Ads logo

Ads

Community
j1ngg
ads

Generates paid ad copy for Google, Meta, and LinkedIn. Produces platform-ready variants using a creative matrix approach with headlines, descriptions, and image briefs.

Overview

Publisherj1ngg
Repositorytech-marketing-framework
Skill nameads
Stars
59
Forks
8
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by j1ngg on GitHub. Read the source before you install it.

Installation

Install the Ads AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/j1ngg/tech-marketing-framework/tree/main/.claude/skills/ads
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/j1ngg/tech-marketing-framework.git /tmp/tech-marketing-framework
mkdir -p .claude/skills
cp -r /tmp/tech-marketing-framework/.claude/skills/ads .claude/skills/ads
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ads in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ads on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ads is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Paid Ads Generator

This skill transforms your product context into paid ad copy. It uses a creative matrix (Topics x Personas x Angles) to generate targeted variants for each platform.

Step 1: Platform Selection

Before generating any content, ask the user:

Platform:

  • Google Ads (Search or Display)
  • Meta (Facebook/Instagram)
  • LinkedIn
  • Multiple platforms

Ad format:

  • Search (text only)
  • Display/Feed (image + copy)

Wait for the user to answer before proceeding.


Step 2: Campaign Context

Ask the user:

  1. Campaign objective: Awareness, consideration, or conversion?
  2. Landing page URL: Where does the ad drive traffic?
  3. Specific offer or CTA: (Optional) Any promotion, demo offer, or specific action?

Wait for answers before proceeding.


Step 3: Gather Inputs

Read from repo automatically:

FileWhat to extract
docs/inputs/product_brief.mdProduct name, 3 to 5 key capabilities, available links
docs/inputs/messaging_positioning.mdPain points (become Topics), value propositions
docs/inputs/target_personas.mdAudience segments (become Personas)
docs/inputs/competitor_intel.mdCompetitor weaknesses, differentiation points

Read these files before asking for additional inputs.

Then ask:

"Do you have recent competitive research to incorporate? If you ran how-they-market on a competitor, provide the file path (e.g., output/research/competitor-name.json). Otherwise, type 'skip' and I'll use the static competitor intel."

If the user provides a path, read that file and extract:

  • Competitor messaging patterns
  • Gaps in their positioning
  • Angles they are not using

If the user types "skip" or the file does not exist, proceed with docs/inputs/competitor_intel.md only.


Step 4: Build the Creative Matrix

Construct the matrix from gathered inputs:

Topics (from messaging_positioning.md):

  • Extract 3 to 4 pain points or value propositions
  • Each becomes a core message theme

Personas (from target_personas.md):

  • Extract 2 to 3 primary audience segments
  • Each gets tailored language and emphasis

Angles (standard set):

  • Problem-agitation: Lead with the pain, twist the knife
  • Social proof: Lead with who else uses it, results they got
  • How-to: Lead with the action, product enables it
  • Comparison: Lead with competitor weakness, your strength (use competitor intel)

Matrix output: Topics x Personas x Angles

Do NOT generate all combinations. Select the 3 to 5 strongest combinations based on:

  • Campaign objective (conversion = problem-agitation, social proof)
  • Platform (LinkedIn = social proof works well for budget holders)
  • Available proof points (only use social proof if testimonials exist)

Step 5: Generate Ad Copy

Generate 3 to 5 variants for each selected platform. Follow platform-specific rules below.


Platform Rules

Google Search Ads (Responsive Search Ads)

ElementSpecGuidance
HeadlinesUp to 15, 30 chars eachWrite 6 to 8. Front-load keywords. No punctuation at end.
DescriptionsUp to 4, 90 chars eachWrite 3 to 4. Include CTA. One with social proof if available.
Display URL paths2 paths, 15 chars eachUse product name and action (e.g., /demo, /start)

Google-specific rules:

  • No exclamation marks in headlines
  • No ALL CAPS
  • No dynamic keyword insertion placeholders unless user requests
  • Headlines should work independently (they get shuffled)

Meta Ads (Facebook/Instagram)

ElementSpecGuidance
Primary text125 chars recommended, 500 maxHook in first line. Question or bold claim.
Headline27 chars recommended, 255 maxBenefit or CTA. Short wins.
Description27 chars recommendedOften hidden. Keep optional.
Image guidance1080x1080 or 1200x628Describe visual concept, not just "product screenshot"

Meta-specific rules:

  • No text covering more than 20% of image
  • Primary text: First 125 chars must hook (rest gets truncated)
  • Mobile-first: Assume thumb-stopping in feed

LinkedIn Ads

ElementSpecGuidance
Intro text150 chars before truncation, 600 maxLead with insight or question. Business outcome focus.
Headline70 chars recommended, 200 maxRole-specific language. Speak to the budget holder.
Description100 chars recommendedReinforce CTA.
Image guidance1200x627Professional. Data visualizations work well.

