Guarantee Generator logo

Guarantee Generator

Organization
Affitor
guarantee-generator

Create YOUR personal guarantee on top of the product's guarantee for risk reversal. Triggers on: "create a guarantee", "guarantee for my affiliate", "risk reversal", "money back guarantee", "what guarantee can I offer", "reduce buyer risk", "guarantee copy", "how to guarantee", "affiliate guarantee", "personal guarantee", "risk-free offer", "satisfaction guarantee", "results guarantee".

Overview

PublisherAffitor
Repositoryaffiliate-skills
Skill nameguarantee-generator
Stars
705
Forks
209
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 Affitor on GitHub. Read the source before you install it.

Installation

Install the Guarantee Generator 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/Affitor/affiliate-skills/tree/main/skills/landing/guarantee-generator
  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/Affitor/affiliate-skills.git /tmp/affiliate-skills
mkdir -p .claude/skills
cp -r /tmp/affiliate-skills/skills/landing/guarantee-generator .claude/skills/guarantee-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Guarantee Generator 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 Guarantee Generator 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 Guarantee Generator 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.

Guarantee Generator

Create YOUR personal guarantee that sits on top of the product's built-in guarantee. Addresses the gap: "What if I buy through your link and it doesn't work for me?" Risk reversal is the most underleveraged conversion tool in affiliate marketing.

Stage

S4: Landing — Guarantees are landing page copy. They directly impact conversion by removing the last barrier to clicking your affiliate link.

When to Use

  • User wants to increase conversion by reducing buyer perceived risk
  • User asks "what guarantee can I offer as an affiliate?"
  • User says "guarantee", "risk reversal", "risk-free", "money back"
  • After running grand-slam-offer or bonus-stack-builder to complete the offer
  • User has low conversion rates and needs to address trust/risk objections

Input Schema

yaml
product:                    # REQUIRED
  name: string              # Product name
  pricing: string           # Product price
  has_free_trial: boolean   # Does the product offer a free trial?
  has_guarantee: string     # Product's existing guarantee (e.g., "30-day money back")

your_bonuses: string[]      # OPTIONAL — bonuses from bonus-stack-builder
                            # Default: none

your_capacity: string       # OPTIONAL — "low" | "medium" | "high"
                            # How much personal time you can invest
                            # Default: "medium"

audience_fears: string[]    # OPTIONAL — top objections/fears
                            # Default: inferred from product type

Chaining from S4 bonus-stack-builder: Use bonus_stack.bonuses to reference specific bonuses in guarantee.

Chaining from S4 grand-slam-offer: Use value_equation to target the weakest component with the guarantee.

Workflow

Step 1: Gather Context

  1. Understand the product's existing guarantee/refund policy
  2. Identify top 3 buyer fears for this product category
  3. Assess user's capacity to deliver on guarantee promises

Step 2: Design Guarantee Options

Read shared/references/offer-frameworks.md for guarantee types.

Create 3 guarantee options at different commitment levels:

Option A: Light Touch (low capacity)

  • Scope: Your bonuses only
  • Example: "If my bonuses don't help you get started faster, I'll refund their value"
  • Risk to you: Minimal

Option B: Support Guarantee (medium capacity)

  • Scope: Your time + bonuses
  • Example: "If you're stuck after 30 days, I'll personally help you implement for 1 hour"
  • Risk to you: Moderate (capped time)

Option C: Results Guarantee (high capacity)

  • Scope: Specific outcome
  • Example: "If you don't [specific measurable result] in [timeframe], I'll [specific action]"
  • Risk to you: Higher (but highest conversion impact)

Step 3: Write Guarantee Copy

For each option, produce:

  1. Guarantee headline — bold, specific, confident
  2. Guarantee body — exactly what you promise, the conditions, and the timeframe
  3. Claim process — how they reach you if they want to use the guarantee
  4. Fine print — fair conditions (must actually use the product, specific timeframe)

Step 4: Recommend Best Fit

Based on your_capacity and product type, recommend one guarantee with reasoning.

Step 5: Self-Validation

  • Guarantee is specific (not vague "satisfaction guaranteed")
  • Guarantee is scoped to what YOU can deliver (not the product's features)
  • Guarantee has a clear timeframe
  • Claim process is simple and accessible
  • Guarantee is realistic — you can actually fulfill it
  • No guarantees about income or specific financial results (FTC)

Output Schema

yaml
output_schema_version: "1.0.0"
guarantee:
  product_name: string
  recommended_option: string     # "A" | "B" | "C"
  options:
    - level: string              # "light" | "support" | "results"
      headline: string
      body: string
      claim_process: string
      timeframe: string
      risk_to_you: string        # "minimal" | "moderate" | "higher"
      conversion_impact: string  # "moderate" | "high" | "very high"

chain_metadata:
  skill_slug: "guarantee-generator"
  stage: "landing"
  timestamp: string
  suggested_next:
    - "landing-page-creator"
    - "email-drip-sequence"

