CtrlK
BlogDocsLog inGet started
Tessl Logo

meeting-scheduler

Handles end-to-end meeting scheduling using the Superhuman Mail MCP server — from finding available times to sending the invite or proposing times via email. Use this skill whenever someone asks to "schedule a meeting with [person]", "find a time to meet", "book a call", "set up a meeting", "when am I free to meet with [person]", "propose times to [person]", "send my availability", "create a meeting invite", "schedule a 1:1", "find overlap in our calendars", "reschedule my meeting with [person]", or any variation of coordinating a meeting. Also trigger when someone says "I need to find time with [person]", "can you check my calendar and suggest times", "set up a recurring sync", "block time for [task]", or when an email thread involves scheduling and the user wants to act on it. Trigger broadly — if someone needs help coordinating when people meet, this skill should activate.

94

1.66x
Quality

92%

Does it follow best practices?

Impact

98%

1.66x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is meeting-scheduler in superhuman/mcp-mail

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

The body is a well-sequenced, highly actionable workflow that names exact MCP tools and parameters and builds in confirmation checkpoints and error-recovery paths. The main weakness is conciseness: the closing 'Important guidelines' section duplicates guidance already stated in the steps.

Suggestions

Trim the 'Important guidelines' section to only points not already covered in the steps, or replace it with a short checklist that cross-references the relevant step instead of restating it, to reduce token redundancy.

Consolidate the repeated 'always include the user (the user's email address)' instruction — currently stated in Step 2, Step 4a, and Important guidelines — into a single authoritative location and reference it.

Consider folding the timezone-filtering example in Step 2b into a tighter rule statement, since the ET/PT illustration restates the discard rule immediately above it.

DimensionReasoningScore

Conciseness

The body is mostly efficient and explains no basic concepts Claude already knows, but the 'Important guidelines' section restates points already covered in the steps (verify identity, respect working hours, always include the user), so not every token earns its place.

2 / 3

Actionability

Names exact MCP tools and their parameters (participants, start_date, duration_minutes, recurrence, instructions, etc.) with concrete example instructions and a formatted output template — copy-paste-ready guidance for an instruction-only skill.

3 / 3

Workflow Clarity

A clear Step 1→4c sequence with explicit confirmation checkpoints (identity resolution in 1b, 'always confirm before booking', draft review before send) and error-recovery paths for ambiguous matches and no-available-slots cases.

3 / 3

Progressive Disclosure

Well-organized into clearly headed sections (How it works, Steps, Handling scheduling threads, Important guidelines) with no nested or deep references; the single cohesive workflow is appropriately kept inline and easy to navigate.

3 / 3

Total

11

/

12

Passed

Description

100%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.

The description is strong: it states concrete capabilities tied to a specific MCP server, provides an explicit 'Use when…' clause with abundant natural trigger phrases, and carves out a distinct scheduling niche. Its only weakness is verbosity — the trigger list is padded with overlapping variations — but there is no conciseness dimension in this rubric to penalize that.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'finding available times', 'sending the invite', 'proposing times via email' — anchored to the named Superhuman Mail MCP server, matching the anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly states what it does ('end-to-end meeting scheduling…from finding available times to sending the invite or proposing times via email') and when to use it ('Use this skill whenever someone asks to…'), clearly answering both with explicit triggers.

3 / 3

Trigger Term Quality

Covers many natural phrases a user would actually say ('schedule a meeting with [person]', 'book a call', 'find a time to meet', 'set up a recurring sync', 'block time for [task]'), giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear scheduling/calendar niche with distinct coordination triggers; the email-thread trigger is scoped to 'involves scheduling', keeping conflict risk low.

3 / 3

Total

12

/

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.