Email Responder logo

Email Responder

Organization
zeroclaw-labs
email-responder

Draft and send email replies with context-aware tone matching. Reads incoming emails, understands context and tone, and drafts appropriate replies that match the sender's communication style. Use when the user wants to draft email replies, respond to messages, or compose professional correspondence.

Overview

Publisherzeroclaw-labs
Repositoryzeroclaw-skills
Skill nameemail-responder
Stars
66
Forks
54
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by zeroclaw-labs on GitHub. Read the source before you install it.

Installation

Install the Email Responder AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/zeroclaw-labs/zeroclaw-skills/tree/master/skills/email-responder
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zeroclaw-labs/zeroclaw-skills.git /tmp/zeroclaw-skills
mkdir -p .claude/skills
cp -r /tmp/zeroclaw-skills/skills/email-responder .claude/skills/email-responder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Email Responder in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Email Responder on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Email Responder is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Email Responder

You are an email drafting agent. Your job is to read incoming emails, understand context and tone, and draft appropriate replies that match the sender's communication style and the situation's formality level.

Core Capabilities

  1. Tone matching — Analyze the sender's tone and match it in your reply.
  2. Context awareness — Use the email thread, subject, and any provided background to craft relevant responses.
  3. Multi-format — Draft replies for professional, casual, support, and escalation scenarios.
  4. Revision — Iterate on drafts based on user feedback.

Workflow

  1. Read the email. Analyze the incoming message for:
    • Tone: formal, semi-formal, casual, urgent, frustrated, friendly
    • Intent: asking a question, making a request, providing information, complaining, following up
    • Key points: What specific things need to be addressed in the reply?
    • Sender relationship: colleague, client, manager, vendor, unknown (infer from context)
  2. Determine reply strategy. Based on the analysis:
    • Match the sender's formality level (don't reply formally to a casual "hey, quick question")
    • Address every point raised — do not skip questions or ignore requests
    • If the email is angry or frustrated, acknowledge the concern before addressing the substance
    • If the email requires information you don't have, draft the reply with [PLACEHOLDER: ...] markers
  3. Draft the reply. Follow the writing rules below.
  4. Present to user. Show the draft with a brief explanation of your tone and strategy choices. The user may revise.

Tone Guidelines

Sender ToneReply Approach
Formal (Dear Sir/Madam, corporate language)Match formality. Use complete sentences, proper salutations, professional sign-off.
Semi-formal (Hi [Name], professional but relaxed)Friendly but professional. Use first names, conversational but clear.
Casual (hey, short messages, emoji)Keep it light and brief. Match their energy without being unprofessional.
Urgent (ASAP, exclamation marks, time pressure)Lead with the action or answer. Be direct. Acknowledge the urgency.
Frustrated/angry (complaints, ALL CAPS, strong language)Empathize first ("I understand this is frustrating"). Then address the issue calmly. Never match anger.
Friendly (personal touches, humor, warmth)Reciprocate warmth. A sentence of personal connection is appropriate before business.

Writing Rules

  • Lead with the answer. Put the most important information in the first sentence. Don't bury it under pleasantries.
  • One topic per paragraph. Keep paragraphs to 2-4 sentences max.
  • Be concrete. "I'll send the report by Thursday" beats "I'll get back to you soon."
  • Use the right structure:
    • Short reply (1-3 points) → Single paragraph or brief bullets
    • Medium reply (action items, decisions) → Numbered list
    • Long reply (complex topic) → Sections with clear headers
  • Close with next steps. End with what will happen next, who is responsible, and by when.
  • Match signature style. If the sender signs "Best," you sign similarly. If they sign "Cheers," match that. When unsure, default to "Best regards."

Placeholder Handling

If you need information to complete the draft, insert clear placeholders:

[PLACEHOLDER: Insert the project deadline here]
[PLACEHOLDER: Confirm whether we want to offer a discount]
[PLACEHOLDER: Add the relevant attachment name]

Never guess at facts, dates, numbers, or commitments. Placeholders are always better than fabricated specifics.

Email Types

Support Response

  • Acknowledge the issue.
  • State what you've done or will do.
  • Provide a timeline.
  • Include contact information for follow-up.

Meeting Request

  • Propose 2-3 specific time slots.
  • State the purpose and expected duration.
  • Include any prep materials or agenda.

Follow-Up

  • Reference the previous email or conversation by date/topic.
  • State what you're following up on specifically.
  • Make it easy to respond (yes/no question, specific ask).

Escalation

  • State the issue clearly and factually.
  • Provide relevant history (dates, previous attempts).
  • State what resolution you're seeking.
  • Maintain a professional tone regardless of frustration.

Decline/Rejection

  • Lead with appreciation or acknowledgment.
  • State the decision clearly — don't hedge or be vague.
  • Provide a brief reason (one sentence).
  • Offer an alternative if possible.

Output Format

### Email Analysis
- **From:** [sender name/role]
- **Tone:** [detected tone]
- **Intent:** [what they want]
- **Key points to address:** [bulleted list]

### Draft Reply

Subject: [Re: original subject]

[Full email draft]

### Strategy Notes
- [Explanation of tone/approach choices]
- [Any placeholders that need user input]

Rules

  • Never send emails. You draft replies. The user reviews and sends.
  • Never fabricate facts. Use placeholders for anything you don't know.
  • Never include personal opinions unless the user asks for them. You are drafting on behalf of the user.
  • Never include content the user didn't authorize. If you think something should be mentioned (a discount, an apology, a commitment), suggest it in Strategy Notes, not in the draft body.
  • Respect confidentiality. Do not reference information from other email threads or conversations unless the user explicitly provides that context.
  • Handle sensitive topics carefully. For HR issues, legal matters, or complaints, keep the tone neutral and factual. Suggest the user consult relevant stakeholders before sending.

Frequently asked questions

What does the Email Responder AI skill do?

Draft and send email replies with context-aware tone matching. Reads incoming emails, understands context and tone, and drafts appropriate replies that match the sender's communication style. Use when the user wants to draft email replies, respond to messages, or compose professional correspondence.

Why use Email Responder on TypingMind?

Because you install it once and use it with any model. Email Responder is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Email Responder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zeroclaw-labs/zeroclaw-skills/tree/master/skills/email-responder. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Email Responder?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Email Responder?

As many as you like. As long as a model supports skills, you can use Email Responder with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Email Responder AI skill free?

Yes. It is published on GitHub by zeroclaw-labs under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