
- Installs
- 57
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/aws-samples/sample-strands-agent-with-agentcore --skill gmail- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads gmail automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Gmail
Available Tools
-
list_labels(): List all Gmail labels (system: INBOX, SENT, TRASH, SPAM, DRAFT, IMPORTANT, STARRED, UNREAD; plus user-created labels).
-
list_emails(label?, max_results?, include_spam_trash?): List emails by label.
label(string, optional, default: "INBOX"): Label to filter by (INBOX, SENT, DRAFT, TRASH, SPAM, STARRED, IMPORTANT, or custom label ID)max_results(integer, optional, default: 10, max: 100): Number of emails to returninclude_spam_trash(boolean, optional, default: false): Include SPAM and TRASH
-
search_emails(query, max_results?): Search Gmail using query syntax.
query(string, required): Gmail search query (from:, to:, subject:, is:unread, has:attachment, after:, before:, older_than:, newer_than:)max_results(integer, optional, default: 10, max: 50): Number of results
-
read_email(message_id): Read a full email including body and attachments.
message_id(string, required): Gmail message ID (from list_emails or search_emails)
-
send_email(to, subject, body, cc?, bcc?, reply_to?, in_reply_to?, html_body?): Send an email.
to(string, required): Recipient(s), comma-separatedsubject(string, required): Email subjectbody(string, required): Plain text email bodycc(string, optional): CC recipient(s)bcc(string, optional): BCC recipient(s)reply_to(string, optional): Reply-To addressin_reply_to(string, optional): Message-ID to reply to (for threading)html_body(string, optional): HTML version of email body
-
draft_email(to, subject, body, cc?, bcc?, reply_to?, in_reply_to?, html_body?): Create a draft for later editing/sending. Same parameters as
send_email. -
delete_email(message_id, permanent?): Delete an email.
message_id(string, required): Gmail message IDpermanent(boolean, optional, default: false): If true, permanently delete; if false, move to Trash
-
bulk_delete_emails(query, reason, max_delete?): Permanently delete multiple emails by query. Cannot be undone.
query(string, required): Gmail search query to find emailsreason(string, required): Human-readable explanation (shown to user for approval)max_delete(integer, optional, default: 50, max: 100): Maximum emails to delete
-
modify_email(message_id, add_labels?, remove_labels?): Add/remove labels on an email.
message_id(string, required): Gmail message IDadd_labels(string, optional): Comma-separated label IDs to add (e.g., "STARRED,IMPORTANT")remove_labels(string, optional): Comma-separated label IDs to remove (e.g., "UNREAD,INBOX")
-
get_email_thread(thread_id): Get all messages in an email thread/conversation.
thread_id(string, required): Gmail thread ID (from read_email or search_emails)
Usage Guidelines
- Call
list_emailsdirectly for standard labels such as INBOX, SENT, DRAFT, TRASH, SPAM, STARRED, and IMPORTANT. Uselist_labelsonly when the user asks for a custom label or the label name is unknown. - Gmail search query syntax:
from:sender,to:recipient,subject:text,is:unread,has:attachment,after:2024/01/01,before:2024/12/31. - Use
get_email_threadto view entire conversation context before replying.
Common Operations
Label operations via modify_email:
| Operation | Parameters |
|---|---|
| Mark as read | remove_labels="UNREAD" |
| Mark as unread | add_labels="UNREAD" |
| Archive | remove_labels="INBOX" |
| Star | add_labels="STARRED" |
| Unstar | remove_labels="STARRED" |
| Mark important | add_labels="IMPORTANT" |
Bulk Deletion
bulk_delete_emails(query, reason) permanently deletes all emails matching a Gmail query. This cannot be undone.
- Always provide a
reasonparameter explaining the intent. - Always explain what will be deleted and get user confirmation before calling.
Common queries:
- Spam cleanup:
"is:spam older_than:7d" - Old unread:
"in:inbox is:unread older_than:14d" - Promotions purge:
"category:promotions older_than:30d" - From specific sender:
"from:noreply@example.com older_than:30d"
UI Guidance (from tools-config)
Gmail Tool Usage:
- list_labels: Discover custom labels when the requested label is unknown
- list_emails: Browse emails by label (INBOX, SENT, DRAFT, TRASH, etc.)
- search_emails: Use Gmail query syntax (from:, to:, subject:, is:unread, has:attachment, after:, before:)
- read_email: Get full email content with attachments
- send_email: Send emails with optional CC, BCC, and HTML body
- draft_email: Create drafts for later editing/sending
- delete_email: Move to trash (permanent=True for permanent deletion)
- bulk_delete_emails: Permanently delete multiple emails by query (requires user approval)
- modify_email: Add/remove labels (mark read: remove UNREAD, archive: remove INBOX, star: add STARRED)
- get_email_thread: View entire conversation thread
Bulk Deletion (bulk_delete_emails):
- Use for spam cleanup, old email purge, etc.
- Always provide 'reason' parameter explaining the intent
- Common queries: "is:spam older_than:7d", "in:inbox is:unread older_than:14d", "category:promotions older_than:30d"
- WARNING: Permanently deletes emails - cannot be recovered
Common Operations:
- Mark as read: modify_email(id, remove_labels="UNREAD")
- Archive: modify_email(id, remove_labels="INBOX")
- Star: modify_email(id, add_labels="STARRED")
- Mark important: modify_email(id, add_labels="IMPORTANT")
FAQ
What does the gmail skill do?
Read, send, draft, delete, and organize Gmail emails
How do I install gmail?
Run npx skills add https://github.com/aws-samples/sample-strands-agent-with-agentcore --skill gmail in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/gmail/ (personal) or .claude/skills/gmail/ (project).
Which AI agents can use gmail?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is gmail safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains gmail?
It is published by aws-samples in aws-samples/sample-strands-agent-with-agentcore. It has 57 recorded installs.
More from aws-samples/sample-strands-agent-with-agentcore
financial-news
aws-samples/sample-strands-agent-with-agentcore
Open the skill to read its SKILL.md instructions.
code-interpreter
aws-samples/sample-strands-agent-with-agentcore
Test and prototype code in a sandboxed environment. Use for debugging, verifying logic, or installing packages.
word-documents
aws-samples/sample-strands-agent-with-agentcore
Open the skill to read its SKILL.md instructions.
google-maps
aws-samples/sample-strands-agent-with-agentcore
Open the skill to read its SKILL.md instructions.
wikipedia-search
aws-samples/sample-strands-agent-with-agentcore
Open the skill to read its SKILL.md instructions.
arxiv-search
aws-samples/sample-strands-agent-with-agentcore
Open the skill to read its SKILL.md instructions.
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。