Output Format

## Your Guarantee: [Product Name]

### Product's Existing Guarantee
[What the product already offers]

### YOUR Guarantee Options

#### Option A: Light Touch ⚡
**"[Guarantee headline]"**
[Body copy]
- Timeframe: [X days]
- Claim: [how to claim]
- Risk to you: Minimal

#### Option B: Support Guarantee 🤝
**"[Guarantee headline]"**
[Body copy]
- Timeframe: [X days]
- Claim: [how to claim]
- Risk to you: Moderate

#### Option C: Results Guarantee 🎯
**"[Guarantee headline]"**
[Body copy]
- Timeframe: [X days]
- Claim: [how to claim]
- Risk to you: Higher

### Recommended: Option [X]
[Why this option fits your situation]

### Ready-to-Use Copy
[Complete guarantee section copy, ready to paste into landing page]

Error Handling

  • No product provided: "I need a product to create a guarantee for. Tell me the product or run affiliate-program-search first."
  • User uncomfortable with guarantees: Emphasize Option A — low risk, still impactful. "Even a light guarantee outperforms no guarantee."
  • Product has no refund policy: Note this as a risk factor. Design guarantee around YOUR bonuses only (Option A).
  • User wants to guarantee income/results: Flag FTC risk. Reframe to process guarantees: "I guarantee I'll help you implement" not "I guarantee you'll make $X".

Examples

Example 1: "Create a guarantee for my HeyGen promotion" → Research HeyGen's refund policy, identify fears (is AI video quality good enough? will I look stupid?), create 3 options ranging from "bonus refund" to "I'll personally record your first video with you."

Example 2: "I don't have much time but want to offer a guarantee for Semrush" → your_capacity=low → Recommend Option A: "If my SEO audit template doesn't save you 3+ hours, email me and I'll personally audit one page for you." Low time commitment, high perceived value.

Example 3: "Design a results guarantee" (after grand-slam-offer + bonus-stack) → Use value equation weakness (e.g., time delay) as guarantee target: "If you haven't created your first campaign within 48 hours using my setup guide, I'll do it for you on a screenshare."

Revenue & Action Plan

Expected Outcomes

  • Revenue potential: Adding a personal guarantee increases conversion rates by 15-30%. If your landing page converts at 2% with 1,000 monthly visitors = 20 sales × $50 = $1,000/month. With a guarantee at 2.5% = 25 sales = $1,250/month — an extra $250/month for 30 minutes of work
  • Benchmark: Results guarantees (Option C) show the highest conversion lift (25-30%) but carry more risk. Support guarantees (Option B) offer the best risk-reward balance (15-20% lift, capped time commitment)
  • Key metric to track: Conversion rate before vs after adding the guarantee. Also track guarantee claim rate — if <5% of buyers claim the guarantee, you're safe to offer bolder guarantees

Do This Right Now (15 min)

  1. Pick the Recommended option from the output
  2. Copy the "Ready-to-Use Copy" section and paste it directly into your landing page
  3. Add your contact email/DM as the claim channel
  4. If you don't have a landing page yet, run landing-page-creator with the guarantee section included

Track Your Results

After 30 days: did conversion rate increase? How many people claimed the guarantee? If zero claims after 50+ sales, consider upgrading to a bolder guarantee (more conversion lift, same low risk).

Next step — copy-paste this prompt: "Create a landing page for [product] with this guarantee and my bonus stack" → runs landing-page-creator

Flywheel Connections

Feeds Into

  • landing-page-creator (S4) — guarantee copy for the guarantee section
  • email-drip-sequence (S5) — guarantee as conversion lever in emails

Fed By

  • grand-slam-offer (S4) — value equation identifies what to guarantee
  • bonus-stack-builder (S4) — specific bonuses to scope guarantee around

Feedback Loop

  • conversion-tracker (S6) measures if guarantee increases conversion rate → refine guarantee scope and messaging

Quality Gate

Before delivering output, verify:

  1. Would I share this on MY personal social?
  2. Contains specific, surprising detail? (not generic)
  3. Respects reader's intelligence?
  4. Remarkable enough to share? (Purple Cow test)
  5. Irresistible offer framing? (guarantee makes saying yes feel safe)

Any NO → rewrite before delivering.

References

  • shared/references/offer-frameworks.md — Guarantee types, rules, and examples
  • shared/references/ftc-compliance.md — FTC rules on guarantee claims
  • shared/references/flywheel-connections.md — Master connection map

Frequently asked questions

What does the Guarantee Generator AI skill do?

Create YOUR personal guarantee on top of the product's guarantee for risk reversal. Triggers on: "create a guarantee", "guarantee for my affiliate", "risk reversal", "money back guarantee", "what guarantee can I offer", "reduce buyer risk", "guarantee copy", "how to guarantee", "affiliate guarantee", "personal guarantee", "risk-free offer", "satisfaction guarantee", "results guarantee".

Why use Guarantee Generator on TypingMind?

Because you install it once and use it with any model. Guarantee Generator 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 Guarantee Generator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Affitor/affiliate-skills/tree/main/skills/landing/guarantee-generator. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Guarantee Generator?

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 Guarantee Generator?

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

Is the Guarantee Generator AI skill free?

Yes. It is published on GitHub by Affitor 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 👇