Skip to content

Add email-drafter skill: personalized email drafting with tone analysis via WorkIQ#1182

Merged
aaronpowell merged 2 commits intogithub:stagedfrom
onsenturk:add-email-drafter-skill
Mar 26, 2026
Merged

Add email-drafter skill: personalized email drafting with tone analysis via WorkIQ#1182
aaronpowell merged 2 commits intogithub:stagedfrom
onsenturk:add-email-drafter-skill

Conversation

@onsenturk
Copy link
Contributor

What this adds

An email-drafter skill that drafts professional emails matching the user's personal writing style.

Key features

  • Analyzes 3-5 recent sent emails via WorkIQ to learn the user's greeting style, structure, sign-off, formality level, and language preference
  • Generates context-aware drafts using prior correspondence with the recipient
  • Adapts tone per recipient (formal for external, casual for internal)
  • Supports proposals, follow-ups, replies, introductions, and status updates
  • Saves drafts as markdown files — never sends emails directly
  • Gracefully degrades without WorkIQ (uses professional defaults)

How it helps

Writing emails that match your personal tone is tedious when you send dozens daily. This skill automates the drafting process while preserving your authentic voice, by learning from your actual email patterns rather than using generic templates.

Requirements

  • WorkIQ MCP tool recommended for tone analysis (Microsoft 365 / Outlook)
  • Works without WorkIQ using sensible professional defaults

Validation


  • pm run skill:validate\ ✅ passed

  • pm run build\ ✅ README updated

@onsenturk onsenturk requested a review from aaronpowell as a code owner March 26, 2026 14:08
Copilot AI review requested due to automatic review settings March 26, 2026 14:08
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds a new email-drafter skill to the skills catalog, providing guided instructions for drafting professional emails with optional WorkIQ-based tone/style analysis, and registers it in the skills index.

Changes:

  • Introduces skills/email-drafter/SKILL.md with a multi-step workflow (context gathering, tone analysis via WorkIQ, drafting rules, and output guidance).
  • Adds the new skill entry to docs/README.skills.md so it’s discoverable in the repository’s skills list.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.

File Description
skills/email-drafter/SKILL.md New skill documentation describing how to draft emails using WorkIQ for tone/style inference, with fallback defaults.
docs/README.skills.md Adds the email-drafter row to the skills index table.

@@ -0,0 +1,100 @@
---
name: email-drafter
description: "Draft and review professional emails that match your personal writing style. Analyzes your sent emails for tone, greeting, structure, and sign-off patterns via WorkIQ, then generates context-aware drafts for any recipient. USE FOR: draft email, write email, compose email, reply email, follow-up email, analyze email tone, email style."
Copy link

Copilot AI Mar 26, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In skill front matter, description is wrapped in double quotes. The skill template/checklist in this repo uses single quotes for description (and it avoids needing to escape quotes inside the text). Consider switching to single quotes to match the established SKILL.md front matter format.

Suggested change
description: "Draft and review professional emails that match your personal writing style. Analyzes your sent emails for tone, greeting, structure, and sign-off patterns via WorkIQ, then generates context-aware drafts for any recipient. USE FOR: draft email, write email, compose email, reply email, follow-up email, analyze email tone, email style."
description: 'Draft and review professional emails that match your personal writing style. Analyzes your sent emails for tone, greeting, structure, and sign-off patterns via WorkIQ, then generates context-aware drafts for any recipient. USE FOR: draft email, write email, compose email, reply email, follow-up email, analyze email tone, email style.'

Copilot uses AI. Check for mistakes.
Comment on lines +35 to +42
1. Pull 3–5 recent sent emails from the user to the same recipient or similar recipients
2. Identify patterns:
- **Greeting style** — formal ("Dear"), standard ("Hello"), casual ("Hi"), or direct (no greeting)
- **Structure** — short paragraphs vs. bullet lists vs. numbered steps
- **Sign-off** — what closing and name format the user typically uses
- **Formality level** — professional, friendly-professional, casual
- **Language** — which language the user writes in with this recipient
3. Apply those patterns to the draft
Copy link

Copilot AI Mar 26, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Step 2 instructs pulling recent sent emails via WorkIQ, but it doesn’t explicitly constrain what content can be copied into the chat/output. To reduce the risk of leaking sensitive info, consider adding an explicit rule to only extract tone/style signals (no verbatim email bodies by default), redact identifiers where possible, and never persist raw WorkIQ email content into the saved draft unless the user requests quoting.

Suggested change
1. Pull 3–5 recent sent emails from the user to the same recipient or similar recipients
2. Identify patterns:
- **Greeting style** — formal ("Dear"), standard ("Hello"), casual ("Hi"), or direct (no greeting)
- **Structure** — short paragraphs vs. bullet lists vs. numbered steps
- **Sign-off** — what closing and name format the user typically uses
- **Formality level** — professional, friendly-professional, casual
- **Language** — which language the user writes in with this recipient
3. Apply those patterns to the draft
1. Pull 3–5 recent sent emails from the user to the same recipient or similar recipients **for analysis only** (do not surface full message bodies by default).
2. Identify patterns:
- **Greeting style** — formal ("Dear"), standard ("Hello"), casual ("Hi"), or direct (no greeting)
- **Structure** — short paragraphs vs. bullet lists vs. numbered steps
- **Sign-off** — what closing and name format the user typically uses
- **Formality level** — professional, friendly-professional, casual
- **Language** — which language the user writes in with this recipient
3. Apply those patterns to the draft.
4. **Privacy & data handling:**
- Use WorkIQ emails only to extract tone and style signals. Do **not** copy prior emails verbatim into the chat or draft by default.
- If you must reference prior content, summarize it and redact direct identifiers where possible (names, email addresses, ticket/contract numbers, internal URLs).
- Never persist raw WorkIQ email content into the saved draft unless the user explicitly requests quoting or inclusion of specific prior text.

Copilot uses AI. Check for mistakes.
Comment on lines +78 to +85
3. Save the final draft to `outputs/<year>/<month>/` with a descriptive filename (e.g., `2026-03-26-email-acme-followup.md`)

## Important Rules

- **Never send emails** — only draft them as files for the user to review and send manually
- Always check WorkIQ for prior context with the recipient when available
- If the user says "draft email" or "write email", activate this skill automatically
- Save drafts using the `outputs/<year>/<month>/` folder convention
Copy link

Copilot AI Mar 26, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The instructions call outputs/<year>/<month>/ a “folder convention”, but this appears to be the only skill referencing that path in the repo. If this is meant to be a new convention, it should be documented centrally; otherwise consider rewording to a default location (or aligning with an existing, documented output directory pattern).

Suggested change
3. Save the final draft to `outputs/<year>/<month>/` with a descriptive filename (e.g., `2026-03-26-email-acme-followup.md`)
## Important Rules
- **Never send emails** — only draft them as files for the user to review and send manually
- Always check WorkIQ for prior context with the recipient when available
- If the user says "draft email" or "write email", activate this skill automatically
- Save drafts using the `outputs/<year>/<month>/` folder convention
3. Save the final draft as a markdown file in the workspace (for example, in an `outputs/` folder) with a descriptive filename (e.g., `2026-03-26-email-acme-followup.md`)
## Important Rules
- **Never send emails** — only draft them as files for the user to review and send manually
- Always check WorkIQ for prior context with the recipient when available
- If the user says "draft email" or "write email", activate this skill automatically
- When saving drafts, follow any existing workspace or project output directory conventions (for example, using an `outputs/` folder if one exists)

Copilot uses AI. Check for mistakes.
@aaronpowell aaronpowell merged commit c49c7a1 into github:staged Mar 26, 2026
8 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants