ads
무료Use when you want paid ad copy for Google, Meta, or LinkedIn, including headlines, descriptions, and image briefs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Generates paid ad copy for Google, Meta, and LinkedIn. Produces platform-ready variants using a creative matrix approach with headlines, descriptions, and image briefs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
설치 방법 보기설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
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.
Before generating any content, ask the user:
Platform:
Ad format:
Wait for the user to answer before proceeding.
Ask the user:
Wait for answers before proceeding.
Read from repo automatically:
| File | What to extract |
|---|---|
docs/inputs/product_brief.md | Product name, 3 to 5 key capabilities, available links |
docs/inputs/messaging_positioning.md | Pain points (become Topics), value propositions |
docs/inputs/target_personas.md | Audience segments (become Personas) |
docs/inputs/competitor_intel.md | Competitor 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:
If the user types "skip" or the file does not exist, proceed with docs/inputs/competitor_intel.md only.
Construct the matrix from gathered inputs:
Topics (from messaging_positioning.md):
Personas (from target_personas.md):
Angles (standard set):
Matrix output: Topics x Personas x Angles
Do NOT generate all combinations. Select the 3 to 5 strongest combinations based on:
Generate 3 to 5 variants for each selected platform. Follow platform-specific rules below.
| Element | Spec | Guidance |
|---|---|---|
| Headlines | Up to 15, 30 chars each | Write 6 to 8. Front-load keywords. No punctuation at end. |
| Descriptions | Up to 4, 90 chars each | Write 3 to 4. Include CTA. One with social proof if available. |
| Display URL paths | 2 paths, 15 chars each | Use product name and action (e.g., /demo, /start) |
Google-specific rules:
| Element | Spec | Guidance |
|---|---|---|
| Primary text | 125 chars recommended, 500 max | Hook in first line. Question or bold claim. |
| Headline | 27 chars recommended, 255 max | Benefit or CTA. Short wins. |
| Description | 27 chars recommended | Often hidden. Keep optional. |
| Image guidance | 1080x1080 or 1200x628 | Describe visual concept, not just "product screenshot" |
Meta-specific rules:
| Element | Spec | Guidance |
|---|---|---|
| Intro text | 150 chars before truncation, 600 max | Lead with insight or question. Business outcome focus. |
| Headline | 70 chars recommended, 200 max | Role-specific language. Speak to the budget holder. |
| Description | 100 chars recommended | Reinforce CTA. |
| Image guidance | 1200x627 | Professional. Data visualizations work well. |
LinkedIn-specific rules:
[Pain point as question or statement]
[Consequence of not solving]
[Product as relief] + [CTA]
[Company/role] + [achieved outcome]
[How they did it with product]
[CTA: See how / Get the same]
[Action verb] + [desired outcome]
[Product makes it possible]
[CTA: Start / Try / See how]
[Competitor approach] = [problem with it]
[Your approach] = [better outcome]
[CTA: Switch / Compare / See the difference]
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]
Before delivering, verify each variant passes:
When docs are incomplete:
product_brief.md is empty, ask user for product name and 3 capabilitiesmessaging_positioning.md is empty, ask user for 3 pain pointstarget_personas.md is empty, ask user to describe 2 audience segmentscompetitor_intel.md is empty AND user skips research file, omit comparison angle entirelyWhen testimonials are missing:
When user wants more variants:
When user wants fewer variants:
Multi-platform requests:
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Use when you want paid ad copy for Google, Meta, or LinkedIn, including headlines, descriptions, and image briefs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when you want campaign performance reviewed against benchmarks, with a health score and prioritized optimization recommendations.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when you want a strict review of a marketing asset against style rules, factual accuracy, and messaging alignment.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Skill Optimization: Auto Research. Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when you want to benchmark and improve an existing repo skill through repeated evals, prompt mutations, and score tracking.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Generates SEO and AEO optimized blog posts from source content. Supports feature announcements, product launches, thought leadership, cookbooks/tutorials, report conversions, and news analysis. Outputs complete posts with TLDR, FAQ, schema markup, and internal linking recommendations.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.