Syntic

Skills may execute instructions and code that could affect your environment. Marketplace scans reduce risk but do not guarantee safety. Always review files, run your own security checks, and use at your own risk.

Paid & MeasurementFree Safe

Ad Creative

Security Scan Summary

Status: Safe

Source: Syntic Skills registry

Automated security scan completed with no high-risk patterns detected. Manual review is still required.

About This Skill

Use when the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid ad platform.

Downloadable SKILL.md

Download SKILL.md and place it in your Syntic skills folder. For Syntic Code, install in your local skills directory, review contents, and run in a controlled environment first. Acknowledge the risk notice above to enable the download.

SKILL.md
---
name: Ad Creative
description: Use when the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid ad platform.
category: Paid & Measurement
version: 2.0.0
tools: []
---

# Ad Creative

Generate high-performing ad creative at scale — headlines, descriptions, and primary text that drive clicks and conversions — and iterate based on real performance data.

## Before Starting

Search the Knowledge Base for existing product marketing context before asking questions; use whatever is already there and only ask about what's missing.

Gather this context (ask if not provided):

**Platform & format** — which platform (Google Ads, Meta, LinkedIn, TikTok, Twitter/X), which ad format (search RSAs, display, social feed, stories, video), and whether there's existing creative to iterate on or this is starting from scratch.

**Product & offer** — what's being promoted (product, feature, free trial, demo, lead magnet), the core value proposition, and what differentiates it from competitors.

**Audience & intent** — the target audience, their awareness stage (problem-aware, solution-aware, product-aware), and the pain points or desires driving them.

**Performance data (if iterating)** — what's currently running, which headlines/descriptions perform best (CTR, conversion rate, ROAS), which underperform, and what angles have already been tested.

**Constraints** — brand voice guidelines or words to avoid, compliance requirements (industry regulations, platform policies), and mandatory elements (brand name, trademark symbols, disclaimers).

## How This Skill Works

Two modes: **Generate from Scratch** — build a full creative set from product context, audience insight, and platform best practice — and **Iterate from Performance Data** — the user supplies performance data (pasted text, CSV, or API output) and you analyze what's working, identify patterns in top performers, and generate new variations that build on winning themes while exploring new angles.

Core loop: gather performance data → identify winning patterns → generate new variations → validate against platform specs → deliver.

## Platform Specs

Platforms reject or truncate creative that exceeds these limits — verify every piece of copy fits before delivering.

**Google Ads (Responsive Search Ads):** Headline 30 characters, up to 15; Description 90 characters, up to 4; Display URL path 15 characters each, 2 paths. Headlines must make sense independently and in any combination; pin headlines to positions only when necessary (it reduces optimization); include at least one keyword-focused, one benefit-focused, and one CTA headline.

**Meta Ads (Facebook/Instagram):** Primary text 125 characters visible (up to 2,200) — front-load the hook; Headline 40 characters recommended, below the image; Description 30 characters recommended, below the headline; URL display link 40 characters, optional.

**LinkedIn Ads:** Intro text 150 characters recommended (600 max), above the image; Headline 70 characters recommended (200 max), below the image; Description 100 characters recommended (300 max), shown in some placements.

**TikTok Ads:** Ad text 80 characters recommended (100 max), above the video; Display name 40 characters.

**Twitter/X Ads:** Tweet text 280 characters; Headline 70 characters (card headline); Description 200 characters (card description).

## Generating Ad Visuals

For image and video creative, point the user to generative tools rather than producing files directly: **Nano Banana Pro (Gemini)**, **Flux**, or **Ideogram** for static images; **Veo**, **Kling**, **Runway**, **Sora**, **Seedance**, or **Higgsfield** for video; **ElevenLabs**, **OpenAI TTS**, or **Cartesia** for voiceover, cloning, and multilingual audio; **Remotion** for templated, code-based video at scale. Recommended workflow: generate hero creative with AI tools first (exploratory, high quality), build templates from the winning patterns, batch-produce variations from data feeds, then keep using AI for new angles and templating for scale.

## Generating Ad Copy

**Step 1 — Define angles.** Before writing individual headlines, establish 3-5 distinct angles — different reasons someone would click, each tapping a different motivation: pain point ("Stop wasting time on X"), outcome ("Achieve Y in Z days"), social proof ("Join 10,000+ teams who..."), curiosity ("The X secret top companies use"), comparison ("Unlike X, we do Y"), urgency ("Limited time: get X free"), identity ("Built for [role/type]"), contrarian ("Why [common practice] doesn't work").

**Step 2 — Generate variations per angle.** Vary word choice (synonyms, active vs. passive), specificity (numbers vs. general claims), tone (direct vs. question vs. command), and structure (short punch vs. full benefit statement).

**Step 3 — Validate against specs.** Check every piece of creative against the platform's character limits before delivering; flag anything over and provide a trimmed alternative.

**Step 4 — Organize for upload** in a structured format that maps to the platform's upload requirements.

## Iterating from Performance Data

**Analyze winners** (by CTR, conversion rate, or ROAS — ask which metric matters most): winning themes, winning structures (questions/statements/commands/numbers), winning word patterns, and whether top performers run shorter or longer than average.

**Analyze losers:** themes that fall flat, and common patterns in low performers (too generic, too long, wrong tone).

**Generate new variations** that double down on winning themes with fresh phrasing, extend winning angles into new variations, test 1-2 new angles not yet explored, and avoid patterns found in underperformers.

**Document the iteration** — round number, date, top performers with metrics, a winning-pattern summary, the count of new headlines/descriptions generated, angles being tested, and angles retired.

## Writing Quality Standards

**Headlines that click** are specific ("Cut reporting time 75%") over vague ("Save time"), benefit-led ("Ship code faster") over feature-led ("CI/CD pipeline"), active voice ("Automate your reports") over passive, and include numbers when possible ("3x faster," "in 5 minutes," "10,000+ teams"). Avoid jargon, unsupported superlatives ("Best," "Leading," "Top"), all caps or excessive punctuation, and clickbait the landing page can't deliver on.

**Descriptions that convert** complement headlines rather than repeat them: add proof points (numbers, testimonials, awards), handle objections ("No credit card required"), reinforce CTAs ("Start your free trial today"), and add genuine urgency ("Limited to first 500 signups").

## Output Formats

**Standard output** — organize by angle, with a character count next to each line; flag anything over the limit and provide a trimmed alternative.

**Bulk output** — for 10+ variations, offer a table (headline_1/2/3, description_1/2, platform) formatted for direct upload.

**Iteration report** — summarize what was analyzed, the top and worst performer with their metric values, the pattern observed, the new creative organized by angle, and recommendations for what to pause, scale, or test next.

## Batch Generation Workflow

For large-scale production (high-output growth teams generate 100+ variations per cycle):

1. **Break into sub-tasks** — headline generation (click-through focus), description generation (conversion focus), primary text generation (engagement focus, for Meta/LinkedIn).
2. **Generate in waves** — Wave 1: core angles (3-5 angles, 5 variations each). Wave 2: extended variations on the top 2 angles. Wave 3: wild-card angles (contrarian, emotional, hyper-specific).
3. **Quality filter** — remove anything over the character limit, remove duplicates/near-duplicates, flag possible platform-policy violations, and confirm headline/description combinations make sense together.

## Common Mistakes

- Writing headlines that only work in isolation — RSA headlines get combined randomly by the platform
- Ignoring character limits — platforms truncate without warning
- All variations sounding the same — vary angles, not just word choice
- No CTA headlines — RSAs need 2-3 action-oriented headlines to drive clicks
- Generic descriptions ("Learn more about our solution" wastes the slot)
- Iterating without data — gut feelings are less reliable than metrics
- Testing too many things at once — change one variable per test cycle
- Retiring creative too early — allow 1,000+ impressions before judging

## Related Work

For campaign strategy, targeting, and budgets, pair this with the **ads** skill. For landing page copy where the traffic lands, use **copywriting**. For structuring tests with statistical rigor, use **ab-testing**. For the psychology behind high-performing creative, use **marketing-psychology**. For polishing copy before launch, use **copy-editing**.

Bundle Download

Includes SKILL.md and bundled support files where provided. Risk acknowledgement is required.

Install Targets

Syntic App

  1. 1. Create a dedicated folder for this skill in your local skills library.
  2. 2. Place SKILL.md into that folder.
  3. 3. Restart Syntic and invoke this skill on matching tasks.

Syntic Code (CLI)

  1. 1. Save SKILL.md in your local Syntic Code skills directory.
  2. 2. Keep related files in the same skill folder.
  3. 3. Run in a safe environment and validate outputs.

Source

https://github.com/coreyhaines31/marketingskills/blob/main/skills/ad-creative/SKILL.md

Open Source Link
Paid & Measurement

Related Skills