Mkt Ad Optimization Agent Skill

Optimize digital advertising campaigns across Google Ads, Meta Ads, and LINE LAP including bidding strategies, audience targeting, creative testing, and ROAS optimization. Use this skill when the user needs to improve ad performance, reduce CPA, select bidding strategies, or allocate budget across platforms — even if they say 'our ads aren't working', 'reduce our cost per acquisition', 'Google vs Facebook ads', or 'improve our ROAS'.

8k tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

223

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/asgard-ai-platform/skills --skill mkt-ad-optimization

What comes with it

24 323 bytes besides the instruction

examples/sample_scenario.md

references/google-ads-structure.md

references/meta-creative.md

The instruction itself

9 sections, as written by the author

Digital Ad Optimization

Framework

IRON LAW: Optimize for the Business Metric, Not the Ad Metric

High CTR with low conversion = wasted clicks (attracting curiosity, not buyers).
Low CPC with no sales = cheap traffic that doesn't convert.

The only metrics that matter: CPA (Cost Per Acquisition), ROAS (Return On Ad Spend),
and ultimately: profit per ad dollar. Optimize the funnel, not the ad.

Platform Comparison

|----------|---------|---------|-----------------|-------------------|

Bidding Strategies

| Strategy | How It Works | When to Use |

|----------|-------------|------------|

| Manual CPC | You set max CPC | Learning phase, small budgets, full control |

| Target CPA | Algorithm optimizes for target cost per acquisition | 30+ conversions/month, known CPA target |

| Target ROAS | Algorithm optimizes for target return on ad spend | E-commerce, known revenue per conversion |

| Maximize Conversions | Spend full budget to get max conversions | Growth phase, less concerned about CPA |

| Maximize Clicks | Most clicks for budget | Traffic campaigns, awareness |

Optimization Workflow

Phase 1: Audit Current Performance

CPA by campaign, ad group, keyword/audience
Quality Score (Google) or Relevance Score (Meta)
Conversion rate by landing page
Wasted spend: search terms with clicks but no conversions

Phase 2: Quick Wins (Week 1-2)

Add negative keywords (Google Search)
Pause underperforming ad groups/audiences
Reduce bids on high-CPA keywords
Fix landing page mismatches (ad promise ≠ landing page content)

Phase 3: Structural Improvements (Week 3-4)

Audience segmentation: separate cold, warm, hot audiences
Creative refresh: new ad copy/images (fatigue sets in after 2-4 weeks)
Landing page optimization: speed, mobile, clear CTA

Phase 4: Scaling (Month 2+)

Increase budget on winning campaigns (incrementally, +20%/week)
Expand to new audiences (lookalikes, new interests)
Test new platforms
Build retargeting funnel: awareness → consideration → conversion

Creative Testing (A/B)

| Element | What to Test | Minimum Sample |

|---------|-------------|---------------|

| Headline | Benefit vs feature, question vs statement | 1,000 impressions each |

| Image/Video | Product shot vs lifestyle, static vs video | 1,000 impressions each |

| CTA | "Shop Now" vs "Learn More" vs "Get Offer" | 500 clicks each |

| Offer | Free shipping vs % discount vs gift | 100 conversions each |

Output Format

# Ad Optimization Report: {Campaign/Account}

## Performance Summary
| Metric | Current | Target | Status |
|--------|---------|--------|--------|
| Spend | NT${X}/month | — | — |
| CPA | NT${X} | NT${X} | 🟢/🟡/🔴 |
| ROAS | {X}x | {X}x | 🟢/🟡/🔴 |
| CVR | {%} | {%} | 🟢/🟡/🔴 |

## Top Performing
| Campaign/Ad | CPA | ROAS | Action |
|------------|-----|------|--------|
| {name} | NT${X} | {X}x | Scale +20% |

## Underperforming
| Campaign/Ad | CPA | Issue | Action |
|------------|-----|-------|--------|
| {name} | NT${X} | {diagnosis} | Pause/Optimize/Restructure |

## Optimization Plan
| Priority | Action | Expected Impact | Timeline |
|----------|--------|----------------|----------|
| 1 | {action} | CPA -{X%} | {weeks} |

Gotchas

Learning phase needs patience: Google/Meta algorithms need 50+ conversions per week per ad group to optimize. Restructuring too frequently resets learning.
Attribution isn't perfect: Google takes credit for Google, Meta takes credit for Meta. Use UTM parameters and a neutral analytics tool (GA4) for cross-platform attribution.
Creative fatigue is real: Even winning ads degrade over 2-4 weeks as the same audience sees them repeatedly. Refresh creatives regularly.
Taiwan ad market specifics: LINE LAP reaches demographics that Facebook is losing (older users). Google is dominant for search intent. Mix platforms based on your audience.
iOS privacy (ATT): Since iOS 14.5, Meta tracking is limited. Expect less accurate reporting for iOS users. Use conversion API and model-based attribution.

References

For Google Ads account structure best practices, see references/google-ads-structure.md
For Meta Ads creative guidelines, see references/meta-creative.md

Other skills for the same job

different authors, same section of the catalogue

Viral Instagram Reels

by vyralcontent

×1

Plan, write, and diagnose Instagram Reels that earn cold-audience reach. Use whenever someone wants a reels script or reels hook for a specific Reel, is debugging why a Reel flopped, wants to know if a draft is worth testing with Trial Reels before going public, or needs a reels caption tuned for the post-hashtag instagram algorithm. Built around what Mosseri has publicly named as the signal hierarchy (watch time, sends per reach, likes per reach), the Trial Reels test-then-publish loop, the Original Content Guidelines and 30-day recovery window, the Edits app, and Reels Insights metrics (skip rate, share rate, followers from this post). Covers a Reels-specific reels strategy: send-driving CTAs, originality without watermarks, audio licensing by account type, captions as the primary SEO signal, and the anti-patterns that quietly cap distribution. Pattern-based guidance, not a virality promise.

Perform relative value analysis on bonds by combining pricing, yield curve context, credit spreads, and scenario stress testing. Use when analyzing bond richness/cheapness, computing spread decomposition, comparing bonds, assessing bond value vs curves, or running rate shock scenarios.

Build quick IRR/MOIC sensitivity tables for PE deal evaluation. Models returns across entry multiple, leverage, exit multiple, growth, and hold period scenarios. Use when sizing up a deal, stress-testing assumptions, or preparing IC returns exhibits. Triggers on "returns analysis", "IRR sensitivity", "MOIC table", "what's the return at", "model the returns", or "back of the envelope".

837 tokens

Brainstorm Experiments New

by phuryn

Design lean startup experiments (pretotypes) for a new product. Creates XYZ hypotheses and suggests low-effort validation methods like landing pages, explainer videos, and pre-orders. Use when validating a new product idea, creating pretotypes, or testing market demand.

634 tokens

Amazon Alexa QA

by browser-act

Amazon Alexa for Shopping Q&A automation: submits questions to Amazon's Alexa/Rufus AI shopping assistant and collects response text; supports optional keyword search context (navigate to search results page before asking for category-specific answers). Use when user mentions Amazon Alexa, Rufus, Amazon shopping assistant, Amazon AI chat, ask Amazon, Amazon Q&A, automate Alexa questions, Rufus chatbot, Amazon assistant automation, collect Alexa responses, bulk question submission to Amazon, keyword search context, category research. Also applies to extracting Amazon product recommendations from conversational AI, automating repeated queries to Amazon's AI shopping feature, collecting Alexa shopping responses at scale, or market research within a specific product category.

4k tokens scripts

AI Ugc Ads

by tech-leads-club

When the user wants to create UGC ad campaigns, recruit UGC creators, generate AI UGC content, or scale with user-generated content. Also use when the user mentions 'UGC,' 'user-generated content,' 'creator ads,' 'Spark Ads,' 'whitelisting,' 'AI UGC,' 'Arcads,' 'Creatify,' 'creator brief,' or 'UGC testing.' This skill covers the UGC growth framework from creator recruitment through AI-powered scaling. Do NOT use for technical implementation, code review, or software architecture.

5k tokens

Input File Skill

by NVIDIA

Parse, modify, validate, and patch simulator input files. Use when working with reservoir simulation input files, testing scenarios, or validating simulation configurations. This implementation supports reference format (.DATA); other simulators use different extensions (e.g., .afi, .DAT). Supports natural language modifications, keyword patching, and syntax validation.

11k tokens scripts

Recon Scope Triage

by elementalsouls

Triage ASM/recon output for ownership before testing — separate the target's real assets from namespace-collision noise. Automated recon keyword-matches on the brand name, so for any target whose name is a common/dictionary word, the output is dominated by assets belonging to UNRELATED same-named companies (repos, cloud buckets, mobile apps, breach corpora, typosquats). Built from an authorized engagement where an ASM report's "Criticals" were overwhelmingly false positives and the combo/repos/mobile/bucket lists were polluted with unrelated same-named orgs. Use at the START of any engagement, immediately on receiving any ASM/recon/OSINT dataset, BEFORE testing anything.

2k tokens

How to use it

Copy the folder

Take asgard-ai-platform/mkt-ad-optimization from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.