tools/google-workspace/SKILL.md
Connect to Gmail and Google Calendar via OAuth 2.0. Use when users want to search/read emails, create drafts, search calendar events, check availability, or schedule meetings. Triggers on queries about email, inbox, calendar, schedule, or meetings.
npx skillsauth add letta-ai/skills google-workspaceInstall 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.
Gmail and Google Calendar access via shared OAuth 2.0 authentication.
credentials.json) downloadedgoogle-api-python-client, google-auth-httplib2, google-auth-oauthlibhttps://www.googleapis.com/auth/gmail.readonlyhttps://www.googleapis.com/auth/gmail.composehttps://www.googleapis.com/auth/gmail.modifyhttps://www.googleapis.com/auth/calendar.readonlyhttps://www.googleapis.com/auth/calendar.eventscredentials.jsonuv add google-api-python-client google-auth-httplib2 google-auth-oauthlib
Run any script - it will open a browser for OAuth consent. A token.json is saved for future use.
uv run python tools/google-workspace/scripts/search_emails.py "from:[email protected]" --credentials ./credentials.json
uv run python tools/google-workspace/scripts/read_email.py <message_id> --credentials ./credentials.json
uv run python tools/google-workspace/scripts/create_draft.py \
--to "[email protected]" \
--subject "Subject line" \
--body "Email body" \
--credentials ./credentials.json
uv run python tools/google-workspace/scripts/needs_reply.py --credentials ./credentials.json
uv run python tools/google-workspace/scripts/list_calendars.py --credentials ./credentials.json
# Search by text
uv run python tools/google-workspace/scripts/search_events.py "meeting" --credentials ./credentials.json
# Search by date range
uv run python tools/google-workspace/scripts/search_events.py --start "2024-01-15" --end "2024-01-20" --credentials ./credentials.json
uv run python tools/google-workspace/scripts/find_busy.py \
--start "2024-01-15T09:00:00" \
--end "2024-01-15T17:00:00" \
--credentials ./credentials.json
uv run python tools/google-workspace/scripts/create_event.py \
--summary "Team Meeting" \
--start "2024-01-15T10:00:00" \
--end "2024-01-15T11:00:00" \
--attendees "[email protected],[email protected]" \
--credentials ./credentials.json
Options: --description, --location, --timezone, --calendar
Gmail:
gmail_auth.py - Gmail authentication utilitiessearch_emails.py - Search inbox with Gmail query syntaxread_email.py - Read email content by message IDcreate_draft.py - Create draft emailsneeds_reply.py - Find emails awaiting responseCalendar:
calendar_auth.py - Calendar authentication utilitieslist_calendars.py - List accessible calendarssearch_events.py - Search events by text/datefind_busy.py - Check free/busy periodscreate_event.py - Create calendar eventssearch_events.py --start ... --end ...create_event.py --summary "..." --start ... --end ...needs_reply.pyread_email.py <id>create_draft.py --to ... --subject "Re: ..."testing
Navigates archived ChatGPT or Claude-style conversation exports and a MemFS reference archive on demand. Use when recalling what a past assistant knew, searching old conversations, rendering specific chats, seeding reference memory from export sidecars, or mining historical context without doing a full import.
testing
Migrates deprecated Letta Filesystem folders/files to MemFS using markdown document corpora, chunking, local lexical search, and QMD semantic search via the memfs-search skill. Use when replacing folders.files.upload, working with PDFs or document QA, or emulating open_file, grep_file, and search_file behavior.
data-ai
Configures Letta agent compaction settings and custom summarization prompts. Use when a user asks to change an agent's compaction prompt, improve summaries after context eviction, tune sliding-window or all-message compaction, or design companion/coding-agent continuity summaries.
development
Semantic search over agent memory files. Use when you need to find conceptually related memory blocks, discover forgotten reference files, check what you already know before creating new memory, or search beyond exact keyword matching. Currently supports QMD (local, no API keys).