Index of every page on this site: llms.txt
All skills
Run it yourself

When the user wants to write or judge ad creative, or asks which ad, hook, or angle to run or kill: headlines, primary text, and variations for Google, Meta, LinkedIn, and TikTok, fresh angles when creative fatigues. Test hypotheses name the metric, comparison, and expected direction. No AI tells like 'it's not X, it's Y'. For campaign strategy, see ads. For landing pages, see copywriting.

Use this Skill: https://skilld.dev/gh/coreyhaines31/marketingskills/ad-creative

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesawareness-headlines.md

≈1.7k tokens on demand. Your agent reads this file only when SKILL.md points to it.

Awareness-Based Headline Creative

Use for text-led static concepts, especially B2B feed ads. These are compact treatments within the existing angle and template workflow; they do not replace audience research, the hook system, or platform specs.

Concept lineage: the maintainer's #404 follow-up to the ivangfalco/ads-skills remix. Re-expressed independently and reconciled with this repo's grounding and AI-tells rules; no source copy or creative assets imported.

Choose the Reader's Next Step

Awareness What the reader needs Useful treatments CTA direction
Unaware / unfamiliar with the category Recognize a specific lived situation Feeling, conversation Learn about the situation or mechanism
Problem-aware See a credible path out of a named friction Pain + outcome, time-anchored friction See the workflow or explanation
Solution-aware Understand a concrete way this approach differs State change, documented statistic Compare the mechanism or watch a demo
Product-aware Resolve an objection with specific proof Statistic, pain + outcome Inspect proof, try, or book the relevant next step

Stage is a working hypothesis about this audience, not a diagnosis based on the platform alone. If unknown, state the assumption and propose two distinct stage hypotheses. A formula alone cannot prove an ad will convert.

Six Treatments

The examples below are invented illustrations of structure, not approved product claims, real customer quotes, or ready-to-run ads. Replace their facts with the user's verified corpus. Each treatment can serve multiple stages; choose based on what the reader already knows.

Treatment Construction and guardrail Illustrative SaaS example Illustrative DTC example
Feeling Name a recognizable feeling tied to a specific work/life moment. Avoid vague empowerment or a forced positive/negative reveal. “Leave Friday with the forecast finished.” “Dinner sorted before the commute home.”
Conversation Two short lines from a recognizable situation. Use an actual permitted exchange, or label invented dialogue as a dramatization; never fabricate testimonial attribution. “Is this the final sheet?” / “There are three final sheets.” “What's for dinner?” / “I'm still on the train.”
State change Show the current and proposed workflow with concrete artifacts. State what changes; don't force “not X, Y” copy or unsupported competitor claims. “Bring the three approval threads into one queue.” “Pack tomorrow's lunch while tonight's dinner cooks.”
Time-anchored friction Name an obsolete or repetitive process and its actual moment. Critique the process without shaming the buyer or inventing a trend. “Month-end still starts with copying CSVs.” “The Sunday grocery list starts over again.”
Documented statistic One supported number plus the population, period, or meaningful qualifier. Keep its real precision; rounded numbers are not evidence of fakery. “Pilot teams cut weekly reconciliation from 6 hours to 2.” “Three dinners packed in one delivery.”
Pain + outcome One named friction and a concrete next action/outcome, usually under ten words. Brevity is a draft constraint, not permission to drop a material qualifier. “Find the missing invoice before close.” “Get dinner ready between calls.”

Read each draft against the existing AI-tells guidance. Do not produce six near-identical sentences just to fill a formula menu. Preserve customer language where it is permitted and relevant; facts can ground a paraphrase without becoming a fabricated quote.

Gather Proof Before Copy

Build a small evidence sheet: source ID, verbatim phrase or product fact, audience, date, allowed usage, and limitations. Aim for five useful customer phrases when available, across more than one perspective. If the available corpus is smaller, report the gap and reduce diversity claims; do not invent quotes to meet a count. Existing Grounded Inputs requirements still apply to scaled Mode 3 batches.

