chatbot-app/agentcore/skills/gmail/SKILL.md
Read, send, draft, delete, and organize Gmail emails
npx skillsauth add aws-samples/sample-strands-agent-with-agentcore gmailInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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 TRASHsearch_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 resultsread_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 bodydraft_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 Trashbulk_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 deletemodify_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)list_labels first to discover available labels before filtering.from:sender, to:recipient, subject:text, is:unread, has:attachment, after:2024/01/01, before:2024/12/31.get_email_thread to view entire conversation context before replying.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_delete_emails(query, reason) permanently deletes all emails matching a Gmail query. This cannot be undone.
reason parameter explaining the intent.Common queries:
"is:spam older_than:7d""in:inbox is:unread older_than:14d""category:promotions older_than:30d""from:[email protected] older_than:30d"development
Read and write files in the shared session workspace. Use this to access files created by any skill — code-agent outputs, office documents, images, and more. All within the same isolated session.
documentation
Create, modify, and manage Word documents.
documentation
Wikipedia article search and retrieval
development
Search the web using DuckDuckGo for current information, news, and research topics.