---
title: Retargeting Funnel Skill for Claude Code
canonical: https://skillselion.com/skills/mbfinotti/advertising-skills/retargeting-funnel
content_type: text/markdown
description: "retargeting-funnel by mbfinotti - This skill designs a multi-stage retargeting sequence from a site's own funnel data."
---

# Retargeting Funnel Skill

Title: Retargeting Funnel Skill for Claude Code

> retargeting-funnel by mbfinotti - This skill designs a multi-stage retargeting sequence from a site's own funnel data.

Canonical: https://skillselion.com/skills/mbfinotti/advertising-skills/retargeting-funnel

This skill designs a multi-stage retargeting sequence from a site's own funnel data. It sets recency windows and behavior depth tiers per stage, a message and offer ladder, exclusive audiences and frequency caps. A solo founder reaches for it when visitors leave without buying and need a planned sequence to come back.

## Key facts

- Installs: 26,684
- GitHub stars: 2
- Author: mbfinotti
- Repository: mbfinotti/advertising-skills
- Install command: `npx skills add https://github.com/mbfinotti/advertising-skills --skill retargeting-funnel`
- Last updated: October 26, 2026

## What Retargeting Funnel does

Designs a multi-stage retargeting sequence from a site's funnel data, with recency windows, message ladders and frequency caps.

Retargeting shows the same ad to everyone for too long.

A staged sequence with caps and exclusions.

Best for: Founders with traffic that leaves without converting.

Not for: Sites with too little traffic to fill retargeting pools.

- Recency windows and depth tiers per stage
- Message and offer ladder for each stage
- Frequency caps and mutually exclusive audiences

## SKILL.md

## Retargeting Funnel

Design a multi-stage retargeting sequence from the client's own conversion data: stage boundaries, per-stage message intent, exclusion logic, frequency caps, and a measurement plan.

### Scope and handoffs

This skill decides stage boundaries, per-stage message intent, exclusion logic, caps, and the measurement plan. It does not build campaigns inside any ad platform, and it hands off neighbouring work:

- Working event tracking is a hard prerequisite - retargeting audiences cannot be built without it. Verify first via `mbfinotti/advertising-skills@ad-conversion-tracking`.
- The broader targeting plan across interest/lookalike/retargeting layers → `mbfinotti/advertising-skills@ad-audience-targeting`.
- Ongoing creative-decay monitoring after launch → `mbfinotti/advertising-skills@ad-creative-fatigue`.
- Writing the per-stage ads themselves → `mbfinotti/advertising-skills@ad-copy-variants` and `mbfinotti/advertising-skills@ad-creative-brief`.
- Splitting the total budget across campaigns and channels → `mbfinotti/advertising-skills@ad-spend-allocation`.

If you draft any customer-facing copy while illustrating a stage, route it through your preferred humanizer skill before the user ships it - this is not a copywriting skill.

### Interview

Ask these questions one at a time, multiple-choice where possible. Stop asking as soon as you have enough to design; do not batch all of them into one wall of questions.

1. Business model: (a) B2C / e-commerce, (b) B2B, (c) hybrid (e.g. PLG SaaS with self-serve and sales-assisted tiers)?
2. Typical time from first visit to conversion: (a) under 3 days, (b) 3-14 days, (c) 2-8 weeks, (d) 2 months or more, (e) unknown?
3. Monthly site traffic and monthly conversions, roughly? (Order of magnitude is enough.)
4. Which behavioural events are actually tracked today: page views only, product/feature views, pricing views, cart or checkout starts, trial starts, purchases, CRM stages?
5. Which paid channels are in use or planned?
6. Offer type: (a) transactional purchase, (b) free trial, (c) demo request, (d) lead form / gated content?
7. Is a discount ever available as an incentive? (Many B2B businesses: no - that removes a rung of the ladder, not the ladder.)
8. Total monthly paid budget and the current prospecting-vs-retargeting split, if one exists?
9. Does a converter-suppression / exclusion audience already exist on any channel?
10. By what date must this be live and producing, and is that date hard? (The creative ladder in step 5 spans near-zero to a quarter in time-to-effect, so its ordering cannot be picked without this.)
11. Do you want the fastest revenue available this quarter, or durable assets that keep paying - a proof library, an incrementality baseline? (The first favours the cheap rungs, the second the slow ones.)
12. Effort ceiling: who can produce creative and how often, and can you actually obtain customer consent and legal sign-off? (A "no" removes the top rungs of the ladder rather than delaying them.)

Refuse to invent stage boundaries without time-lag data. If the user answered "unknown" to question 2, say explicitly: "I will not guess your windows - either export a time-to-conversion report, or I will use <named proxy> and flag every boundary as provisional." Acceptable proxies - always named as a proxy in the output, never silently substituted for real data:

- Ranked by evidence bought per unit of effort: analytics lag report > CRM sales-cycle export > sector-typical figure for the vertical.
- effort (heaviest first): CRM export (an hour, plus whoever owns the CRM) > analytics export (an hour, self-serve) > sector figure (near-zero, one search).
- The cheapest proxy is also the weakest. The CRM export overtakes the analytics one only when the cycle outruns what the pixel can see (B2B, multi-month).
- This is a default, not a law - re-rank against what the user already holds. A lag report exported last month beats a better one nobody will pull.

### Workflow

#### 1. Pull the funnel data

Gather these, in order:

1. Traffic by page type (content / product or feature / pricing / cart or signup)
2. Conversion rate by funnel stage
3. The time-to-conversion lag distribution
4. The main drop-off points
5. The abandonment rate at the deepest pre-conversion step

If your harness can read files, ask the user to export these reports and drop them where you can read them; otherwise ask them to paste the key numbers. If you can browse the web, you may fetch published benchmarks to sanity-check their figures - but the client's own numbers always win over benchmarks.

#### 2. Set stage boundaries from converter recency percentiles

This is the core move: derive windows from the client's own converters, not from platform defaults. From the lag distribution, find the recency point by which roughly 80% of converters had converted - that is the edge of the hot window. Then:

- If 80%+ convert inside 7 days, collapse to fewer stages (often just hot / warm / win-back). More stages than the cycle supports produces empty stages.
- If the cycle runs 60-90 days (typical B2B, high-ticket), stretch every window and plan for list-based rather than pixel-based membership at the long end, since browser privacy limits make long cookie windows unreliable.
- Default retention windows on ad platforms are arbitrary relative to any specific business. A default-length window on a 90-day cycle silently drops most of the pipeline; the same default on a 2-day impulse cycle wastes weeks of spend on cold traffic.

#### 3. Build the two-axis grid: recency × behavioural depth

Cross the recency windows with the behavioural-depth axis. Claim grid cells deepest first, in this order:

cart, checkout or trial start > pricing page viewer > product or feature page viewer > any visitor / content viewer

Past customer and churned customer sit outside the conversion ladder, as win-back tiers. Assign windows inversely to depth: deep actions get short windows (intent decays fast), shallow actions get long windows (they were never hot, so staleness costs less). Not every grid cell becomes a stage - take the 3-5 deepest cells where the client has volume and a distinct message.

That order is value, not effort: every tier costs the same to build - one audience definition, minutes - so nothing separates them but the intent they capture. Effort splits them only where the event is not tracked yet (question 4): an untracked depth signal costs an engineering ticket and a wait, which can drop it below a shallower tier for this quarter. Re-rank on what the account already owns - a CRM deal stage already synced outranks a pricing-view pixel that needs a sprint.

#### 4. Size-check every stage after exclusions

Check each stage against the platform's documented minimum audience size, measured **after** the exclusions from step 6 are applied - a stage that clears the floor before exclusions can fall under it once fresher stages and converters are carved out. Current floors and retention ceilings are in [references/platform-constraints.md](references/platform-constraints.md); verify against official documentation before building, because these values change often.

Collapse rule: if a stage cannot clear its floor after exclusions, repair it in this order:

widen the window > broaden the trigger > merge adjacent stages > collapse to one combined warm pool

All four cost minutes in the audience builder, so effort does not separate them. The ordering is value: what each step spends is message distinctness (widening keeps the stage's job intact, merging fuses two jobs into one, the single pool gives up sequencing entirely).

Never ship a stage that will not deliver - an under-floor stage either serves nothing or serves at punitive CPMs while the learning phase never exits. Thin-traffic sites often end with two stages, or one (see the Ben Heath position below); that is a correct output, not a failure.

#### 5. Assign message intent and offer per stage

Each stage gets a distinct job, not a louder version of the previous ad. Re-showing the identical offer harder is the weakest stage design - if they saw it and did not act, either the offer or the angle was wrong, so change one of the two.

One menu of rungs, in build order: what each buys per unit of effort to produce it. Build top-down and fill the stages with whatever is ready.

Slot is separate information: where a built rung sits in the funnel sequence, not when to make it.

- B2C slot order: reminder, social proof, objection, incentive.
- B2B slot order: proof, objection, ROI, ask. B2B has no discount rung. Its incentive equivalent is a lower-friction ask, such as an assessment, an audit, or a tailored demo.

| Rung (build order)                                                                    | Slot                      | What it buys                                                        | Effort to produce                                                                     | Compliance cost                                                                        |
| ------------------------------------------------------------------------------------- | ------------------------- | ------------------------------------------------------------------- | ------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- |
| Objection handling - shipping, returns, guarantee; security, integrations, comparison | B2C 3rd / B2B 2nd         | Removes the stated blocker; the only rung that answers a known "no" | An hour - the policy facts already exist in writing                                   | A claims check against the published policy; fully reversible                          |
| Reminder / dynamic item ad                                                            | B2C 1st                   | Re-presents the exact item; converts the almost-decided             | Near-zero - the catalogue writes it                                                   | Catalogue accuracy, on the consent basis the pixel already needs                       |
| Direct ask - demo, trial, assessment, audit                                           | B2B 4th                   | Converts intent already present; buys no new belief                 | Near-zero                                                                             | None beyond standard ad review                                                         |
| ROI or comparison content                                                             | B2B 3rd                   | Arms the internal champion for a committee decision                 | A week - data pull, sometimes customer interviews                                     | Claim substantiation, and legal review where naming a competitor is restricted         |
| Social proof - reviews, UGC                                                           | B2C 2nd                   | Borrowed credibility at scale; strongest on unfamiliar brands       | A week - sourcing reviews or creators                                                 | Creator usage rights, testimonial and paid-partnership disclosure                      |
| Named-customer proof - case study, named results                                      | B2B 1st                   | The strongest evidence available; unlocks committee trust           | A quarter - customer consent, legal sign-off, political capital with the account team | Written approval per use and logo rights, revocable by the customer                    |
| Discount + urgency                                                                    | B2C 4th, final stage only | Buys the last conversion, and only the last                         | Near-zero to make; spends margin every time it runs                                   | Promotion terms, price-display rules in some markets, urgency claims that must be true |

- efficiency (build first) = the row order above.
- value (strongest first): named-customer proof > social proof > ROI content > objection handling > discount > reminder > direct ask - near enough the reverse of effort at the top of the table, which is why the axes are split instead of blended.
- compliance cost (heaviest first): named-customer proof > social proof > discount > ROI content > objection handling > reminder == direct ask. That last tie is a real equality at the floor of the axis: both run on material the advertiser already publishes, neither makes a new claim nor uses anyone else's likeness, so neither needs more than the standard ad review every rung gets.

The discount is the one rung whose real cost is not production:

- It spends margin every time it runs.
- It trains deliberate abandonment: people park carts to farm the coupon.
- It is the hardest thing here to withdraw once the market has learned it.

That is why it ranks last despite costing nothing to make, and why it runs on the final stage only. If no discount exists (question 7), the final rung is the hardest direct ask instead.

The order is a default for a team starting from nothing. It moves with context and with who executes it.

Re-rank against questions 10-12, and name which answer moved which rung:

- A hard near-term date promotes objection handling and the reminder.
- A durable-asset mandate promotes named-customer proof and social proof.
- No route to legal sign-off deletes the proof rungs outright, rather than delaying them.

Re-rank again on what the user already owns:

- A stocked review corpus drops social proof to near-zero effort and pulls it forward.
- An approved case study makes proof the cheapest strong rung there is.
- An in-house video team collapses UGC to a day.

Ship each stage on the best rung available now, and upgrade it later - a stage running an hour-old objection ad beats a stage waiting a quarter for a case study.

What this efficiency order starves is the belief-building end of the ladder. Named-customer proof, social proof and ROI content top the value axis and sit at the bottom of the build order. A sequence built on the ratio alone ships reminders and objection ads, then reaches for the discount when those stop converting - near-zero to make, margin spent every time it runs, and the hardest rung here to withdraw.

Promote a proof rung against the ratio when any of these holds:

- The objection rung has already run and the stage still does not convert, so the blocker is belief rather than friction.
- Question 11 was answered "durable assets".
- The sequence is B2B and the decision needs an internal champion to carry it through a committee.
- The final-stage discount is what is doing the converting, which means nothing above it built belief.

Start the quarter-long rung the week you notice, and run the hour-long rung in that stage meanwhile.

Delete, don't demote, every rung the answers rule out, and name each deletion in the stage table:

- No route to customer consent or legal sign-off deletes named-customer proof.
- No discount policy (question 7) deletes the discount rung.
- No budget for creator usage rights deletes UGC-based social proof.

A deleted rung is not the bottom of the build order - write the ladder without it, or a stage ends up planned around a rung nobody can produce.

Per stage, plan at least 3 distinct creative concepts - small retargeting pools burn through creative fast, and rotation is part of the frequency cap (step 7). Hand the actual production to `mbfinotti/advertising-skills@ad-creative-brief` and `mbfinotti/advertising-skills@ad-copy-variants`.

#### 6. Write the exclusion logic

Excerpt. The rest of the file is on the canonical page and in the source repository.

## Retargeting Funnel FAQ

### Is Retargeting Funnel safe to install?

skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

## Machine access

- [Sitemap](https://skillselion.com/sitemap.xml)
- [llms.txt](https://skillselion.com/llms.txt)
- [llms-full.txt](https://skillselion.com/llms-full.txt)
- [Developer resources](https://skillselion.com/developers)
- [OpenAPI spec](https://skillselion.com/openapi.json)
- [MCP handshake](https://skillselion.com/.well-known/mcp)
- [API catalog](https://skillselion.com/.well-known/api-catalog)
- [AI catalog](https://skillselion.com/.well-known/ai-catalog.json)
- [Pricing](https://skillselion.com/pricing.md)
- [Auth](https://skillselion.com/auth.md)
- [AGENTS.md](https://skillselion.com/AGENTS.md)
- [Contact](https://skillselion.com/contact)
- [Home](https://skillselion.com/)
