beam-ai-team/gmail
skills/integrations/google/gmail/SKILL.md
Read, send, and manage Gmail emails. Load when user mentions 'gmail', 'email', 'send email', 'check email', 'inbox', 'draft', or references sending/reading emails.
testing
Updated May 13, 2026
$ install --global
skillsauthnpx skillsauth add beam-ai-team/beam-next-skills gmailInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 13, 2026, 3:58 AM315.9s2 files scanned
SKILL.md
- name:
- gmail
- type:
- skill
- version:
- 1.3
- description:
- Read, send, and manage Gmail emails. Load when user mentions 'gmail',
- author:
- Fredrik Falk
- category:
- integrations
- platform:
- Google Workspace
- updated:
- 2026-02-24
- visibility:
- public
Purpose
Automate Gmail operations including reading, sending, replying, forwarding, and managing emails. Useful for email automation, inbox management, and communication workflows.
Gmail
Read, send, and manage Gmail via OAuth authentication.
CRITICAL SAFETY RULES
These rules are MANDATORY and must NEVER be bypassed:
1. NEVER Send Without Explicit Approval
- ALWAYS show the user the complete email (to, subject, body) before sending
- ALWAYS ask for explicit confirmation: "Do you want me to send this email? (yes/no)"
- NEVER auto-send emails, even if user says "send an email to X"
- NEVER send multiple emails in a loop without per-email confirmation
2. Draft-First Workflow (DEFAULT BEHAVIOR)
- ALL send/reply/forward operations create a draft FIRST
- User sees the draft and chooses:
yes(send now),no(delete draft), orkeep-draft(review in Gmail) - This ensures user can ALWAYS review in Gmail UI before any email is sent
3. Sensitive Operations Require Confirmation
| Operation | Requires Confirmation | |-----------|----------------------| | Send email | YES - ALWAYS | | Reply to email | YES - ALWAYS | | Forward email | YES - ALWAYS | | Send draft | YES - ALWAYS | | Delete draft | Yes | | Trash email | Yes |
4. Read Operations Are Safe
These do NOT require confirmation:
- List emails, Search emails, Read email content
- List labels, List drafts, Get attachment
Pre-Flight Check (ALWAYS RUN FIRST)
uv run python 00-system/skills/google/google-master/scripts/google_auth.py --check --service gmail
Exit codes:
- 0: Ready to use - proceed with user request
- 1: Need to login - run
python3 00-system/skills/google/google-master/scripts/google_auth.py --login - 2: Missing credentials or dependencies - see ../google-master/references/setup-guide.md
Quick Reference
List Emails
uv run python 00-system/skills/google/gmail/scripts/gmail_operations.py list --max 10
List Unread Emails
uv run python 00-system/skills/google/gmail/scripts/gmail_operations.py list --query "is:unread" --max 10
Search Emails
uv run python 00-system/skills/google/gmail/scripts/gmail_operations.py search "from:[email protected] subject:report"
Read Email
uv run python 00-system/skills/google/gmail/scripts/gmail_operations.py read <message_id>
Send Email
uv run python 00-system/skills/google/gmail/scripts/gmail_operations.py send --to "[email protected]" --subject "Hello" --body "Message body"
Reply to Email
uv run python 00-system/skills/google/gmail/scripts/gmail_operations.py reply <message_id> --body "Reply text"
Forward Email
uv run python 00-system/skills/google/gmail/scripts/gmail_operations.py forward <message_id> --to "[email protected]"
Create Draft
uv run python 00-system/skills/google/gmail/scripts/gmail_operations.py draft --to "[email protected]" --subject "Draft" --body "Content"
List Drafts
uv run python 00-system/skills/google/gmail/scripts/gmail_operations.py drafts
List Labels
uv run python 00-system/skills/google/gmail/scripts/gmail_operations.py labels
Trash/Archive/Mark Read
uv run python 00-system/skills/google/gmail/scripts/gmail_operations.py trash <message_id>
uv run python 00-system/skills/google/gmail/scripts/gmail_operations.py archive <message_id>
uv run python 00-system/skills/google/gmail/scripts/gmail_operations.py mark-read <message_id>
Gmail Search Syntax
| Operator | Example | Description |
|----------|---------|-------------|
| from: | from:[email protected] | Emails from sender |
| to: | to:[email protected] | Emails to recipient |
| subject: | subject:meeting | Subject contains word |
| is:unread | is:unread | Unread emails |
| has:attachment | has:attachment | Has attachments |
| after: | after:2024/01/01 | After date |
| before: | before:2024/12/31 | Before date |
| label: | label:important | Has label |
Error Handling
See ../google-master/references/error-handling.md for common errors and solutions.
Setup
First-time setup: ../google-master/references/setup-guide.md
Quick start:
pip install google-auth google-auth-oauthlib google-api-python-client- Create OAuth credentials in Google Cloud Console (enable Gmail API, choose "Desktop app")
- Add to
.envfile at Beam Next root:GOOGLE_CLIENT_ID=your-client-id.apps.googleusercontent.com GOOGLE_CLIENT_SECRET=your-client-secret GOOGLE_PROJECT_ID=your-project-id - Run
python3 00-system/skills/google/google-master/scripts/google_auth.py --login
Related Skills
beam-ai-team/skills/general/taste-skill
development
VerifiedTrustedCommunity
--- name: taste-skill type: skill version: '1.0' author: Leonxlnx (packaged by Zhichao Li) category: general tags: - frontend - design - anti-slop - landing-page updated: '2026-06-11' visibility: public description: Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check. license: MIT.
SKILL.mdUpdated Jun 12, 2026
beam-ai-team/numbers
development
VerifiedTrustedCommunity
Use when communicating quantitative information in any form — Slack updates, emails, reports, decks, dashboards, landing pages, product UI, public talks. Covers two integrated layers: (1) making numbers semantically meaningful (translation, anchoring, simplification, story-pairing) and (2) showing numbers cleanly (chart vs table vs prose, chart-by-message, pre-attentive emphasis, color discipline, decluttering). Distilled and integrated from *Show Me the Numbers* (Stephen Few) and *Make Numbers Count* (Chip Heath & Karla Starr). Not for raw data analysis or statistics — this is about communication of numbers, not their derivation.
SKILL.mdUpdated Jun 12, 2026
beam-ai-team/impeccable
development
VerifiedTrustedCommunity
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
SKILL.mdUpdated Jun 12, 2026
beam-ai-team/beam-teach
tools
VerifiedTrustedCommunity
Stateful multi-session tutor adapted for Beam — teach a stakeholder to understand, trust, and operate a specific agent, or teach a Solution Engineer a client's business process for delivery. Grounds every lesson in Knowledge Hub sources (real agent graphs, real tasks, transcripts, Linear) before any web resource. Also works for any general topic. Trigger on "teach me", "beam teach", "教我", "onboard <person> on <agent>", "help <stakeholder> understand the agent", "learn this client's process".
SKILL.mdUpdated Jun 12, 2026