Separate language evidence (“the export takes forever”) from claim evidence (a measured reduction across a defined pilot). A complaint supports the pain angle; it does not substantiate a numerical performance promise. Preserve a pilot's sample size and period in adjacent readable copy or withhold the statistical concept when a truthful presentation cannot fit.

Make the Headline the Visual

Apply this treatment to Headline Statement or Stat Callout from the static library when the words carry the concept. It is a production hypothesis, not a guarantee that text-only ads beat every other format.

  • Start with one dominant sentence and a bold, legible sans-serif face. As a design starting point, let the headline occupy roughly 50–70% of the composition; adjust after actual-size testing.
  • Use intentional line breaks that keep phrases together. Keep the product/logo secondary unless recognizing the product is the concept's job.
  • Test a dark background with light text, or a strong brand-colored background with contrasting text. Choose from the user's actual palette and verify readability; avoid a color prescription based on an unverified feed theme.
  • Include the audience's specific moment, one defensible idea, and enough qualification to read truthfully. Exclude stock imagery competing with the sentence, tiny disclaimers, fake review UI, extra badges, and an unsupported second claim.
  • Make a preview at the actual mobile feed display size, not only on a desktop canvas. Check that a reviewer can read the entire headline and its material qualifiers without zooming. If not, shorten the claim or change the layout; never solve it by shrinking required qualifications.
  • Get current export dimensions, cropping, safe areas, and text-field limits from the platform-spec reference and the selected placement. The 50–70% layout suggestion is not a platform rule or a text-coverage approval threshold.

Deliver and Learn

For each concept, provide: audience/stage assumption, distinct angle, treatment + static template, headline, supporting qualification, CTA, source IDs, and visual specification with mobile-readability check. Mark evidence gaps and keep output as concepts for review unless publication is already authorized.

Test stage/angle hypotheses before fine font changes. Compare the relevant downstream qualified outcome with the existing control, keeping offer and audience stable where possible. Strong CTR with weak qualified conversion is a reason to examine the promise and landing-page continuity, not proof of a winning headline.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 alert1d5 checks · Risk SAFE
  • Gen Agent Trust Hub2d

    This is a highly sophisticated and professionally structured skill for managing the entire ad creative lifecycle, including generation, iteration, and strategic roadmapping. It emphasizes 'grounded inputs' from real customer data and includes detailed security best practices for its interactive HTML review tool. No malicious patterns were detected.

  • Socket1d

    No alerts

  • Snyk2d

    Risk: CRITICAL · 3 issues

  • Runlayer8mo

    2/3 files flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 5b2b400. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated yesterday
metadata
{
  "version": "2.13.5"
}
  • ad-copy
  • google-ads
  • meta
  • linkedin
  • performance-marketing
  • headlines
  • copywriting
  • a-b-testing
  • creative-optimization

README badge

README badge for coreyhaines31/marketingskills/ad-creative

Generates and iterates ad creative—headlines, descriptions, and primary text—for Google Ads, Meta, LinkedIn, TikTok, and Twitter/X, with character-limit validation and performance-data analysis. Use when scaling ad copy, building RSA variations, or optimizing based on CTR and conversion metrics.

Generated from the current SKILL.md.

Does this skill support all ad platforms?
Yes. The skill covers Google Ads (RSAs), Meta (Facebook/Instagram), LinkedIn, TikTok, and Twitter/X, with platform-specific character limits and format rules for each.
Can I use this skill to iterate on existing ads based on performance data?
Yes. The skill includes a mode for analyzing top and bottom performers, identifying winning patterns, and generating new variations that build on what's working while testing new angles.
Does this generate images or video for ads?
No. This skill generates text copy only. For visual ad assets, it references tools like Flux, Remotion, and Veo in a bundled guide, but does not generate images or video directly.
What if my ad copy is too long for the platform?
The skill validates all copy against platform character limits before delivery and provides trimmed alternatives when necessary.
Do I need to provide product context or performance data to use this skill?
The skill can generate from scratch if you provide product, audience, and offer details, or iterate from existing ads if you provide performance metrics like CTR or conversion rate.

Generated from the current SKILL.md. These answers refresh after source changes.