of their email and calendar') which would anchor at 4, but the description is written in second person ('your inbox', 'your day') and the actions are composite rather than atomic, so the voice penalty and slight abstraction pull it to 3.

3 / 5

Completeness

Explicitly answers both 'what' (generates a morning briefing that triages inbox and previews the day) and 'when' with a clear 'Use this skill whenever someone asks to...' clause plus concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive coverage of natural phrases a user would actually say — 'brief me on my day', 'triage my inbox', 'summarize my unread emails', 'what do I need to deal with today', 'I just woke up, what's going on', 'catch me up on my inbox' — including synonyms and informal variations.

5 / 5

Distinctiveness Conflict Risk

Clear niche (morning briefing / chief-of-staff triage via the Superhuman Mail MCP server) with distinct triggers, but phrases like 'clear my inbox' and 'summarize my unread emails' carry minor overlap risk with generic email-management skills.

4 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
superhuman/mcp-mail
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.