56 Retargeting Plan Global logo

56 Retargeting Plan Global

Community
minhnv0807
56-retargeting-plan-global

Use when warm audiences need a plan — retargeting tiers by intent and recency, a different message per tier, frequency caps, attribution windows, lookalike seeds, exclusion rules, and a first-party data base that survives iOS ATT and cookie deprecation. Trigger on 'retargeting', 'remarketing', 'warm audience', 'custom audience setup', 'retarget cart abandoners', 'my retargeting pool is too small'. Also use when the user says people visit once and never come back. Not for — cold prospecting audiences, see `51-audience-research-global`; the pixel and events that feed these audiences, see `53-tracking-setup-global`; email win-back flows, see `14-email-marketing-global`; raising budgets, see `55-scaling-ads-global`.

Overview

Publisherminhnv0807
Repositoryai-business-skills
Skill name56-retargeting-plan-global
Stars
612
Forks
228
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by minhnv0807 on GitHub. Read the source before you install it.

Installation

Install the 56 Retargeting Plan Global AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/minhnv0807/ai-business-skills/tree/master/skills/en/56-retargeting-plan-global
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/minhnv0807/ai-business-skills.git /tmp/ai-business-skills
mkdir -p .claude/skills
cp -r /tmp/ai-business-skills/skills/en/56-retargeting-plan-global .claude/skills/56-retargeting-plan-global
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 56 Retargeting Plan Global in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads 56 Retargeting Plan Global on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so 56 Retargeting Plan Global is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Retargeting Plan (Global)

Retargeting is a conversation with people who already know you. The message must differ completely from cold ads: handle objections, do not reintroduce the brand. Never serve the same ad to cold and warm audiences.

Information gathering

Ask up to 4 questions:

  1. Which platforms and which offer are being retargeted? Meta / Google / TikTok / YouTube / Pinterest / email and SMS?
  2. What event data already exists? Video views, page engagement, landing page visits, add to cart, checkout started, form submits, purchases. If none, run 53-tracking-setup-global first and let data accumulate.
  3. How large are the current warm pools, and how large is the first-party list? Pixel audience size plus email/SMS/CRM list size.
  4. Budget, and what is the main objection? Price, trust, timing, or "not now"?

Principles

  1. Message intensity follows audience heat. Hotter audiences get the offer and urgency; cooler audiences get trust and value.
  2. Shorter window means hotter audience means stronger message. Someone who visited yesterday is not someone who watched a video last month.
  3. First-party data is the durable base, not pixel audiences. Post-iOS ATT and with third-party cookies deprecated, pixel-built retargeting pools are materially smaller and decay faster than they used to. Email, SMS, and CRM lists you own do not disappear when a browser changes policy. Build the plan on owned lists and treat pixel audiences as an accelerator.
  4. Always exclude converters. Do not waste impressions on people who already bought, unless there is a genuine upsell.
  5. Frequency caps are mandatory. High-frequency retargeting produces irritation and negative feedback, which raises costs.
  6. Retargeting is 10-20% of budget (repo operating standard is 15%). The pool is finite; volume comes from cold.
  7. Seed quality beats seed size. A lookalike from purchasers beats a lookalike from viewers.
  8. Consent applies to every uploaded list. Custom Audience and Customer Match uploads require documented marketing consent, hashed data, and removal on opt-out — see the consent section in 53-tracking-setup-global.

Workflow

1. Build the durable first-party base first

Before designing pixel tiers, confirm these exist:

AssetWhy it mattersMinimum action
Email list with consentSurvives cookie and ATT changes; usable on every platformCapture email before or during checkout, and on the lead magnet
SMS list with consentHigh-intent channel in US marketsExplicit opt-in with a documented double confirmation where required
CRM with source fieldsConnects retargeting to actual revenueSource, campaign, stage, revenue, opt-out flag
Logged-in or account usersStable identifier across devicesEncourage account creation post-purchase
Server-side event streamRecovers events browsers dropConversions API / Events API (53-tracking-setup-global)

If pixel pools are too small to run, the first-party list is what keeps retargeting alive. Upload it as a Custom Audience and Customer Match list, and run email and SMS flows in parallel through 14-email-marketing-global.

2. Audience tiers

TierAudienceSignalWindowMessage direction
1 (hottest)Add to cart / checkout startedPixel + server event7-14 daysStrong offer, urgency, guarantee
2Lead form opened but not submitted, open sales conversationPixel, CRM3-7 daysReminder, remove the next-step friction
3Landing page visitors who did not convertPixel + server event14-30 daysTrust, social proof, objection handling
4Video viewers above 50%Platform engagement audience14-30 daysDeepen interest, educate, prove
5Page and post engagersPlatform engagement audience30-60 daysSoft offer, value add
6Email / SMS / CRM listFirst-party uploadContinuousNurture through owned channels, ads as reinforcement
7Past customersPurchase event + CRM180 daysUpsell, cross-sell, replenishment, loyalty

Note on durability: tiers 1-5 are pixel-dependent and will be smaller than the platform-reported estimate suggests. Tiers 6 and 7 are the ones you control. If tiers 1-3 are too small to spend the planned budget, merge them into a single hot tier rather than running several starved ad sets.

3. Message framework per tier

  • Tiers 1-2 (about to buy): offer, urgency, guarantee. CTA: "Complete your order", "Finish signing up". Formats: dynamic product ads, countdown, limited availability, abandoned-cart email plus SMS in sequence.
  • Tiers 3-4 (interested): objection handling, social proof, soft CTA. CTA: "See how it works", "Read the reviews". Formats: testimonial video, FAQ, comparison, founder explainer.
  • Tiers 5-6 (aware): value add and soft offer. CTA: "Learn more", "Get the free [resource]". Formats: educational content, case study, newsletter.
  • Tier 7 (existing customers): upsell, cross-sell, replenishment, member-only pricing. CTA: "Your exclusive offer". Formats: bundle, subscription, referral (see 18-referral-program-global).

Message-to-audience map to hand to 05-ad-copy-global:

AudienceCore message
Video viewers 75%Education plus proof
Site visitors, last 3 daysStrong offer plus urgency
Page visitors who did not convertAddress the objection plus scarcity
Open sales conversationPersonal, last chance
Email subscribers, never purchasedFirst-purchase incentive
Past customersUpsell, cross-sell, replenishment

4. Creative formats

  • Dynamic product ads (catalog required): re-show exactly what was viewed.
  • Testimonial and review video: answers "can I trust this".
  • Comparison and FAQ: answers a specific, named objection.
  • Urgency creative: countdown, limited stock — tiers 1-2 only, and only when the scarcity is real.
  • Founder or behind-the-scenes: works well on tiers 4-5 where the barrier is familiarity.

5. Frequency caps

PlatformRecommended cap
Meta2-3 impressions per 7 days (hot tiers may run slightly higher)
TikTok3-4 impressions per 7 days
YouTube2 impressions per day
Any platform, absolute ceiling2-3 impressions per person per day

6. Lookalike and similar audiences

SeedMinimum seed sizeLookalike %PlatformPurpose
Purchasers>= 1001%MetaHighest-quality prospecting
High-value purchasers (top revenue decile)>= 1001-2%MetaValue-based lookalike
Qualified leads>= 5001-3%MetaScale lead generation
Video viewers 75%>= 1000BroadTikTokScale awareness
Email / CRM list>= 3001-5%Meta, Google Customer MatchExtend from owned data

Lookalikes are cold campaigns and sit in the 5% lookalike slice of the 30/50/15/5 split, not in the retargeting budget — but their seeds are produced by this system. Build value-based lookalikes wherever revenue data is available; they consistently beat flat purchaser seeds.

7. Exclusions

  • Existing purchasers (unless a genuine upsell path exists)
  • Submitted leads and closed deals
  • Email and SMS unsubscribes, and anyone who exercised an opt-out right
  • Audiences currently running in prospecting campaigns (exclude in both directions)
  • Cross-tier: hotter tiers excluded from cooler tiers, so each person sits in exactly one tier

Output structure

File name: retargeting-plan-[product]-[YYYYMMDD].md

markdown
# Retargeting Plan — [Product/Campaign]
Platforms: [x] · Budget: [amount] ([%] of total) · Primary window: [days]

## 1. First-party base      [lists owned, size, consent status, growth plan]
## 2. Audience tiers        [tier, audience, signal, window, estimated size]
## 3. Message per tier      [tier -> message -> CTA -> format]
## 4. Creative brief        [what to produce; hand to 05-ad-copy-global]
## 5. Frequency caps        [per platform]
## 6. Lookalike brief       [seed, %, purpose, refresh cadence]
## 7. Exclusion rules       [converters, opt-outs, prospecting overlap, cross-tier]
## 8. Expected KPIs         [retargeting CPA and ROAS, typically 2-3x better than prospecting]

Related skills

  • 51-audience-research-global: defines the original cold/warm/hot tiering.
  • 53-tracking-setup-global: pixel, server-side events, and consent are the raw material for every custom audience.
  • 05-ad-copy-global: writes the copy for each tier's message.
  • 52-account-structure-global: retargeting sits in its own campaign with cross-exclusions.
  • 55-scaling-ads-global: scaling cold grows the warm pool — raise retargeting budget in step.
  • 14-email-marketing-global: the owned-channel half of tiers 6 and 7.
  • 16-marketing-psychology-global: objection handling, social proof, and honest scarcity.

Quality checklist

  • First-party list plan documented before pixel tiers, with consent status per list
  • Only tiers with enough people to actually spend are created; thin tiers merged
  • Each tier has its own message, CTA, and format — no shared creative with cold
  • Windows match audience heat: hotter means shorter window and stronger message
  • Frequency caps stated per platform
  • Lookalike seeds meet minimum size, with value-based seeds used where revenue data exists
  • Exclusions complete: purchasers, closed leads, opt-outs, prospecting overlap, cross-tier
  • Retargeting budget within 10-20% of total (standard 15%)
  • Plan acknowledges pixel pool decay and does not depend on pixel audiences alone

Frequently asked questions

What does the 56 Retargeting Plan Global AI skill do?

Use when warm audiences need a plan — retargeting tiers by intent and recency, a different message per tier, frequency caps, attribution windows, lookalike seeds, exclusion rules, and a first-party data base that survives iOS ATT and cookie deprecation. Trigger on 'retargeting', 'remarketing', 'warm audience', 'custom audience setup', 'retarget cart abandoners', 'my retargeting pool is too small'. Also use when the user says people visit once and never come back. Not for — cold prospecting audiences, see `51-audience-research-global`; the pixel and events that feed these audiences, see `53-...

Why use 56 Retargeting Plan Global on TypingMind?

Because you install it once and use it with any model. 56 Retargeting Plan Global is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install 56 Retargeting Plan Global in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/minhnv0807/ai-business-skills/tree/master/skills/en/56-retargeting-plan-global. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use 56 Retargeting Plan Global?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with 56 Retargeting Plan Global?

As many as you like. As long as a model supports skills, you can use 56 Retargeting Plan Global with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the 56 Retargeting Plan Global AI skill free?

Yes. It is published on GitHub by minhnv0807 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