advertising-skills-ai-agents
```markdown
What this skill does
```markdown
---
name: advertising-skills-ai-agents
description: Skill library for encoding direct-response advertising, copywriting, and funnel thinking into AI coding agents using the Agent Skills pattern.
triggers:
- set up advertising skills for my AI agent
- install advertising skills skill library
- use advertising skills with Claude Code
- build a booked call campaign with AI
- add direct response copywriting skills to my agent
- configure advertising skills for cursor or codex
- run a funnel campaign orchestrator
- chain advertising skills for paid ads
---
# Advertising Skills for AI Agents
> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection.
A structured, opinionated skill library that encodes direct-response advertising, Eugene Schwartz copywriting, funnel architecture, and paid media strategy into AI coding agents. Skills are chained, not prompted — the system builds strategy before writing a single word of copy.
---
## What This Project Does
Advertising Skills gives AI agents (Claude Code, Cursor, Codex, Windsurf, Open Claw, custom frameworks) a reusable library of focused advertising "skills" — each one a `SKILL.md` file that defines:
- **When** to use it
- **What inputs** it needs
- **How it thinks** (the reasoning layer)
- **What it outputs**
- **What it must not do**
Skills are grouped into five categories and designed to be chained in sequence, producing output that is positioned, specific, and conversion-focused — not generic AI marketing copy.
---
## Installation
### Step 1: Clone or download the repository
```bash
git clone https://github.com/realkimbarrett/advertising-skills.git
```
### Step 2: Install skills into your agent's skill directory
```bash
cp -r advertising-skills/skills .agents/skills/
```
Or for a specific orchestrator only:
```bash
cp -r advertising-skills/skills/orchestrators/booked-call-campaign-orchestrator \
.agents/skills/booked-call-campaign-orchestrator
```
### Step 3: Verify structure
Your project should now contain:
```
.agents/
skills/
foundations/
avatar-extraction/
SKILL.md
voice-of-customer-miner/
SKILL.md
offer-extraction/
SKILL.md
proof-harvester/
SKILL.md
positioning-core/
SKILL.md
copy-chief/
schwartz-awareness-mapper/
SKILL.md
market-sophistication-analyzer/
SKILL.md
dominant-desire-extractor/
SKILL.md
mechanism-builder/
SKILL.md
headline-matrix/
SKILL.md
objection-crusher/
SKILL.md
close-architect/
SKILL.md
operator-os/
scroll-stopping-creative/
SKILL.md
ad-angle-multiplier/
SKILL.md
conversion-path-builder/
SKILL.md
landing-page-architect/
SKILL.md
email-sequence-architect/
SKILL.md
performance-diagnosis/
SKILL.md
testing-roadmap/
SKILL.md
qa/
generic-language-killer/
SKILL.md
claim-checker/
SKILL.md
consistency-auditor/
SKILL.md
final-polish/
SKILL.md
orchestrators/
full-funnel-campaign-orchestrator/
SKILL.md
booked-call-campaign-orchestrator/
SKILL.md
campaign-diagnosis-orchestrator/
SKILL.md
```
---
## Skill File Structure
Every `SKILL.md` follows this pattern:
```markdown
# Skill Name
## When to Use This Skill
[Trigger conditions]
## Inputs Required
[What the agent must gather before running]
## How to Think
[The reasoning process — the most important section]
## Output Format
[What the agent should produce]
## Do Not
[Hard constraints — what this skill must never do]
```
---
## Core Skill Categories
### Foundations
Run these first. They define reality before any copy is written.
| Skill | Purpose |
|---|---|
| `avatar-extraction` | Defines the exact person being targeted — demographics, desires, fears, language |
| `voice-of-customer-miner` | Extracts real customer language from reviews, forums, interviews |
| `offer-extraction` | Clarifies what is actually being sold and why it matters |
| `proof-harvester` | Collects credible, specific proof elements |
| `positioning-core` | Establishes the market position before a single headline is written |
### Copy Chief
The Eugene Schwartz layer — awareness, sophistication, mechanism, and conversion.
| Skill | Purpose |
|---|---|
| `schwartz-awareness-mapper` | Maps prospect awareness level (unaware → most aware) |
| `market-sophistication-analyzer` | Determines how saturated the market is and what level of claim to lead with |
| `dominant-desire-extractor` | Identifies the single strongest desire driving the prospect |
| `mechanism-builder` | Builds the unique mechanism — the "how" that makes the offer believable |
| `headline-matrix` | Generates headlines matched to awareness level and desire |
| `objection-crusher` | Surfaces and pre-empts the real objections |
| `close-architect` | Structures the call to action and close logic |
### Operator OS
Execution, platform, and scale layer.
| Skill | Purpose |
|---|---|
| `scroll-stopping-creative` | Structures ad creative for Meta, TikTok, YouTube |
| `ad-angle-multiplier` | Generates multiple angles from a single offer |
| `conversion-path-builder` | Maps the prospect journey from ad to conversion |
| `landing-page-architect` | Structures landing pages for the defined awareness level |
| `email-sequence-architect` | Builds nurture and conversion email sequences |
| `performance-diagnosis` | Diagnoses underperforming campaigns from metrics |
| `testing-roadmap` | Builds a structured creative/copy testing plan |
### QA
Output quality filters — run these last on any copy or funnel output.
| Skill | Purpose |
|---|---|
| `generic-language-killer` | Flags and rewrites vague, forgettable language |
| `claim-checker` | Validates that claims are specific, credible, and provable |
| `consistency-auditor` | Checks that messaging is consistent across all funnel touchpoints |
| `final-polish` | Final read for tone, rhythm, and conversion readiness |
### Orchestrators
Pre-built multi-skill chains for common campaign types.
| Orchestrator | Skills Chained |
|---|---|
| `booked-call-campaign-orchestrator` | avatar-extraction → offer-extraction → schwartz-awareness-mapper → mechanism-builder → ad-angle-multiplier → scroll-stopping-creative → conversion-path-builder → objection-crusher → generic-language-killer |
| `full-funnel-campaign-orchestrator` | Full chain from foundations through copy chief, operator OS, and QA |
| `campaign-diagnosis-orchestrator` | performance-diagnosis → testing-roadmap → ad-angle-multiplier |
---
## Usage with Claude Code
### Run a single skill
```
@.agents/skills/foundations/avatar-extraction/SKILL.md
My offer: 1-1 coaching for B2B founders who want to run profitable Meta ads without hiring an agency.
```
### Chain skills manually
```
Step 1 — Run avatar-extraction with the above offer brief.
Step 2 — Feed the avatar output into schwartz-awareness-mapper.
Step 3 — Feed awareness level into mechanism-builder.
Step 4 — Feed mechanism into headline-matrix.
Step 5 — Run generic-language-killer on all headlines.
```
### Use an orchestrator (recommended for full campaigns)
```
@.agents/skills/orchestrators/booked-call-campaign-orchestrator/SKILL.md
Business: B2B SaaS. Offer: 30-day onboarding sprint. Target: ops leads at 50-200 person companies.
Proof: 3 case studies, avg 40% reduction in onboarding time.
Platform: Meta ads, landing page, booked-call funnel.
```
---
## Usage with Cursor / Windsurf / Codex
Reference the skill file directly in your agent context or rules:
```
# .cursorrules or agent system prompt addition
You have access to the following advertising skills:
- .agents/skills/foundations/
- .agents/skills/copy-chief/
- .agents/skills/operator-os/
- .agents/skills/qa/
- .agents/skills/orchestrators/
When asked to writeRelated in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".