CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is eod-wrapup in superhuman/mcp-mail

SKILL.md
Quality
Evals
Security

Quality

Content

72%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, highly actionable instruction skill with concrete MCP calls and clear sequencing. It loses points on conciseness (soft tone padding) and workflow_clarity (no explicit verification checkpoint before the batch archive/mark-done actions).

Suggestions

Tighten the tone/philosophy prose (e.g., 'without that nagging feeling that they forgot something', 'End on a positive note') into terse behavioral directives so every token earns its place and conciseness reaches 3.

Add an explicit verification checkpoint before batch destructive actions, e.g. 'Before archiving, list the threads to be marked done and confirm with the user; only then call update_thread with mark_done: true', to satisfy the rubric's feedback-loop requirement and lift workflow_clarity to 3.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete MCP calls and no concept-explanation fluff, but includes soft tone/philosophy padding ('without that nagging feeling that they forgot something', 'reduce anxiety, not create it', 'Don't guilt-trip', 'End on a positive note') that could be tightened, matching the level-2 'mostly efficient but could be tightened' anchor rather than the level-3 'every token earns its place' anchor.

2 / 3

Actionability

Provides specific, parameterized executable MCP calls ('Superhuman_Mail.list_threads' with 'labels: ["INBOX"]', 'limit: 50', 'is_unread: true'; 'query_email_and_calendar'; 'create_or_update_draft'; 'update_thread' with 'mark_done: true'/'mark_starred: true') plus a concrete output template, matching the level-3 'fully executable; copy-paste ready' anchor.

3 / 3

Workflow Clarity

The 5-step sequence is clearly numbered with explicit guardrails (the 'labels: ["INBOX"]' filter emphasized in Step 1 and the guidelines), but Step 4 performs batch/destructive-ish operations ('archive the low-priority unread threads' via mark_done) with no explicit verify-before-act checkpoint, so per the rubric's batch/destructive-ops rule workflow_clarity is capped at 2.

2 / 3

Progressive Disclosure

A single-file skill with no bundle files, organized into clear headed sections (How it works -> 5 steps -> Important guidelines) and no obvious content that should be split out; the rubric's note allows 3 for skills with no need for external references when well-organized.

3 / 3

Total

10

/

12

Passed

Description

90%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 strong, complete description with excellent trigger-term coverage and a clear, distinguishable niche. Its only real weakness is second-person benefit framing ('your day', 'you can leave work with a clear head') that costs it a specificity point under the rubric's voice rule.

Suggestions

Rewrite the benefit clause in third person to remove 'your day' and 'so you can leave work with a clear head' (e.g., 'identifies open loops, unanswered emails, and action items from the day so the user can sign off with confidence') to recover the specificity point lost to the second-person penalty.

Trim a few generic triggers like 'anything I'm forgetting' and 'what should I tackle tomorrow' that overlap with general task-management skills, or scope them explicitly to inbox/email context to reduce conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Generates an end-of-day wrap-up', 'identifies open loops, unanswered emails, and action items') which maps to the level-3 anchor, but the second-person benefit framing ('from your day', 'so you can leave work with a clear head') triggers the rubric's -1 specificity penalty for non-third-person voice, bringing it to 2.

2 / 3

Completeness

Explicitly answers what it does ('Generates an end-of-day wrap-up... identifies open loops, unanswered emails, and action items') and when to use it ('Use this skill whenever someone asks to...', 'Also trigger when...', 'Trigger broadly'), matching the level-3 anchor for clear what-AND-when with explicit triggers.

3 / 3

Trigger Term Quality

Broad coverage of natural phrases a user would actually say ('wrap up my day', "what's still open in my inbox", 'what fell through the cracks', 'daily debrief', 'before I log off'), matching the level-3 anchor for good natural-term coverage.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear email/inbox end-of-day niche tied to the Superhuman Mail MCP server with predominantly inbox-specific triggers, fitting the level-3 'clear niche with distinct triggers' anchor despite a few broad phrases like 'anything I'm forgetting'.

3 / 3

Total

11

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
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.