email-assistant
User asks to read, check, or manage emails - User asks to reply to or send an email - User asks to draft an email response
Best use case
email-assistant is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. User asks to read, check, or manage emails - User asks to reply to or send an email - User asks to draft an email response
User asks to read, check, or manage emails - User asks to reply to or send an email - User asks to draft an email response
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "email-assistant" skill to help with this workflow task. Context: User asks to read, check, or manage emails - User asks to reply to or send an email - User asks to draft an email response
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/email-assistant/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How email-assistant Compares
| Feature / Agent | email-assistant | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
User asks to read, check, or manage emails - User asks to reply to or send an email - User asks to draft an email response
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Email Assistant
Guidelines for reading and writing emails via Gmail MCP tools.
## When to Use
- User asks to read, check, or manage emails
- User asks to reply to or send an email
- User asks to draft an email response
## Core Rules
### 1. Succinct Responses
Keep email drafts **short and to the point**. Avoid:
- Unnecessary pleasantries
- Verbose explanations
- Redundant information
### 2. Match Input Language
**Always reply in the same language as the original email.**
- French email → French reply
- English email → English reply
- Mixed → Follow the dominant language
### 3. Validate Before Sending
**Never send an email without user approval.**
Workflow:
1. Read the email
2. Draft a response
3. Show the draft to the user
4. Wait for explicit confirmation ("yes", "send it", "ok")
5. Only then send the email
## Workflow
### Reading Emails
```text
1. Use list_emails to show recent emails
2. Use read_email to get full content when user selects one
3. Summarize key points if email is long
```
### Replying to Emails
```text
1. Read the original email
2. Identify the language
3. Draft a succinct reply in the same language
4. Present the draft:
---
**To:** recipient@example.com
**Subject:** RE: Original Subject
**Attachment:** file.pdf (if any)
> Draft content here
---
5. Ask: "Should I send this?"
6. Wait for confirmation
7. Use reply_email tool only after approval
```
### Sending New Emails
```text
1. Gather: recipient, subject, content
2. Draft the email
3. Present for validation
4. Send only after explicit approval
```
## Draft Format
Always present drafts in this format:
```text
**To:** recipient@example.com
**Subject:** Subject line
**Attachment:** filename.pdf (if applicable)
---
[Email body here]
---
Ready to send?
```
## Examples
### Good Draft (French)
```text
Bonjour,
Veuillez trouver ci-joint le document demandé.
Cordialement,
[Name]
```
### Bad Draft (Too verbose)
```text
Bonjour Monsieur,
J'espère que vous allez bien et que vous passez une excellente journée.
Je me permets de vous écrire pour vous transmettre le document que vous
m'avez demandé lors de notre dernier échange. Vous trouverez ci-joint
le fichier en question. N'hésitez pas à me contacter si vous avez des
questions ou si vous avez besoin d'informations supplémentaires.
Je vous souhaite une excellente fin de journée et reste à votre
entière disposition.
Bien cordialement,
[Name]
```
## Available Tools
| Tool | Use For |
| --------------- | ---------------------------------- |
| `list_emails` | Browse inbox |
| `read_email` | Get full email content |
| `search_emails` | Find specific emails |
| `reply_email` | Reply in thread (with attachments) |
| `send_email` | New email (with attachments) |
## Account Parameter
Use the 1Password item name for the `account` parameter:
- `"Gmail Zama Claude"` - Work account
- `"Gmail Personal Claude"` - Personal account
Ask user which account if unclear.Related Skills
github-release-assistant
Generate bilingual GitHub release documentation (README.md + README.zh.md) from repo metadata and user input, and guide release prep with git add/commit/push. Use when the user asks to write or polish README files, create bilingual docs, prepare a GitHub release, or mentions release assistant/README generation.
agent-email-cli
Operate the agent-email CLI to create disposable inboxes, poll for new mail, retrieve full message details, and manage local mailbox profiles. Use when the user needs terminal-based email inbox access for LLM or agent automation workflows.
image-assistant
配图助手 - 把文章/模块内容转成统一风格、少字高可读的 16:9 信息图提示词;先定“需要几张图+每张讲什么”,再压缩文案与隐喻,最后输出可直接复制的生图提示词并迭代。
llm-application-dev-ai-assistant
You are an AI assistant development expert specializing in creating intelligent conversational interfaces, chatbots, and AI-powered applications. Design comprehensive AI assistant solutions with natur
email-systems
Email has the highest ROI of any marketing channel. $36 for every $1 spent. Yet most startups treat it as an afterthought - bulk blasts, no personalization, landing in spam folders. This skill covers transactional email that works, marketing automation that converts, deliverability that reaches inboxes, and the infrastructure decisions that scale. Use when: keywords, file_patterns, code_patterns.
react-email
Use when creating HTML email templates with React components - welcome emails, password resets, notifications, order confirmations, newsletters, or transactional emails.
feature-design-assistant
Turn ideas into fully formed designs and specs through natural collaborative dialogue. Use when planning new features, designing architecture, or making significant changes to the codebase.
openclaw-feishu-ops-assistant
Feishu (Lark) workspace operations for OpenClaw agents. Provides document CRUD, cloud drive management, permission control, and knowledge-base navigation through a unified tool surface. Activate when user mentions Feishu docs, wiki, drive, permissions, or Lark cloud documents.
home-assistant-manager
Expert-level Home Assistant configuration management with efficient deployment workflows (git and rapid scp iteration), remote CLI access via SSH and hass-cli, automation verification protocols, log analysis, reload vs restart optimization, and comprehensive Lovelace dashboard management for tablet-optimized UIs. Includes template patterns, card types, debugging strategies, and real-world examples.
homeassistant-config
Create and manage Home Assistant YAML configuration files including automations, scripts, templates, blueprints, Lovelace dashboards, and file organization. Use when working with Home Assistant configuration files (.yaml, .yml) or discussing HA automations, scripts, sensors, or dashboards.
when-reviewing-code-comprehensively-use-code-review-assistant
Comprehensive PR review with multi-agent swarm specialization for security, performance, style, tests, and documentation
when-debugging-code-use-debugging-assistant
Intelligent debugging workflow that systematically identifies symptoms, performs root cause analysis, generates fixes with explanations, validates solutions, and prevents regressions through compre...