What does this skill do, and when should you use it?
This is a sub-skill of the AI Marketing Suite for Claude Code, triggered by /market emails <topic/url>. It first gathers business context (by fetching a site or asking questions), then recommends at least two of seven sequence types: welcome, nurture, launch, re-engagement, onboarding, cart abandonment, and cold outreach. Every email follows proven frameworks like 'one email, one job,' with subject-line formulas, send-timing tables, A/B testing priorities, and industry open/click benchmarks. Output lands in a paste-ready EMAIL-SEQUENCES.md file plus a compliance checklist covering CAN-SPAM, GDPR, and CASL.
Reads a topic or fetches a URL to understand the business, audience, pricing, and voice; selects at least two sequence types from seven; writes full email bodies with subject-line A/B variants and preview text using frameworks (value-before-ask, story-driven, problem-agitate-solution); produces day-by-day cadence tables, segmentation strategies, prioritized A/B test plans, and per-industry open/click/conversion benchmarks; writes everything to EMAIL-SEQUENCES.md and prints a terminal summary. It cross-references sibling artifacts (BRAND-VOICE.md, FUNNEL-ANALYSIS.md, COPY-SUGGESTIONS.md, MARKETING-AUDIT.md) when they exist to stay on-brand and funnel-aligned.
- An indie founder launching a product: an 8-12 email launch sequence with open-cart, reminder, and close-cart cadence
- An e-commerce seller recovering abandoned carts: 1-hour/24-hour/72-hour reminder emails with objection handling and timed discounts
- A B2B founder doing cold outreach: a 3-5 email sequence with follow-ups and breakup templates
- A SaaS team activating trial users: a 5-7 email onboarding sequence to drive activation and cut churn
- An agency delivering to clients: a full email marketing plan with benchmark metrics generated from the client's URL
How do you install this skill?
- Static review only; actual quality of generated emails is unverified.
- Industry benchmark figures (open/click rates) are unsourced and should not be treated as reliable promises.
- Compliance guidance covers CAN-SPAM/GDPR/CASL only; other jurisdictions require separate legal review.
- URL fetching has no explicit confirmation step; be aware of data flow when targeting third-party sites.
- Publisher identity unverified; maintenance and update path unclear.
- Network access
- Local filesystem
Install the whole suite: curl -fsSL https://raw.githubusercontent.com/zubair-trabzada/ai-marketing-claude/main/install.sh | bash, or git clone the repo and run ./install.sh. This skill lives at skills/market-emails/. The repo does not document standalone installation of a single sub-skill.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/zubair-trabzada/ai-marketing-claude.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/market-emails" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
In Claude Code, run /market emails <topic/url>. With a URL it fetches the site to understand the business; with a topic it may ask clarifying questions. Optional PDF report support across the suite requires pip install reportlab (not used by this email skill itself).
What are this skill's strengths and limitations?
- Covers seven sequence types, each with specific email counts, day-by-day cadence, and full templates
- Includes actionable detail: subject-line formulas, send-time benchmarks, prioritized A/B testing order
- Built-in CAN-SPAM, GDPR, and CASL compliance checklist required in every output
- Cross-references sibling skills (brand voice, funnel, copy) so outputs stay consistent across the suite
- It is a prompt-instruction file only — no scripts, no test suite, no automated verification; output quality depends entirely on model execution
- Industry benchmarks are generalized numbers with no cited sources or methodology
- Depends on the suite's /market command routing; using it outside Claude Code requires reworking the trigger
- Does not integrate with any email service provider — pasting into an ESP and setting up automation is manual
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Email Sequence Generation (Market Emails) this page | 49 · Use with care | ★ 2.8k | 7mo ago | MIT |
| Email Marketing Bible | 60 · Recommended | ★ 342 | 12d ago | MIT |
| Email Experiment Designer | 56 · Use with care | ★ 3k | 11d ago | Apache-2.0 |
| AI Marketing Suite Orchestrator (market) | 48 · Use with care | ★ 2.8k | 7mo ago | MIT |
| Landing Page CRO Analysis Skill | 49 · Use with care | ★ 2.8k | 7mo ago | MIT |
How did FollowSkills review this skill?
Pure prompt-based skill with no scripts or code; narrow permission surface and mostly transparent data flow (URL fetch, writes EMAIL-SEQUENCES.md). Deducted for: URL fetching without an explicit user-confirmation step, no rollback guidance, unverified publisher identity, and attribution resting solely on the repository.
Instructions are self-consistent with clear trigger, phased structure and output format; can fall back to clarifying questions. Deducted for: no tests, no abnormal-input handling, no failure-feedback guidance if URL fetching fails — plausible happy path with thin edge handling (static cap 10).
Trigger (/market emails <topic/url>), seven sequence types with use cases, and I/O definitions are clear; cross-skill integration conditions explicit. Deducted for: no declared non-fit boundaries, no Chinese-language support, send-time and compliance guidance skewed to US/EU/Canada markets, limited fit for mainland-China users.
Well-layered document (phases-frameworks-templates-output), clear MIT license, install/uninstall paths exist. Deducted for: no per-skill version or changelog, no FAQ or known-limitations section, unclear maintenance responsibility and update path, uncited benchmark data.
Output template is complete and paste-ready for an ESP, with compliance checklist and benchmarks; claimed marginal value is concrete. Deducted for: generation quality unverifiable in static review, industry benchmark numbers unsourced, expected open/click-rate promises potentially misleading (static cap 7).
Only author-authored methodology claims; no tests, no third-party execution evidence, no cross-source corroboration; benchmark figures not traceable (static cap 5).
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →