Install the "ai-persuasive-email-writer" agent skill from https://github.com/ILoveDotNet/ilovedotnet/tree/main/.github/skills/ai-persuasive-email-writer into .claude/skills/ai-persuasive-email-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-persuasive-email-writer", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add ILoveDotNet/ilovedotnet --skill ai-persuasive-email-writer -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "ai-persuasive-email-writer" agent skill from https://github.com/ILoveDotNet/ilovedotnet/tree/main/.github/skills/ai-persuasive-email-writer into .agents/skills/ai-persuasive-email-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-persuasive-email-writer", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add ILoveDotNet/ilovedotnet --skill ai-persuasive-email-writer -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "ai-persuasive-email-writer" agent skill from https://github.com/ILoveDotNet/ilovedotnet/tree/main/.github/skills/ai-persuasive-email-writer into .cursor/skills/ai-persuasive-email-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-persuasive-email-writer", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add ILoveDotNet/ilovedotnet --skill ai-persuasive-email-writer -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "ai-persuasive-email-writer" agent skill from https://github.com/ILoveDotNet/ilovedotnet/tree/main/.github/skills/ai-persuasive-email-writer into .gemini/skills/ai-persuasive-email-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-persuasive-email-writer", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add ILoveDotNet/ilovedotnet --skill ai-persuasive-email-writer -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "ai-persuasive-email-writer" agent skill from https://github.com/ILoveDotNet/ilovedotnet/tree/main/.github/skills/ai-persuasive-email-writer into .github/skills/ai-persuasive-email-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-persuasive-email-writer", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add ILoveDotNet/ilovedotnet --skill ai-persuasive-email-writer -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "ai-persuasive-email-writer" agent skill from https://github.com/ILoveDotNet/ilovedotnet/tree/main/.github/skills/ai-persuasive-email-writer into .opencode/skills/ai-persuasive-email-writer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-persuasive-email-writer", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
ai-persuasive-email-writer
GitHub stars
155
Token cost
~3k tokens
SKILL.md length
1,423 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
CC0-1.0
At a glance
Craft persuasive, goal-driven emails using AI. An agent skill from ILoveDotNet/ilovedotnet.
Works in 8 steps: Define a Persuasive Email Goal → Map Audience Intent and Context → Structure a Clear Narrative (PAS) → …
Tasks that involve A/B testing
SKILL.md covers Overview, Core Rules, Workflows and Quick-Reference Prompt Cheat…, plus 1 more section
Calls make
What it does
AI Persuasive Email Writer is an agent skill from ILoveDotNet/ilovedotnet. Craft persuasive, goal-driven emails using AI. Covers goal definition, audience research, narrative structure (Problem-Agitate-Solution), tone calibration, subject-line generation, call-to-action sharpening, pre-send draft review, and ethical A/B testing. WHEN: write persuasive email, improve email response rate, fix email tone, generate subject lines, strengthen CTA, review email draft, split-test email campaign, email not getting replies.
Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Marketing & SEO, covering A/B testing, Email writing and Email marketing. The repository describes itself as: I love to teach dotnet concepts in a simple way with real world examples to people who aspire to to be a dotnet developer. I also help developers to refresh their memory with… The licence is CC0-1.0.
When your agent uses it
Tasks that involve A/B testing
Tasks that involve Email writing
Tasks that involve Email marketing
Example prompts
“/ai-persuasive-email-writer”
Workflow steps
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 71752c3. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
make
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
AI Persuasive Email Writer loads about 3k tokens when it runs. Until then it costs about 118 tokens; SKILL.md has 1,423 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~118
When it runs· the whole SKILL.md, loaded when a task matches
~3k
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
This skill turns AI into a co-author for high-converting emails. Every section maps to a
concrete failure mode in business email and provides an AI-assisted workflow to fix it.
Core Rules
Lock in the goal before writing. Know the single action you want the reader to take.
Include that goal explicitly in every AI prompt — without it, AI produces vague output.
One call to action per email. Multiple asks = no ask. If the email cannot be reduced to
one CTA, split it into multiple emails.
Structure before prose. Apply Problem → Agitate → Solution (PAS) before polishing language.
Tone is the reader's mood, not yours. Always request an AI tone audit before sending.
Change one variable at a time. When A/B testing, test subject line OR body OR CTA — never all at once.
If it can't fit PAS, it's too long. Cut until it can.
Workflows
1. Define a Persuasive Email Goal
Before opening any AI tool, answer: "What is the single, specific action I want the reader
to take — and by when?" Then encode that answer directly in the prompt.
Prompt template:
Help me write an email that results in [SPECIFIC ACTION] by [DATE/TIME].
Context: [1–2 sentences of background].
❌ Vague prompt
✅ Goal-driven prompt
Help me write a response.
Help me write a response that secures a 15-minute meeting next Tuesday to discuss the security proposal.
Why it matters: An email that impresses the reader but asks for too much can actually
work against you — the recipient may intend to give it a reply it "deserves", defer it,
and forget. Too many ideas, too many questions, and no clear action means no reply.
2. Map Audience Intent and Context
Persuasion starts with understanding what the reader is dealing with — their struggles,
desires, and fears — before a single word is written.
AI-assisted research prompts:
Summarise this email thread and identify the reader's primary concern and desired outcome:
[PASTE THREAD]
Based on these LinkedIn posts / reviews / competitor messages, what is this person's
biggest frustration and what outcome are they hoping for?
[PASTE CONTENT]
Principle: A single sentence directed at a real pain point outperforms an entire paragraph
of well-crafted pitch. Research first; write second.
Why it matters: Studying negative reviews of competing products is one of the fastest ways
to understand what your audience actually struggles with. When you discover that readers feel
excluded by advice that assumes resources they do not have, addressing that gap directly in
your messaging — before the reader even asks — dramatically increases resonance.
3. Structure a Clear Narrative (PAS)
A wall of text is the fastest way to get an email deleted. Readers are busy — if they cannot
scan the email in 10 seconds and know what you want, they will delete it or defer it until they forget.
Apply Problem → Agitate → Solution:
Section
Purpose
Target length
Problem
Name the exact pain the reader has
1–2 sentences
Agitate
Expand why it matters / what it costs them
1–3 sentences
Solution
Your offer or the single proposed next step
1–2 sentences
Prompt template:
Restructure my email using the Problem-Agitate-Solution format.
Make it scannable in under 10 seconds. Here is the draft:
[PASTE DRAFT]
Diagnostic: If the draft cannot be broken into PAS cleanly, it is too long — cut it down
until it fits. Structure is how you respect the reader's time.
Why it matters: Effort that the audience never receives is wasted effort. Decision-makers
skim first and read only if the opening earns it. If your email's structure does not make the
value and the ask obvious within the first glance, the rest of the content is invisible.
4. Calibrate Tone for Trust and Action
Email strips out body language and voice. The mood you are in when you write is irrelevant —
what matters is the mood the reader is in when they read.
Pre-send tone audit prompts:
Does this email feel [professional / warm / urgent / neutral]?
Flag any sentence that could be read as curt, passive-aggressive, or dismissive.
Rewrite the following so it reads as confident and friendly without being informal:
[PASTE EMAIL]
Is this email positive? Is there anything here that could land badly
if the reader is having a bad day?
[PASTE EMAIL]
Why it matters: The same words read differently depending on the reader's current state.
A terse, upbeat reply written in a relaxed moment can land as cold or hostile to someone
under pressure. The writer's intent is invisible — only what the words convey to the reader matters.
5. Generate Compelling Subject Lines
The subject line is the gatekeeper. If it fails, the email never gets opened — no matter how
good the body is.
Workflow:
Write the email body first.
Ask AI to generate at least 5 subject line options.
Choose the option that is specific, curiosity-driving, and avoids spam triggers.
Choosing from a selection always produces a better result than committing to the first draft.
Prompt template:
Generate 5 subject lines for the email below.
Optimise for maximum open rate. Avoid spam-trigger words.
Keep each under 50 characters where possible.
[PASTE EMAIL BODY]
Subject line checklist:
Specific — not generic ("Following up" fails; "Your 3-min feedback on the Tuesday proposal" works)
Creates curiosity or signals clear, immediate value
Free of spam words: FREE, URGENT, !!!, ALL CAPS
Tone matches the email body
Avoids "Fwd:" / "Re:" prefixes that trigger spam filters
Why it matters: Readers make split-second judgements based on the subject line alone.
A subject that looks automated, spammy, or irrelevant will be deleted before the email is
ever opened — regardless of how important or well-written the body is.
Show full SKILL.md (645 more words)Show less
6. Strengthen Calls to Action
A vague CTA destroys deals that the body already won. "Looking forward to working with you"
tells the reader nothing — they are left waiting while you wait for them.
A strong CTA must answer:
What should the reader do?
When should they do it?
Can it be answered with yes / no or a single action?
CTA checklist:
Specifies exactly one action
Includes a timeline or deadline
Answerable with yes/no or one step
Zero ambiguity about who does what next
❌ Vague CTA
✅ Clear CTA
Looking forward to working with you.
I'll send the invoice by EOD today. Please review the project steps and we'll kick off Monday.
Let me know your thoughts.
Reply with your available slots on Tuesday or Wednesday and I'll book us a 15-minute call.
Prompt template:
Review the call to action in my email. Rewrite it so it:
1. Specifies one clear action
2. Includes a timeline
3. Can be answered with yes/no or a single step
4. Leaves no room for ambiguity about who does what next
[PASTE EMAIL]
Why it matters: When both sides are waiting for the other to act, nothing moves.
A warm, enthusiastic closing message feels good to write but gives the reader no clear
next step — creating confusion that can stall or kill a deal that was already won.
7. Evaluate Drafts with AI Feedback
Familiarity blinds. After staring at your own writing, you stop seeing the problems —
especially cultural, tonal, or assumption-based blind spots.
Pre-send review prompt (run before every high-stakes email):
Review this email for:
1. Any sentence that could be misinterpreted or read negatively
2. Assumptions the reader may not share
3. Tone inconsistencies or cultural blind spots
4. Anything that might cause the reader to hesitate or not reply
[PASTE EMAIL]
Is there anything in this email that could land flat or be misunderstood
by someone from a different cultural or professional background?
[PASTE EMAIL]
Why it matters: Writing styles, humour, and professional norms vary across cultures and
backgrounds. What reads as wit or casual warmth in one context can seem dismissive or sarcastic
in another. Assumptions you do not know you are making are the hardest blind spots to catch —
a fresh AI review surfaces them before the email is sent.
8. Design Ethical A/B Tests
Stop guessing what works. Data beats intuition every time.
Rules:
Test one variable at a time: subject line, opening hook, CTA, or body.
Keep both variants honest — no misleading subject lines or false urgency.
Use results to improve future emails, not to manipulate individuals.
Run the test, measure replies/opens/conversions, adopt the winner.
Test priority order (highest leverage first):
Subject line — gates open rates
Call to action — gates conversions
Opening hook — gates continued reading
Body structure / length
Prompt template:
Write two meaningfully different versions of the [subject line / CTA / opening hook]
for the email below, so I can A/B test which drives more replies.
Keep both honest and on-brand.
[PASTE EMAIL]
Why it matters: Intuition — even experienced intuition — is frequently wrong about what
an audience will respond to. A single test that contradicts your assumption can redirect an
entire strategy. The only way to know what works is to measure it, not guess.
Quick-Reference Prompt Cheat Sheet
Goal
Prompt starter
Write with a specific goal
Write an email that results in [ACTION] by [DATE]
Research the reader
Summarise this thread and identify the reader's primary concern and desired outcome
Restructure for clarity
Rewrite using Problem-Agitate-Solution, scannable in under 10 seconds
Tone audit
Flag sentences that could be read as [curt / passive-aggressive / unclear]
Generate subject lines
Generate 5 subject lines optimised for open rate, free of spam triggers
Sharpen the CTA
Rewrite the CTA so it specifies one action, includes a timeline, and can be answered yes/no
Pre-send blind spot check
Is there anything here that could be misinterpreted or read in a negative way?
A/B variants
Write two meaningfully different versions of [element] so I can split-test them
Common Mistakes to Avoid
Mistake
Fix
Prompting AI with no stated goal
Always include the desired reader action in the prompt
Multiple CTAs in one email
Pick one; save others for follow-up emails
Sending without a tone audit
Always run the pre-send review prompt before high-stakes emails
Committing to the first subject line
Always generate at least 5 options and choose deliberately
Vague timeline in CTA
Use specific dates/times — never "soon" or "when you get a chance"
Testing multiple variables at once
Change exactly one element per test cycle
Writing from your own mood
Write for the reader's mood — run the tone audit
Overly long emails with many ideas
One email = one goal = one CTA; cut everything else
AI Persuasive Email Writer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
AI Persuasive Email Writer compared with similar skills
Skill
Stars
Used in
Tokens
Auto-check
Licence
Repo updated
AI Persuasive Email Writer this skillILoveDotNet/ilovedotnet
A skill your agent uses when the user asks to "write the email", "draft subject lines", or "build email creative"; produces the pre-click unit — subject-line variants + preheader, body copy, one…
A skill your agent uses when warm audiences need a plan — retargeting tiers by intent and recency, a different message per tier, frequency caps, attribution windows, lookalike seeds, exclusion…
Dung khi can xay chuoi email hoac Zalo OA gui theo kich ban — welcome series, nurture, promotion, win-back: phan tep, luong automation, subject line, tan suat gui, A/B test va KPI open/click.
Craft persuasive, goal-driven emails using AI. An agent skill from ILoveDotNet/ilovedotnet. AI Persuasive Email Writer is an agent skill from ILoveDotNet/ilovedotnet. Craft persuasive, goal-driven emails using AI.
When should I use AI Persuasive Email Writer?
AI Persuasive Email Writer fits situations like: tasks that involve A/B testing; tasks that involve Email writing; tasks that involve Email marketing.
How do I install AI Persuasive Email Writer in Claude Code?
Run `npx skills add ILoveDotNet/ilovedotnet --skill ai-persuasive-email-writer -a claude-code`. Or copy the skill folder (.github/skills/ai-persuasive-email-writer in ILoveDotNet/ilovedotnet) into .claude/skills/ai-persuasive-email-writer in your project. Claude Code loads it when a task matches its description.
How do I install AI Persuasive Email Writer in Codex?
Run `npx skills add ILoveDotNet/ilovedotnet --skill ai-persuasive-email-writer -a codex`. Or copy the skill folder (.github/skills/ai-persuasive-email-writer in ILoveDotNet/ilovedotnet) into .agents/skills/ai-persuasive-email-writer in your project. Codex loads it when a task matches its description.
Can I use AI Persuasive Email Writer in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ILoveDotNet/ilovedotnet --skill ai-persuasive-email-writer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-persuasive-email-writer, .gemini/skills/ai-persuasive-email-writer, .github/skills/ai-persuasive-email-writer and .opencode/skills/ai-persuasive-email-writer in your project.
What does AI Persuasive Email Writer need to run?
Going by SKILL.md and its folder, AI Persuasive Email Writer needs the command-line tools its instructions call (make).
Does AI Persuasive Email Writer access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is AI Persuasive Email Writer safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does AI Persuasive Email Writer use?
AI Persuasive Email Writer is published under the CC0-1.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does AI Persuasive Email Writer use?
About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to AI Persuasive Email Writer?
Skills that share tags, products or a category with AI Persuasive Email Writer: Email Creative Builder (aaron-he-zhu/aaron-marketing-skills, 2.9k stars), Marketing Campaign (affaan-m/ECC, 277k stars), Autoresearch (ericosiu/ai-marketing-skills, 3.6k stars) and 56 Retargeting Plan Global (minhnv0807/ai-business-skills, 609 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains AI Persuasive Email Writer?
ILoveDotNet (a GitHub organization) maintains it in ILoveDotNet/ilovedotnet, which has 155 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 6, 2026.
Source: ILoveDotNet/ilovedotnet on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.