batch-draft-writer
Drafts multiple email replies or follow-ups in batch using the Superhuman Mail MCP server — processing your inbox in bulk rather than one email at a time. Use this skill whenever someone asks to "draft replies to my unread emails", "respond to all my emails", "write follow-ups for my meetings this week", "batch draft responses", "draft emails for all threads that need a reply", "auto-draft my inbox", "help me respond to everything", "write follow-up emails based on my meetings", "process my inbox", "draft responses to these threads", or any variation of wanting multiple emails drafted at once. Also trigger when someone says "I have a bunch of emails to respond to", "help me get through my inbox", "draft a mail merge", "send personalized emails to these people", or wants to create multiple drafts from a single prompt. Trigger broadly — if someone wants more than one email drafted, this skill should activate.
85
83%
Does it follow best practices?
Impact
85%
1.84xAverage score across 3 eval scenarios
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 excellent trigger term coverage and clear completeness, explicitly answering both what the skill does and when to use it. Its main weakness is that the 'what' portion could be more specific about the concrete capabilities beyond just 'drafts replies and follow-ups' — for example, does it search inbox, filter threads, handle attachments, or format differently for different contexts? The description is also quite verbose, with the trigger phrase list being somewhat redundant.
Suggestions
Add more specific concrete actions to the capability description, e.g., 'searches inbox for unread threads, categorizes by priority, drafts contextual replies, and queues them as Superhuman drafts' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (email drafting in batch via Superhuman Mail MCP server) and the core action (drafts multiple email replies or follow-ups in batch), but it doesn't list multiple distinct concrete actions beyond 'drafts replies' and 'follow-ups'. Most of the description is trigger phrases rather than capability details. | 2 / 3 |
Completeness | The description clearly answers both 'what' (drafts multiple email replies/follow-ups in batch using Superhuman Mail MCP server) and 'when' (extensive explicit 'Use this skill whenever...' clause with numerous trigger scenarios). The 'when' guidance is exceptionally thorough. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say, including 'draft replies to my unread emails', 'respond to all my emails', 'process my inbox', 'help me get through my inbox', 'batch draft responses', 'mail merge', and many more natural variations. These are highly realistic user phrases. | 3 / 3 |
Distinctiveness Conflict Risk | The skill is clearly distinguished by its focus on *batch/multiple* email drafting via a specific tool (Superhuman Mail MCP server). The repeated emphasis on 'more than one email' and 'bulk' processing creates a clear niche distinct from single-email drafting 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 with a well-defined multi-step workflow and clear validation checkpoints (user approval gates before drafting and sending). Its main weakness is moderate verbosity — the inbox filter warning is repeated three times, the introductory context is unnecessary, and some guidelines restate what's already covered in the workflow steps. The actionability is excellent with specific tool calls and parameters throughout.
Suggestions
Consolidate the repeated 'always filter to inbox' guidance into a single prominent callout rather than stating it in Steps 2, the Important box in Step 2, and again in the guidelines section.
Remove the introductory paragraph ('You are a writing assistant...') and the 'How it works' header — Claude doesn't need to be told what the skill is about when the steps themselves are self-explanatory.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary verbosity — e.g., the introductory paragraph explaining what the skill does, the 'How it works' framing, and some redundant restatements of guidelines (the inbox filter point is made three times). Several sections could be tightened without losing clarity. | 2 / 3 |
Actionability | The skill provides specific MCP tool calls with exact parameter names (e.g., `Superhuman_Mail.list_threads` with `is_unread: true` and `labels: ["INBOX"]`), concrete workflow templates, and precise instructions for each step. The guidance is directly executable — Claude knows exactly which tools to call and with what parameters. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced across 6 steps with explicit validation checkpoints: Step 3 requires user approval before drafting, Step 5 requires explicit confirmation before sending, and Step 6 handles revisions. The feedback loop of draft → review → revise → send is well-defined, and sensitive threads are flagged rather than auto-drafted. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear headers and logical sections, but it's a monolithic document with no references to external files. Given the length (~150+ lines) and the amount of detail on voice matching, mail merges, and meeting follow-ups, some content could be split into separate reference files. However, with no bundle files provided, this is a reasonable single-file approach. | 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.