LinkedIn-specific rules:

  • Audience is VPs, Heads of, CTOs (budget holders, not builders)
  • Focus on business outcomes: risk, cost, time, compliance
  • Social proof from recognizable companies matters more here
  • No hashtags in ad copy

Angle-Specific Templates

Problem-Agitation

[Pain point as question or statement]
[Consequence of not solving]
[Product as relief] + [CTA]

Social Proof

[Company/role] + [achieved outcome]
[How they did it with product]
[CTA: See how / Get the same]

How-To

[Action verb] + [desired outcome]
[Product makes it possible]
[CTA: Start / Try / See how]

Comparison

[Competitor approach] = [problem with it]
[Your approach] = [better outcome]
[CTA: Switch / Compare / See the difference]

Output Format

For each variant, output:

## Variant [N]: [Topic] x [Persona] x [Angle]

**Platform:** [Google/Meta/LinkedIn]
**Objective fit:** [Why this variant fits the campaign objective]

---

### Headlines
1. [Headline] (X chars)
2. [Headline] (X chars)
3. [Headline] (X chars)
[Continue as needed per platform spec]

### Descriptions
1. [Description] (X chars)
2. [Description] (X chars)
[Continue as needed per platform spec]

### Image/Creative Brief
[2 to 3 sentence description of visual concept. Include: subject, composition, mood, text overlay if any]

### Display URL / Paths
[For Google only]

---

After all variants, include:

## Summary

| Variant | Platform | Topic | Persona | Angle |
|---------|----------|-------|---------|-------|
| 1 | [Platform] | [Topic] | [Persona] | [Angle] |
| 2 | ... | ... | ... | ... |

**Recommended test priority:**
1. [Variant N] — [Why test this first]
2. [Variant N] — [Why test this second]

Review Checklist

Before delivering, verify each variant passes:

  • Headlines under character limit for platform
  • Descriptions under character limit for platform
  • No dashes in copy (rewrite if needed)
  • No passive voice
  • No banned words (robust, seamless, leverage, cutting-edge, game-changer, revolutionary, transformative)
  • No hedging ("we believe", "consider")
  • Claims match product_brief.md exactly
  • CTA matches campaign objective
  • Social proof uses only approved customers from testimonials.md
  • Comparison angle uses real competitor intel, not fabricated weaknesses
  • Image briefs are specific enough to execute

Adaptation Notes

When docs are incomplete:

  • If product_brief.md is empty, ask user for product name and 3 capabilities
  • If messaging_positioning.md is empty, ask user for 3 pain points
  • If target_personas.md is empty, ask user to describe 2 audience segments
  • If competitor_intel.md is empty AND user skips research file, omit comparison angle entirely

When testimonials are missing:

  • Do not use social proof angle with specific company names
  • Fall back to generic framing: "[Industry] teams" or "Engineering leaders"

When user wants more variants:

  • Maximum 5 per platform per session
  • If they want more, suggest running the skill again with different angle priorities

When user wants fewer variants:

  • Minimum 2 to enable A/B testing
  • Ask which angles to prioritize given their objective

Multi-platform requests:

  • Generate variants for each platform sequentially
  • Adapt the same Topic x Persona x Angle to each platform's specs
  • Note where messaging must differ (LinkedIn = business outcome, Meta = hook fast)

Frequently asked questions

What does the Ads AI skill do?

Generates paid ad copy for Google, Meta, and LinkedIn. Produces platform-ready variants using a creative matrix approach with headlines, descriptions, and image briefs.

Why use Ads on TypingMind?

Because you install it once and use it with any model. Ads is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ads in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/j1ngg/tech-marketing-framework/tree/main/.claude/skills/ads. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ads?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ads?

As many as you like. As long as a model supports skills, you can use Ads with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ads AI skill free?

Yes. It is published on GitHub by j1ngg under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