Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add shawnpang/startup-founder-skills --skill email-marketinggit clone --depth 1 https://github.com/shawnpang/startup-founder-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/shawnpang/startup-founder-skills/email-marketing)<a href="https://agentmods.dev/skills/shawnpang/startup-founder-skills/email-marketing"><img src="https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/email-marketing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shawnpang/startup-founder-skills/email-marketing"><img src="https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/email-marketing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.01743 |
| Opus 5 | $0.00018 | $0.00872 |
| Sonnet 5 | $0.00007 | $0.00349 |
| Haiku 4.5 | $0.00004 | $0.00174 |
Grade A, and why
email-marketing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- email-marketing — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Email Marketing
When to Use
- Building a welcome sequence for new signups or lead magnet downloads.
- Designing a lead nurture sequence to move prospects toward conversion.
- Creating a re-engagement campaign for inactive users or subscribers.
- Writing an onboarding email series that drives product activation.
- Planning a newsletter cadence and format.
- Optimizing existing sequences for open rate, click rate, or conversion.
Context Required
- From startup-context: product description, ICP, value proposition, tone of voice, current user journey stages, key activation metrics.
- From the user: sequence type needed (welcome, nurture, re-engagement, onboarding, post-purchase, educational), audience context (who they are, what triggered entry, relationship stage), current email list size and segments, existing sequences (if optimizing), email platform in use, primary conversion action, any existing performance data.
Workflow
- Define the sequence goal -- Every sequence gets one job. Map it to a specific outcome:
- Welcome: activate, build trust, convert
- Nurture: educate, build desire, drive trial/demo/purchase
- Re-engagement: reactivate or clean the list
- Onboarding: drive users to key activation milestones (coordinate with in-app messaging -- email supports, does not duplicate)
- Newsletter: maintain top-of-mind, drive traffic, build relationship
- Map the sequence arc -- Plan the emotional and logical progression across emails:
- Welcome (5-7 emails, 12-14 days): Deliver value and quick win, origin story/connection, educational content on their pain, social proof/case study, address #1 objection, feature highlight, conversion ask with reason to act now.
- Lead nurture (6-8 emails, 2-3 weeks): Lead magnet delivery, topic expansion, problem deepening, solution framework, case study, differentiation, objection handling, direct offer.
- Re-engagement (3-4 emails, 2 weeks, triggered at 30-60 days inactivity): Check-in, value reminder, incentive, last chance and list cleanup.
- Onboarding (5-7 emails, 14 days): Activate, guide to aha moment, feature education, milestone celebration, upgrade prompt.
- Write each email using One Email, One Job -- Each email has one primary message and one call to action. No competing CTAs, no kitchen-sink emails.
- Apply the email copy structure:
- Hook (first 1-2 lines): Open with a question, surprising fact, or relatable scenario. This determines whether they keep reading.
- Context (2-3 lines): Bridge from hook to value. Why does this matter to them right now?
- Value (body): Deliver the insight, story, resource, or proof.
- CTA (final 1-2 lines): Clear, specific, single action. Button for transactional CTAs, text link for content CTAs.
- Formatting: Short paragraphs (1-3 sentences), generous whitespace, bullet points where helpful, mobile-first. Conversational tone, active voice.
- Optimize subject lines -- Write 3 variants per email:
- Keep under 40-60 characters for mobile
- Patterns: questions, how-tos, numbers, direct statements, story teases
- Clear beats clever, specific beats vague
- Avoid spam triggers (ALL CAPS, excessive punctuation, "free")
- Preview text (90-140 characters) is the second subject line -- write it deliberately, do not repeat the subject
- Set timing and triggers -- Welcome email sends immediately. Early sequence emails 1-2 days apart. Nurture phase 2-4 days apart. Long-term weekly or bi-weekly. Define behavior-triggered branching where relevant.
- Plan measurement -- Define success metrics per email: open rate, click rate, reply rate, conversion rate. B2B SaaS benchmarks: 25-35% open, 3-5% click, 1-3% conversion.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 83 lines · 37 tokens per session scan A c3769fe79383
email-marketing is a skill published in the GitHub repository shawnpang/startup-founder-skills (321 stars, last pushed 6mo ago), licensed MIT. It adds 37 tokens to every session and 1,743 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…