eod-wrapup
Generates an end-of-day wrap-up using the Superhuman Mail MCP server — identifies open loops, unanswered emails, and action items from your day so you can leave work with a clear head. Use this skill whenever someone asks to "wrap up my day", "what's still open in my inbox", "end of day summary", "what do I still need to do", "any emails I missed today", "open loops in my inbox", "summarize my day", "what didn't I respond to", "daily review", "close out my day", "what fell through the cracks", or any variation of wanting to know what's unfinished before signing off. Also trigger when someone says "before I log off", "anything I'm forgetting", "daily debrief", "what should I tackle tomorrow", or wants an accounting of their email activity for the day. Trigger broadly — if someone wants to review what happened and what's still pending at the end of their workday, this skill should activate.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%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 that clearly defines what it does, when to use it, and provides extensive natural-language trigger phrases. The specificity of the tool (Superhuman Mail MCP server) and the use case (end-of-day wrap-up) make it highly distinctive. Minor issues: it uses second person ('your day', 'you can') which slightly deviates from the preferred third-person voice, and the trigger list is somewhat verbose — though the thoroughness is more helpful than harmful for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'identifies open loops, unanswered emails, and action items from your day' and specifies the tool used (Superhuman Mail MCP server). Clear about what it produces (end-of-day wrap-up). | 3 / 3 |
Completeness | Clearly answers both 'what' (generates end-of-day wrap-up identifying open loops, unanswered emails, action items via Superhuman Mail MCP) and 'when' (extensive explicit 'Use this skill whenever...' clause with numerous trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would actually say: 'wrap up my day', 'what's still open in my inbox', 'end of day summary', 'any emails I missed today', 'before I log off', 'what fell through the cracks', 'daily review', and many more natural variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — combines a specific tool (Superhuman Mail MCP server), a specific use case (end-of-day email review), and specific outputs (open loops, unanswered emails, action items). Unlikely to conflict with other skills due to the narrow temporal and functional niche. | 3 / 3 |
Total | 12 / 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, highly actionable skill that provides clear MCP tool calls with specific parameters and a well-sequenced multi-step workflow. Its main weakness is moderate verbosity — motivational framing, tone guidance, and some explanatory text that Claude doesn't need add tokens without proportional value. The output template and action offerings are excellent and make this immediately usable.
Suggestions
Trim the guidelines section — remove soft guidance Claude already knows (don't guilt-trip, end positively) and keep only the MCP-specific operational rules like the INBOX filter requirement.
Remove the introductory paragraph ('You are a closing-time assistant...') since the skill description already covers intent and Claude doesn't need motivational framing.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-written but includes some unnecessary framing ('This is the core value of the skill', 'You are a closing-time assistant', 'so they can log off without that nagging feeling') and soft guidance that Claude already understands (don't guilt-trip, end on a positive note). The guidelines section could be tightened, though the MCP-specific details earn their place. | 2 / 3 |
Actionability | Highly actionable — specifies exact MCP tool calls with parameters (e.g., `Superhuman_Mail.list_threads` with `is_unread: true`, `labels: ["INBOX"]`), provides concrete query strings for `query_email_and_calendar`, names specific actions like `create_or_update_draft` and `update_thread` with exact parameter names. The output template is copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear 5-step sequential workflow with explicit parallel execution in Step 1, analysis in Step 2, structured output in Step 3, follow-up actions in Step 4, and an optional expansion in Step 5. The repeated emphasis on the `labels: ["INBOX"]` filter serves as a validation checkpoint against the most common failure mode. The workflow is well-sequenced with clear dependencies between steps. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's a fairly long monolithic file (~120 lines of substantive content). The weekly patterns section and the detailed guidelines could potentially be split into separate references. However, with no bundle files, everything must live here, and the organization is reasonable for a standalone skill. | 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.