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.
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description with exceptional trigger term coverage and clear 'when to use' guidance. Its main weakness is that the 'what it does' portion is somewhat high-level — it says it 'triages your inbox and previews your day' but doesn't enumerate the specific actions it performs (e.g., categorizing by priority, summarizing threads, listing calendar events). Additionally, the description uses second person ('your inbox', 'your day') which should ideally be third person per the rubric guidelines, though this is a minor issue.
Suggestions
Add more specific concrete actions to the 'what' portion, e.g., 'Categorizes emails by urgency, summarizes unread threads, flags action-required messages, and lists upcoming calendar events' instead of the vague 'triages your inbox and previews your day'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (inbox triage, morning briefing, calendar preview) and mentions the Superhuman Mail MCP server, but the actual concrete actions are somewhat vague — 'triages your inbox and previews your day' doesn't list specific operations like 'categorizes emails by priority, summarizes unread threads, lists calendar events'. | 2 / 3 |
Completeness | Clearly answers both what (generates a morning briefing that triages inbox and previews the day using Superhuman Mail MCP) and when (extensive explicit trigger list with 'Use this skill whenever...' clause covering many natural variations). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would actually say: 'brief me on my day', 'triage my inbox', 'what's important in my email', 'summarize my unread emails', 'catch me up on my inbox', 'morning update', 'inbox summary', and casual variants like 'I just woke up, what's going on'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — it's specifically tied to the Superhuman Mail MCP server, morning briefings, and inbox triage. The 'chief of staff' framing and email-specific triggers make it unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill that provides clear step-by-step guidance with specific MCP tool calls and parameters. The workflow is well-sequenced with a complete output template and safety guardrails. The main weakness is moderate verbosity — some framing and explanatory text could be trimmed to improve token efficiency, and the content could benefit from splitting into referenced files for the detailed categorization criteria and output template.
Suggestions
Trim the introductory paragraphs — Claude doesn't need to be told it's an 'AI chief of staff' or what the skill's purpose is; jump straight into the workflow steps.
Consider extracting the output template and categorization criteria into a referenced file to reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary framing (e.g., 'Your job is to give the user a calm, structured start to their day') and explanatory text that Claude doesn't need. The preamble about what the skill does and the MCP server could be trimmed. However, the categorization criteria and action steps are well-justified and earn their tokens. | 2 / 3 |
Actionability | The skill provides specific MCP tool calls with exact parameter names (e.g., `is_unread: true`, `labels: ["INBOX"]`, `limit: 50`), concrete query strings to use, specific tool methods like `Superhuman_Mail.create_or_update_draft` and `Superhuman_Mail.update_thread`, and a complete output template. This is highly executable guidance. | 3 / 3 |
Workflow Clarity | The four-step workflow is clearly sequenced (gather → categorize → present → offer actions), with explicit parallel execution in Step 1, clear categorization criteria in Step 2, a structured output template in Step 3, and concrete follow-up actions in Step 4. The 'Important notes' section includes edge case handling (50+ unread inbox) and a critical safety constraint (never send without approval). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's a fairly long single file with no references to supporting materials. The categorization criteria, output template, and important notes could potentially be split into referenced files for better token efficiency. However, for a standalone skill with no bundle, the inline organization is reasonable. | 2 / 3 |
Total | 10 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- superhuman/mcp-mail
- Commit
03565c9
- 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.