Paid Channel Prioritizer logo

Paid Channel Prioritizer

OrganizationPopular
gooseworks-ai
paid-channel-prioritizer

For founders who don't know where to start with paid ads. Analyzes ICP, competitor ad presence, budget constraints, and product type to recommend which 1-2 paid channels to start with and provides a 90-day ramp plan. Prevents the common mistake of spreading a small budget across too many platforms.

Overview

Publishergooseworks-ai
Repositorygoose-skills
Skill namepaid-channel-prioritizer
Stars
1.2K
Forks
208
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by gooseworks-ai on GitHub. Read the source before you install it.

Installation

Install the Paid Channel Prioritizer 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.
  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/gooseworks-ai/goose-skills.git /tmp/goose-skills
mkdir -p .claude/skills
cp -r /tmp/goose-skills/skills/ads/composites/paid-channel-prioritizer .claude/skills/paid-channel-prioritizer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Paid Channel Prioritizer 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 Paid Channel Prioritizer 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 Paid Channel Prioritizer 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 Channel Prioritizer

Answer the question every early-stage founder asks: "Where should I run ads?" This skill analyzes your product, ICP, competitors, and budget to recommend the right 1-2 channels to start with — plus a 90-day plan to get there.

Core principle: A $3K/month ad budget split across Google, Meta, LinkedIn, and TikTok means $750/channel — not enough for any platform to learn and optimize. This skill picks the best 1-2 channels and concentrates budget where it'll compound fastest.

When to Use

  • "Where should I run ads?"
  • "Which ad platform is best for us?"
  • "I have $X/month for ads — where should I spend it?"
  • "Should I do Google Ads or Facebook Ads?"
  • "Help me choose a paid channel"

Phase 0: Intake

  1. Product name + URL — What are you selling?
  2. Business model — SaaS / Marketplace / E-commerce / Service / App
  3. B2B or B2C? — Drives channel selection heavily
  4. ICP — Who are you selling to? (Role, company size, industry)
  5. Monthly ad budget — Be honest — how much can you spend?
  6. Average deal size / LTV — What's a customer worth?
  7. Current acquisition channels — How are you getting customers today? (Organic, referral, outbound, etc.)
  8. Competitor names — 3-5 competitors
  9. Landing page ready? — Do you have a dedicated LP or just a homepage?
  10. Conversion goal — Free trial / Demo / Purchase / Lead magnet download

Phase 1: Channel Scoring

1A: Buyer Intent Analysis

Where does your buyer look when they have a problem?

Buyer Journey StageLikely ChannelSignal
"I need a tool for X" (active search)Google SearchHigh-intent keywords exist
"I'm browsing and see something relevant" (passive)Meta (FB/IG)Visual/emotional product
"I need to solve this at work" (professional)LinkedInB2B decision-maker targeting
"Everyone's talking about this" (social proof)Twitter/X AdsCategory is trending
"I watch content about this" (education)YouTubeLong consideration cycle
"I discovered it through content" (entertainment)TikTokB2C, young audience, visual

1B: Competitor Ad Presence Research

Use web search to check publicly accessible ad libraries and gather competitor ad intelligence:

web_search: site:facebook.com/ads/library "[competitor name]"
web_search: "[competitor name]" Google Ads OR PPC OR paid search
web_search: "[competitor name]" LinkedIn Ads OR sponsored
web_search: "[competitor name]" advertising strategy

The Meta Ad Library (facebook.com/ads/library) and Google Ads Transparency Center (adstransparency.google.com) are publicly accessible — search them directly to see what competitors are running.

Build a competitor channel map:

CompetitorGoogleMetaLinkedInTwitterYouTubeTikTok
[Comp A][Active/Not found][N ads][Active/Not found].........
[Comp B]..................

Insight: Where competitors are spending = validated channel. Where they're absent = opportunity or dead end.

1C: Channel Scoring Matrix

Score each channel for this specific product:

Factor (Weight)Google SearchMetaLinkedInYouTubeTwitterTikTok
Buyer intent (25%)[1-10][1-10][1-10][1-10][1-10][1-10]
Targeting precision (20%)[1-10][1-10][1-10][1-10][1-10][1-10]
Competitor validation (15%)[1-10][1-10][1-10][1-10][1-10][1-10]
Budget efficiency (15%)[1-10][1-10][1-10][1-10][1-10][1-10]
ICP reachability (15%)[1-10][1-10][1-10][1-10][1-10][1-10]
Creative requirements (10%)[1-10][1-10][1-10][1-10][1-10][1-10]
Weighted Score[X/10][X/10][X/10][X/10][X/10][X/10]

Channel Context Notes

ChannelBest ForWorst ForMin Viable BudgetCreative Needs
Google SearchHigh-intent capture, B2B, established categoryNew categories nobody searches for$1K/moText ads (low barrier)
Meta (FB/IG)Visual products, B2C, retargeting, lookalikesNiche B2B with tiny audience$1K/moImages + video (medium)
LinkedInB2B enterprise, specific titles/industriesB2C, budget-conscious startups$3K/moProfessional content (medium)
YouTubeEducation-heavy products, long considerationImpulse purchases, tiny budgets$2K/moVideo production (high)
Twitter/XDev tools, trending categories, tech audiencesMainstream B2C, precise targeting$1K/moShort-form copy (low)
TikTokB2C, Gen Z/millennial, visual/fun productsB2B enterprise, older audience$500/moShort video (high frequency)

Phase 2: Recommendation

Primary Channel Selection

Pick the #1 channel based on:

  1. Highest weighted score
  2. Budget viability (can they afford minimum viable spend?)
  3. Creative readiness (can they produce the required content?)

