Atlas / Skills / mohitagw15856 / Email Campaign

Email CampaignCAUTION

skills/mohitagw15856/email-campaign

1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in Anthropic's plugin directory. Plus a typed decision layer: which skill, is it safe, ship or slip. Free in-browser or npx pm-

Verdict
CAUTION
Grade
B
Trust score
89 /100
Version
—
Hosts
—
License
MIT
Stars
1,438
01

Overview

1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in Anthropic's plugin directory. Plus a typed decision layer: which skill, is it safe, ship or slip. Free in-browser or npx pm-

Read from source at commit 8d32d25aa3f5OBSERVED · 2026-10-12
02

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: email-campaign
description: "Write and sequence multi-email nurture or launch campaigns. Use when asked for an email sequence, drip campaign, onboarding emails, product launch emails, or nurture flow. Produces subject lines, preview text, full email body, and send-timing recommendations for each email in the sequence."
---

# Email Campaign Skill

This skill writes complete, sequenced email campaigns — from welcome flows to product launches to re-engagement sequences. Each email is written with subject line, preview text, full body copy, and CTA.

## Required Inputs

Work from what is given. If any of these is missing, still produce the complete output: fill each gap with a reasonable assumption marked *(assumed, confirm)* and list those assumptions at the end. Ask a question first only when the core subject itself is missing (there is nothing to write about).
- **Campaign goal** (onboard new users / launch a product / nurture leads / re-engage churned users / announce a feature)
- **Audience** (who receives this? job title, lifecycle stage, what they know already)
- **Product or offer** being promoted or introduced
- **Number of emails in sequence** (if unsure, recommend based on goal)
- **Tone** (professional / conversational / bold / educational)
- **Sender name** (person or brand?)

## Sequence Recommendations by Goal

If the user hasn't specified number of emails, use these defaults:
- **Onboarding:** 4 emails over 7 days (Day 0, Day 1, Day 3, Day 7)
- **Product launch:** 3 emails (Teaser → Launch Day → Follow-up/Last chance)
- **Lead nurture:** 5 emails over 2 weeks
- **Re-engagement:** 3 emails (Gentle nudge → Value reminder → Final offer)
- **Feature announcement:** 2 emails (Announcement → How-to/deep dive)

## Output Structure Per Email

For every email in the sequence, produce:

---

**Email [N] of [Total] — [Descriptive label e.g. "Welcome / Day 0"]**
**Send timing:** [When relative to trigger event or previous email]

**Subject line:** [Primary option]
**Subject line (A/B variant):** [Alternative to test]
**Preview text:** [40–90 characters — adds context to the subject, doesn't repeat it]

**Body:**

[Full email copy — formatted with clear opening line, 2–3 body paragraphs, one primary CTA]

**CTA button text:** [3–6 words]
**CTA destination:** [What page/action this should link to]

**Strategic note:** [Why this email does what it does — the psychological or strategic intent. 1–2 sentences.]

---

## Writing Rules

- Opening line must earn attention — no "Hi, welcome to [product]" openers
- Each email has ONE primary CTA — never two competing asks
- Keep paragraphs to 2–3 sentences maximum for mobile readability
- Use "you" more than "we" — centre the reader, not the brand
- Subject lines under 50 characters perform best on mobile — flag if going over
- Preview text should add information the subject doesn't — never just repeat it
- Every email should stand alone — assume some subscribers miss earlier emails

## Quality Checks

- [ ] Each email has a single clear CTA
- [ ] Subject lines are under 50 characters (or flagged)
- [ ] Preview text doesn't repeat the subject line
- [ ] Opening line is specific and attention-earning
- [ ] Sequence has logical narrative arc (doesn't feel like disconnected blasts)
- [ ] Tone is consistent across all emails
- [ ] Strategic notes explain the intent of each email

## Anti-Patterns

- [ ] Do not include more than one primary CTA per email — competing calls to action reduce click-through by splitting attention
- [ ] Do not open with "Hi, welcome to [product]" or any variation of a generic greeting — the opening line must earn attention immediately or recipients stop reading
- [ ] Do not write preview text that repeats the subject line — preview text is a second chance to earn the open, not a repeat of the first chance
- [ ] Do not write a sequence where each email restates the same value proposition — each email must advance the narrative or serve a distinct purpose in the buyer's journey
- [ ] Do not assume all subscribers receive all emails — each email must stand alone for subscribers who missed earlier messages in the sequence

## Example Trigger Phrases

- "Write a 3-email launch sequence for [product]"
- "Build an onboarding email flow for [SaaS tool]"
- "Create a drip campaign to nurture leads for [offer]"
- "Write a re-engagement campaign for churned users"
03

Trust audit

CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.

LayerWhat it checksResult
L0Provenance & inventoryWARN
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (5)

MEDIUMInventory / provenance · inv.symlink · CWE-1104
templates/pm-discovery-agent/skills/assumption-mapper/SKILL.md
templates/pm-discovery-agent/skills/assumption-mapper/SKILL.md
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
templates/pm-discovery-agent/skills/discovery-interview-guide/SKILL.md
templates/pm-discovery-agent/skills/discovery-interview-guide/SKILL.md
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
templates/pm-discovery-agent/skills/job-story-mapper/SKILL.md
templates/pm-discovery-agent/skills/job-story-mapper/SKILL.md
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
templates/pm-discovery-agent/skills/user-interview-synthesis/SKILL.md
templates/pm-discovery-agent/skills/user-interview-synthesis/SKILL.md
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
templates/pm-launch-agent/skills/content-calendar/SKILL.md
templates/pm-launch-agent/skills/content-calendar/SKILL.md
Why it matters. link not followed

Gates applied: no_behavioural_pass.

Audited 2026-10-12 · audit v0.4.1 · source sha 8d32d25aa3f5full audit observations/trust-audit/skill/mohitagw15856__email-campaign.json · Report an issue / request a re-scan
04

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-128d32d25aa3f5CAUTIONB89first audit
05

Questions

What does the Email Campaign skill do?

1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in Anthropic's plugin directory. Plus a typed decision layer: which skill, is it safe, ship or slip. Free in-browser or npx pm-

Is Email Campaign safe to install?

With care. The audit graded it B (89/100) and found 5 things worth knowing before you trust this skill, listed below with the exact line each was found on.

What can Email Campaign access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

How current is this page?

The grade is for one exact copy of the source (8d32d25aa3f5), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement