Marketing

Ad creative content strategy

Use this skill when onboarding a new ecommerce client and the ad production team needs an evidence-based content strategy before anything gets shot. Produces internal ad library and competitor analyses, review-based audience personas, tone of voice and key messages, and a client-ready HTML strategy report with content pillars, hooks, funnel mapping and a testing framework. Also use for "content strategy for a new client", "analyse their ad library", "competitor ad analysis", "build personas from reviews", "creative strategy for Meta".

Kayla BonnetteCo-Founder, Outlandish

Say something like

“content strategy for a new client”“analyse their ad library”“competitor ad analysis”“build personas from reviews”“creative strategy for Meta”

meta-ads content-strategy paid-social ad-creative ecommerce personas onboarding

SKILL.mdView on GitHub

Applies at the start of a new ecommerce engagement, before ad production begins. Produces two internal analyses for review and one client deliverable: an HTML content strategy report.

The play

Set up a Claude Project with the instructions in references/project-setup.md. Start a new chat for every new client. Never reuse a previous client's conversation.
Collect the assets before anything runs: client name and industry, channels in scope, monthly ad budget, production capacity (in-house, UGC or studio), the product review pages, the brand immersion deck, the website, the brand's Meta Ad Library, social profiles, and three competitors or aspirational brands with their ad library links. The full checklist is in references/project-setup.md. Claude flags anything missing before Step 1.
Step 1, client ad library analysis. Formats, partnership versus brand ads, repeated messaging, apparent personas, the longest-running ads, creative velocity, and a gap analysis comparing what the brand says it stands for against what is actually in its ads. Internal doc. Prompt and the no-active-ads alternate are in references/research-prompts.md.
Step 2, competitor analysis. The same framework across three competitor or aspirational ad libraries, ending with what the client can use strategically. Internal doc. Prompt in references/research-prompts.md.
Step 3, audience persona research. Scrape the brand's own product reviews, extract and rank personas with verbatim hook quotes, compare the real audience against the one the brand thinks it has, then define tone of voice and key messages. Four parts, in references/persona-and-voice-prompts.md.
Step 4, content strategy. Synthesise everything into a styled HTML report: content pillars mapped to personas, three hooks per pillar across varied hook types, funnel mapping across four stages, and a testing framework sized to the budget and production capacity. Prompt in references/strategy-prompt.md.

Run all four steps in one conversation, since the strategy needs every prior output in context. If someone picks up mid-session, they read back through the conversation before running the next prompt.

What good looks like

First thing I check that most people skip: the gap between what the brand says it stands for and what is actually running in its ads. The immersion deck says one thing; the ad library usually says another.
The second is who the reviews say the audience is, compared with who the brand thinks it is. The personas come from real customer reviews, not from the brief, and the verbatim quotes become the hooks.
The mediocre version defaults to solution-based hooks only. Every pillar gets three hooks across varied types: problem-first, pattern interrupt, contrarian, before and after, comment format, fear-based, future-self.
I know the strategy is right when every content pillar and key message maps back to a named persona, and the testing framework fits what the client can actually produce and spend.
Personas describe an actual audience type, like a skin-conscious millennial or a clean beauty buyer, never a funnel stage or a content format.

Rules

MUST collect all assets before Step 1.
MUST keep the Step 1 and Step 2 docs internal. They are QA documents, not client deliverables.
MUST build personas from the brand's own reviews, and note how many reviews were used.
MUST note clearly wherever findings are inferred from organic content rather than paid ads.
MUST source language guidelines from the brand immersion deck.
MUST make the HTML report match the brand's look and feel. It is the only client deliverable.
NEVER reuse a previous client's conversation.

4 reference files

references/persona-and-voice-prompts.md

Step 3: Audience persona research

Four parts, run in order in the same chat. The outputs live in the chat as structured analysis and feed straight into Step 4. No separate doc is needed for this step.

Part A: Review scrape

Go to {brand} website and scrape all available reviews directly from the product pages, up to a
maximum of 5,000. If fewer are available, work with what's there and note the total number of
reviews used in your analysis. Export the results as a CSV.