Secondary Channel Selection

Pick channel #2 only if:

  • Budget > $3K/month (enough for two channels)
  • It serves a different funnel stage than channel #1
  • It doesn't require creative they can't produce

Budget Allocation

Budget LevelRecommendation
< $1.5K/mo1 channel only — concentrate everything
$1.5K-3K/mo1 primary + retargeting — primary channel + Meta/Google retargeting ($300-500)
$3K-7K/mo2 channels — 65% primary, 25% secondary, 10% retargeting
$7K+/mo2-3 channels — diversify with testing budget

Phase 3: 90-Day Ramp Plan

Month 1: Foundation (Days 1-30)

Week 1: Setup

  • Set up conversion tracking (Pixel, GTM, GA4)
  • Create landing page (if needed)
  • Build initial audiences / keyword list
  • Launch 2-3 ad variants on primary channel

Week 2-3: Learn

  • Collect data — do NOT optimize yet
  • Monitor for setup issues (tracking, disapprovals, targeting)
  • Minimum 500 impressions per variant before judging

Week 4: First Optimization

  • Pause worst-performing ad variant
  • Add 1-2 new variants based on early signals
  • Adjust bids/budgets based on CPM/CPC data

Month 2: Optimize (Days 31-60)

  • Review conversion data — any ads producing results?
  • Launch retargeting campaign (if not already)
  • Test new audiences / keywords
  • A/B test landing pages (if conversion rate is low)
  • Begin secondary channel test (if budget allows)

Month 3: Scale or Pivot (Days 61-90)

  • If working: Increase budget 30-50% on winning audiences/keywords
  • If not working: Diagnose (bad targeting? bad LP? bad offer?)
  • Evaluate secondary channel test results
  • Re-run this analysis with real performance data to validate or adjust channel selection

Phase 4: Output Format

markdown
# Paid Channel Strategy — [Product Name] — [DATE]

## Your Profile
- Product: [Name]
- Model: [SaaS / B2C / etc.]
- ICP: [Summary]
- Monthly budget: $[X]
- Conversion goal: [Goal]

---

## Channel Scoring

| Channel | Score | Verdict |
|---------|-------|---------|
| [Top channel] | [X/10] | **PRIMARY — Start here** |
| [Second channel] | [X/10] | **SECONDARY — Add in month 2** |
| [Third channel] | [X/10] | Test later if budget grows |
| [Others] | [X/10] | Not recommended now |

---

## Why [Primary Channel]

**Top reasons:**
1. [Reason — tied to their specific product/ICP]
2. [Reason]
3. [Reason]

**What competitors are doing there:** [Evidence]

**Minimum viable budget:** $[X]/mo
**Expected cost per conversion:** $[X-Y] range (category benchmark)

---

## Why NOT [Channel They Might Assume]

[Brief explanation of why the obvious choice isn't right — e.g., "LinkedIn is too expensive for your $2K budget — you'd only reach ~500 people/month"]

---

## Budget Allocation

| Channel | Monthly Budget | Purpose |
|---------|---------------|---------|
| [Primary] | $[X] | [Prospecting / Lead gen] |
| [Retargeting] | $[X] | [Bring back visitors] |
| [Secondary — Month 2] | $[X] | [Test — evaluate after 30 days] |

---

## 90-Day Ramp Plan

### Month 1: [Primary Channel] Launch
[Specific weekly actions]

### Month 2: Optimize + Test [Secondary]
[Specific actions]

### Month 3: Scale or Pivot
[Decision criteria]

---

## Pre-Launch Checklist
- [ ] Landing page live and tested
- [ ] Conversion tracking installed and verified
- [ ] Initial audiences / keywords built
- [ ] 3 ad variants ready
- [ ] Daily budget cap set ($[X]/day)
- [ ] Weekly review scheduled

Save to channel-strategy-[YYYY-MM-DD].md in the current working directory (or user-specified path).

Cost

ComponentCost
Competitor ad research (web search)Free
Channel analysis and planningFree (LLM reasoning)
TotalFree

Tools Required

  • web_search — for competitor research, ad library lookups, and channel validation

Trigger Phrases

  • "Where should I run ads?"
  • "Which ad platform should I use?"
  • "Help me pick a paid channel"
  • "Google Ads or Facebook Ads?"
  • "I have $[X]/month — where should I advertise?"
  • "What paid channels work for [product type]?"

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Paid Channel Prioritizer AI skill do?

For founders who don't know where to start with paid ads. Analyzes ICP, competitor ad presence, budget constraints, and product type to recommend which 1-2 paid channels to start with and provides a 90-day ramp plan. Prevents the common mistake of spreading a small budget across too many platforms.

Why use Paid Channel Prioritizer on TypingMind?

Because you install it once and use it with any model. Paid Channel Prioritizer 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 Paid Channel Prioritizer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/gooseworks-ai/goose-skills/tree/main/skills/ads/composites/paid-channel-prioritizer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Paid Channel Prioritizer?

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 Paid Channel Prioritizer?

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

Is the Paid Channel Prioritizer AI skill free?

Yes. It is published on GitHub by gooseworks-ai 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 👇