claude-email
CLAUDE.md117 starsChanged 8 months agoMITView on GitHub
This repository contains Claude Email, a Tier 4 Claude Code skill for inbox management, email composition, quality review, deliverability auditing, automation sequences, and email marketing strategy. It follows the Agent Skills open standard and the 3-layer architecture (directive, orchestration, execution).
In this repositoryOne other file it gives its agents.
- emailSkill
The file
We split this CLAUDE.md into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 57
Test with python scripts/check_deliverability.py <domain> --json after changes
- Very specific: line 58
Keep SKILL.md files under 500 lines / 5000 tokens
- Distinctive: line 61
Follow kebab-case naming for all skill directories
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Claude Email — Comprehensive Email Management & Marketing
Project Overview
This repository contains Claude Email, a Tier 4 Claude Code skill for inbox management, email composition, quality review, deliverability auditing, automation sequences, and email marketing strategy. It follows the Agent Skills open standard and the 3-layer architecture (directive, orchestration, execution).
Architecture
claude-email/
CLAUDE.md # This file (project instructions)
email/ # Main orchestrator skill (Tier 4)
SKILL.md # Entry point, routing table, user profile, quality gates
references/ # On-demand knowledge files (6 files)
deliverability-rules.md # SPF/DKIM/DMARC thresholds, bulk sender requirements
benchmarks.md # KPI benchmarks by industry, scoring tables
compliance.md # CAN-SPAM, GDPR, CCPA, RFC 8058
copy-frameworks.md # PAS, AIDA, BAB, FAB, 4Ps frameworks
technical-standards.md # HTML email rendering, dark mode, responsive
mcp-integration.md # Setup guides for Gmail, Outlook, SendGrid, etc.
skills/ # Sub-skills
email-check/SKILL.md # Inbox triage, categorization, reply suggestions
email-write/SKILL.md # Email composition with frameworks and templates
email-review/SKILL.md # Pre-send quality scoring (0-100)
email-audit/SKILL.md # Domain deliverability audit (SPF/DKIM/DMARC)
email-sequence/SKILL.md # Automation sequence designer
email-plan/SKILL.md # Email marketing strategy with industry templates
assets/ # Industry templates (local-business, saas, ecommerce, etc.)
agents/ # Subagent definitions
email-deliverability.md # Deliverability analysis agent
email-compliance.md # Compliance checking agent
email-content.md # Copy quality scoring agent
email-inbox.md # Inbox categorization agent
scripts/ # Python execution scripts
check_deliverability.py # SPF/DKIM/DMARC checks via checkdmarc + dig
analyze_email_html.py # HTML email validation
score_subject_line.py # Subject line scoring algorithm
hooks/ # Quality gate hooks
pre-send-check.sh # Pre-send quality gate
validate-email-html.py # Post-edit HTML validation
install.sh # Installation scriptKey Principles
- User Profile System: First-run onboarding generates email-profile.md for personalized behavior
- MCP-First: Integrates with Gmail/Outlook MCP for live inbox access
- Progressive Disclosure: Metadata always loaded, instructions on activation, references on demand
- Quality Gates: Score emails 0-100 before sending, audit domains before campaigns
- Industry Adaptation: Templates and recommendations adapt to business type
Development Rules
- Test with
python scripts/check_deliverability.py <domain> --jsonafter changes - Keep SKILL.md files under 500 lines / 5000 tokens
- Reference files should be focused and under 200 lines
- Scripts must have docstrings, CLI interface, JSON output
- Follow kebab-case naming for all skill directories
Commands
| Command | Purpose |
/email | Interactive mode with inbox summary or menu |
/email check | Inbox triage and reply suggestions |
/email write | Compose emails with frameworks |
/email review | Pre-send quality scoring |
/email audit <domain> | Deliverability and compliance audit |
/email sequence <type> | Design automation sequences |
/email plan <business> | Email marketing strategy |
MCP Dependencies
- Required: Gmail MCP (taylorwilsdon/google_workspace_mcp)
- Optional: Microsoft 365, SendGrid, Mailchimp, Kit.com
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.