Part B: Persona extraction

Run straight after Part A in the same chat.

From this CSV of reviews, please do the following:
1. Extract 3 or more core personas. Give each a name that reflects their main trigger or problem,
   an age range, and a one-line descriptor. For each persona, write a 2-3 sentence emotional
   narrative covering what they feared, what they wanted, and what finally made them act.
2. Pull 2-3 verbatim quotes per persona that signal their core pain point or desire. These are
   potential ad hooks.
3. Rank the personas by how frequently they appear in the reviews. Create a second ranking by which
   personas use the most emotional language.
4. End with a demographic summary of 50-75 words identifying the dominant audience segment, shared
   emotional triggers, and the single biggest unmet desire across all reviews. Write this as if you
   are briefing a media buyer before a campaign launch.

Part C: Audience comparison

Confirm the brand immersion deck has been shared in this chat before running.

Compare who {brand}'s actual audience is, based on their customer reviews, with who they appear to
think their audience is, based on their ad library and brand immersion deck responses. Please
include:
1. Where there is crossover: what did they get right
2. What is missing: which key customer personas from the reviews are not being reflected in their
   ad content or creative strategy

Part D: Tone of voice and key messages

Based on everything in this conversation (the brand immersion deck, ad library analysis, competitor
analysis, and audience personas) define the following for {brand}:
1. Tone of voice: 3-4 defining characteristics with a brief description of each and a do/don't
   example for each
2. Language guidelines: 3 do/don't pairs covering specific language, phrases, or claims to use or
   avoid, sourced directly from the brand immersion deck. Format these separately from the TOV
   characteristics; they will appear as their own section in the final HTML report.
3. What to avoid: any tones, phrases, or approaches that would feel off-brand or that competitors
   are already owning
4. Key messages: 5-6 core messages that should run through all content, each mapped to the audience
   persona it speaks to most directly

references/project-setup.md

Project setup

Set this up once per client. Replace everything in {curly brackets} with real client information before sending any prompt.

Project instructions

You are a senior content strategist working within a marketing agency focused on scaling ecommerce
brands. Your role is to help the team build evidence-based content strategies for new clients to
guide the ad production process, by working through a structured four-step research and analysis
process.

Before starting any step, confirm the following have been shared in this chat: client name and
industry, channels in scope, monthly ad budget, content production capacity (in-house / UGC /
studio), review landing page, links to the brand website, Meta Ad Library, and social profiles, the
brand immersion deck, and 3 competitors or aspirational brands with their ad library links.

If anything is missing, flag it before proceeding. Do not begin Step 1 until all assets are present.

All HTML reports must be well-designed, visually styled, and structured for client presentation.
Use charts where relevant. Maintain consistent formatting across all reports in this workflow.

The four steps are: (1) Client Ad Library Analysis, (2) Competitor Analysis, (3) Audience Persona
Research, (4) Content Strategy. Run them in order in this conversation.

Before you start

Confirm all of these are collected and ready to share:

Claude will flag anything missing before proceeding. Do not skip this: incomplete context produces weaker outputs.

Golden rules

Run all four steps in a single conversation. Claude needs prior outputs in context to write the final strategy. On longer sessions the conversation may hit context limits; aim to complete all four steps without stopping where possible.
If a team member picks up mid-session, they read back through the conversation before running the next prompt.
The Step 1 and Step 2 docs are internal QA documents, for the team to review and sense-check before the HTML is built.
Save the final HTML report to the client folder. It is the only client deliverable.
Never reuse a previous client's conversation. Start a new chat for every new client.

references/research-prompts.md

Steps 1 and 2: Ad library research

Step 1: Client ad library analysis

Analyses the client's own Meta Ad Library to understand their current paid creative: formats, messaging, targeting, creative velocity and available ads. Ends with a gap analysis comparing what the brand says it stands for against what is actually in its ads.

Can you do an analysis on {brand}'s Meta Ad Library? The end report should be a doc for internal
review. Please include:
- Format breakdown (video, image, carousel, etc.)
- Distribution between partnership ads and brand ads (partnership ads are identified by "with" and
  a creator handle, or "Brand × creator handle" format)
- Core messaging strategies that are being repeated
- Audience personas they appear to be targeting, based on ad content only
- In-depth analysis of all available ads, up to a maximum of 10
- Round-up of their longest-running ads and a trend summary
- Creative velocity: how many ads are being uploaded, when, and when the last upload was
- Gap analysis: compare the brand's stated messaging priorities from the immersion deck against
  what is actually present in the ad library. Note where the ads align and where they fall short

If there are no active ads

{brand} has no active Meta Ad Library data. Please search for any available video or display ad
content on YouTube, TikTok, and Google. Additionally, review their organic social content on
Instagram and TikTok as a proxy for their paid creative direction. Summarise findings using the same
framework (format breakdown, messaging themes, apparent targeting, creative velocity) and note
clearly where data is limited or inferred from organic content rather than paid ads.

Output: one doc saved to the client folder, for internal QA review only.

Step 2: Competitor analysis

Analyses the Meta Ad Libraries of 3 competitor or aspirational brands to find patterns, messaging strategies and opportunities for the client.

Before running: pull the 3 competitors or aspirational brands from the immersion deck and collect their ad library links.

Can you do a competitor ad library analysis for {brand}? Please analyse the 3 competitor Meta Ads
libraries. The end report should be a doc for internal review. For each brand, please include:
- Format breakdown
- Distribution between partnership ads and brand ads
- Core messaging strategies being repeated
- Audience personas each brand appears to be targeting, based on ad content only. Describe the
  actual audience type (e.g. skin-conscious millennial, clean beauty buyer), not funnel stages or
  content formats.
- Their 3 longest-running ads
End with a summary across all three brands covering: key consistencies, standout data points, and
how {brand} can use this information strategically.

If a competitor has no active ads

{competitor} has no active Meta Ad Library data. Please search for any available video or display ad
content on YouTube, TikTok, and Google. Additionally, review their organic social content on
Instagram and TikTok as a proxy for their paid creative direction. Summarise findings using the same
framework (format breakdown, messaging themes, apparent targeting, creative velocity) and note
clearly where data is limited or inferred from organic content rather than paid ads.

Output: one doc saved to the client strategy folder, for internal QA review only.

references/strategy-prompt.md

Step 4: Content strategy

Synthesises all prior research into a full content strategy for direct-response ad creative: content pillars, hook examples, funnel mapping and a testing framework.

Before running the prompt

Confirm Steps 1, 2 and 3 are complete and all outputs are in this chat.
Have the channels, budget and production capacity confirmed and ready to fill in.

Prompt

Using all of the research and analysis from this conversation (the ad library analysis, competitor
analysis, audience personas, and brand immersion deck responses) please outline a content strategy
for direct-response ad creative for {channels}. The end report should be an HTML file with proper
visual styling, charts, and layout. It should match the brand look and feel. Please include:
- Snapshot of the ad creative analysis
- Snapshot of the competitor analysis
- Snapshot of the audience personas
- Snapshot of TOV and key messages, including language guidelines as a standalone section
- Content pillars with key messages mapped to audience personas
- Hook examples for each content pillar. Write 3 hooks per pillar using varied hook types. Include
  at least one from each of the following across your pillars: solution/problem-first,
  curiosity/pattern interrupt, contrarian, before/after, comment format, fear-based, or
  future-self/phone ringing. Do not default to solution-based hooks only.
- Funnel stage outline with pillars mapped across four stages: Unaware, Solution Aware, Brand Aware,
  and Conversion
- Testing framework appropriate to the budget and production capacity

Output

One HTML report saved to the client folder. This is the primary client deliverable.

Marketing

Ad creative content strategy

Kayla BonnetteCo-Founder, Outlandish

Say something like

“content strategy for a new client”“analyse their ad library”“competitor ad analysis”“build personas from reviews”“creative strategy for Meta”

meta-ads content-strategy paid-social ad-creative ecommerce personas onboarding

SKILL.mdView on GitHub

Applies at the start of a new ecommerce engagement, before ad production begins. Produces two internal analyses for review and one client deliverable: an HTML content strategy report.

The play

Set up a Claude Project with the instructions in references/project-setup.md. Start a new chat for every new client. Never reuse a previous client's conversation.
Collect the assets before anything runs: client name and industry, channels in scope, monthly ad budget, production capacity (in-house, UGC or studio), the product review pages, the brand immersion deck, the website, the brand's Meta Ad Library, social profiles, and three competitors or aspirational brands with their ad library links. The full checklist is in references/project-setup.md. Claude flags anything missing before Step 1.
Step 1, client ad library analysis. Formats, partnership versus brand ads, repeated messaging, apparent personas, the longest-running ads, creative velocity, and a gap analysis comparing what the brand says it stands for against what is actually in its ads. Internal doc. Prompt and the no-active-ads alternate are in references/research-prompts.md.
Step 2, competitor analysis. The same framework across three competitor or aspirational ad libraries, ending with what the client can use strategically. Internal doc. Prompt in references/research-prompts.md.
Step 3, audience persona research. Scrape the brand's own product reviews, extract and rank personas with verbatim hook quotes, compare the real audience against the one the brand thinks it has, then define tone of voice and key messages. Four parts, in references/persona-and-voice-prompts.md.
Step 4, content strategy. Synthesise everything into a styled HTML report: content pillars mapped to personas, three hooks per pillar across varied hook types, funnel mapping across four stages, and a testing framework sized to the budget and production capacity. Prompt in references/strategy-prompt.md.

What good looks like

First thing I check that most people skip: the gap between what the brand says it stands for and what is actually running in its ads. The immersion deck says one thing; the ad library usually says another.
The second is who the reviews say the audience is, compared with who the brand thinks it is. The personas come from real customer reviews, not from the brief, and the verbatim quotes become the hooks.
The mediocre version defaults to solution-based hooks only. Every pillar gets three hooks across varied types: problem-first, pattern interrupt, contrarian, before and after, comment format, fear-based, future-self.
I know the strategy is right when every content pillar and key message maps back to a named persona, and the testing framework fits what the client can actually produce and spend.
Personas describe an actual audience type, like a skin-conscious millennial or a clean beauty buyer, never a funnel stage or a content format.

Rules

MUST collect all assets before Step 1.
MUST keep the Step 1 and Step 2 docs internal. They are QA documents, not client deliverables.
MUST build personas from the brand's own reviews, and note how many reviews were used.
MUST note clearly wherever findings are inferred from organic content rather than paid ads.
MUST source language guidelines from the brand immersion deck.
MUST make the HTML report match the brand's look and feel. It is the only client deliverable.
NEVER reuse a previous client's conversation.

4 reference files

references/persona-and-voice-prompts.md

Step 3: Audience persona research

Four parts, run in order in the same chat. The outputs live in the chat as structured analysis and feed straight into Step 4. No separate doc is needed for this step.

Part A: Review scrape

Go to {brand} website and scrape all available reviews directly from the product pages, up to a
maximum of 5,000. If fewer are available, work with what's there and note the total number of
reviews used in your analysis. Export the results as a CSV.

Part B: Persona extraction

Run straight after Part A in the same chat.

From this CSV of reviews, please do the following:
1. Extract 3 or more core personas. Give each a name that reflects their main trigger or problem,
   an age range, and a one-line descriptor. For each persona, write a 2-3 sentence emotional
   narrative covering what they feared, what they wanted, and what finally made them act.
2. Pull 2-3 verbatim quotes per persona that signal their core pain point or desire. These are
   potential ad hooks.
3. Rank the personas by how frequently they appear in the reviews. Create a second ranking by which
   personas use the most emotional language.
4. End with a demographic summary of 50-75 words identifying the dominant audience segment, shared
   emotional triggers, and the single biggest unmet desire across all reviews. Write this as if you
   are briefing a media buyer before a campaign launch.

Part C: Audience comparison

Confirm the brand immersion deck has been shared in this chat before running.

Compare who {brand}'s actual audience is, based on their customer reviews, with who they appear to
think their audience is, based on their ad library and brand immersion deck responses. Please
include:
1. Where there is crossover: what did they get right
2. What is missing: which key customer personas from the reviews are not being reflected in their
   ad content or creative strategy

Part D: Tone of voice and key messages

Based on everything in this conversation (the brand immersion deck, ad library analysis, competitor
analysis, and audience personas) define the following for {brand}:
1. Tone of voice: 3-4 defining characteristics with a brief description of each and a do/don't
   example for each
2. Language guidelines: 3 do/don't pairs covering specific language, phrases, or claims to use or
   avoid, sourced directly from the brand immersion deck. Format these separately from the TOV
   characteristics; they will appear as their own section in the final HTML report.
3. What to avoid: any tones, phrases, or approaches that would feel off-brand or that competitors
   are already owning
4. Key messages: 5-6 core messages that should run through all content, each mapped to the audience
   persona it speaks to most directly

references/project-setup.md

Project setup

Set this up once per client. Replace everything in {curly brackets} with real client information before sending any prompt.

Project instructions

You are a senior content strategist working within a marketing agency focused on scaling ecommerce
brands. Your role is to help the team build evidence-based content strategies for new clients to
guide the ad production process, by working through a structured four-step research and analysis
process.

Before starting any step, confirm the following have been shared in this chat: client name and
industry, channels in scope, monthly ad budget, content production capacity (in-house / UGC /
studio), review landing page, links to the brand website, Meta Ad Library, and social profiles, the
brand immersion deck, and 3 competitors or aspirational brands with their ad library links.

If anything is missing, flag it before proceeding. Do not begin Step 1 until all assets are present.

All HTML reports must be well-designed, visually styled, and structured for client presentation.
Use charts where relevant. Maintain consistent formatting across all reports in this workflow.

The four steps are: (1) Client Ad Library Analysis, (2) Competitor Analysis, (3) Audience Persona
Research, (4) Content Strategy. Run them in order in this conversation.

Before you start

Confirm all of these are collected and ready to share:

Claude will flag anything missing before proceeding. Do not skip this: incomplete context produces weaker outputs.

Golden rules

Run all four steps in a single conversation. Claude needs prior outputs in context to write the final strategy. On longer sessions the conversation may hit context limits; aim to complete all four steps without stopping where possible.
If a team member picks up mid-session, they read back through the conversation before running the next prompt.
The Step 1 and Step 2 docs are internal QA documents, for the team to review and sense-check before the HTML is built.
Save the final HTML report to the client folder. It is the only client deliverable.
Never reuse a previous client's conversation. Start a new chat for every new client.

references/research-prompts.md

Steps 1 and 2: Ad library research

Step 1: Client ad library analysis

Can you do an analysis on {brand}'s Meta Ad Library? The end report should be a doc for internal
review. Please include:
- Format breakdown (video, image, carousel, etc.)
- Distribution between partnership ads and brand ads (partnership ads are identified by "with" and
  a creator handle, or "Brand × creator handle" format)
- Core messaging strategies that are being repeated
- Audience personas they appear to be targeting, based on ad content only
- In-depth analysis of all available ads, up to a maximum of 10
- Round-up of their longest-running ads and a trend summary
- Creative velocity: how many ads are being uploaded, when, and when the last upload was
- Gap analysis: compare the brand's stated messaging priorities from the immersion deck against
  what is actually present in the ad library. Note where the ads align and where they fall short

If there are no active ads

{brand} has no active Meta Ad Library data. Please search for any available video or display ad
content on YouTube, TikTok, and Google. Additionally, review their organic social content on
Instagram and TikTok as a proxy for their paid creative direction. Summarise findings using the same
framework (format breakdown, messaging themes, apparent targeting, creative velocity) and note
clearly where data is limited or inferred from organic content rather than paid ads.

Output: one doc saved to the client folder, for internal QA review only.

Step 2: Competitor analysis

Analyses the Meta Ad Libraries of 3 competitor or aspirational brands to find patterns, messaging strategies and opportunities for the client.

Before running: pull the 3 competitors or aspirational brands from the immersion deck and collect their ad library links.

Can you do a competitor ad library analysis for {brand}? Please analyse the 3 competitor Meta Ads
libraries. The end report should be a doc for internal review. For each brand, please include:
- Format breakdown
- Distribution between partnership ads and brand ads
- Core messaging strategies being repeated
- Audience personas each brand appears to be targeting, based on ad content only. Describe the
  actual audience type (e.g. skin-conscious millennial, clean beauty buyer), not funnel stages or
  content formats.
- Their 3 longest-running ads
End with a summary across all three brands covering: key consistencies, standout data points, and
how {brand} can use this information strategically.

If a competitor has no active ads

{competitor} has no active Meta Ad Library data. Please search for any available video or display ad
content on YouTube, TikTok, and Google. Additionally, review their organic social content on
Instagram and TikTok as a proxy for their paid creative direction. Summarise findings using the same
framework (format breakdown, messaging themes, apparent targeting, creative velocity) and note
clearly where data is limited or inferred from organic content rather than paid ads.

Output: one doc saved to the client strategy folder, for internal QA review only.

references/strategy-prompt.md

Step 4: Content strategy

Synthesises all prior research into a full content strategy for direct-response ad creative: content pillars, hook examples, funnel mapping and a testing framework.

Before running the prompt

Confirm Steps 1, 2 and 3 are complete and all outputs are in this chat.
Have the channels, budget and production capacity confirmed and ready to fill in.

Prompt

Using all of the research and analysis from this conversation (the ad library analysis, competitor
analysis, audience personas, and brand immersion deck responses) please outline a content strategy
for direct-response ad creative for {channels}. The end report should be an HTML file with proper
visual styling, charts, and layout. It should match the brand look and feel. Please include:
- Snapshot of the ad creative analysis
- Snapshot of the competitor analysis
- Snapshot of the audience personas
- Snapshot of TOV and key messages, including language guidelines as a standalone section
- Content pillars with key messages mapped to audience personas
- Hook examples for each content pillar. Write 3 hooks per pillar using varied hook types. Include
  at least one from each of the following across your pillars: solution/problem-first,
  curiosity/pattern interrupt, contrarian, before/after, comment format, fear-based, or
  future-self/phone ringing. Do not default to solution-based hooks only.
- Funnel stage outline with pillars mapped across four stages: Unaware, Solution Aware, Brand Aware,
  and Conversion
- Testing framework appropriate to the budget and production capacity

Output

One HTML report saved to the client folder. This is the primary client deliverable.

Ad creative content strategy

The play

What good looks like

Rules

Step 3: Audience persona research

Part A: Review scrape

Part B: Persona extraction

Part C: Audience comparison

Part D: Tone of voice and key messages

Project setup

Project instructions

Before you start

Golden rules

Steps 1 and 2: Ad library research

Step 1: Client ad library analysis

If there are no active ads

Step 2: Competitor analysis

If a competitor has no active ads

Step 4: Content strategy

Before running the prompt

Prompt

Output

Want this sounding like you?

More from Kayla

Klaviyo account audit

More in Stand out

Call topic mining

Case study build

Content brief

Ad creative content strategy

The play

What good looks like

Rules

Step 3: Audience persona research

Part A: Review scrape

Part B: Persona extraction

Part C: Audience comparison

Part D: Tone of voice and key messages

Project setup

Project instructions

Before you start

Golden rules

Steps 1 and 2: Ad library research

Step 1: Client ad library analysis

If there are no active ads

Step 2: Competitor analysis

If a competitor has no active ads

Step 4: Content strategy

Before running the prompt

Prompt

Output

Want this sounding like you?

More from Kayla

Klaviyo account audit

More in Stand out

Call topic mining

Case study build

Content brief