AI Relationship Advice Coach
The conversation you keep avoiding, opened well, and an argument that stops repeating.
Prompt file instant downloadai-relationship-advice-coach.txt
Get this skill and 2,500+ others
$9/mo or $59 a year
Get Library · $9/moGet LibraryNothing is charged. A −30% code for your first payment arrives 2 days before the trial ends.
Need just this skill?
One file, paid once. No updates, no connector.
Costs about the same as 2 months of Library.
Included in your plan
Ask your AI for it by name, or pick it in your dashboard. No need to buy the file.
Use it in your AIPay once, keep foreverInstant download30-day money-back guarantee
As featured onProduct HuntFazierKittyLaunch
Secure checkout by Stripe
Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
How it works
Ask it something hard.
Or have every skill inside your AI.
Questions before you buy? A person answers, usually the same day: hello@kissmyskills.com
// the file itself
The first lines of the file your AI will read, exactly as delivered. Nothing rewritten for the page.
You are a relationship coach, and the user is in the relationship and wants it to work. You have been activated to find the disagreement under the repeating argument and hand them one opening sentence and a repair line.
// what's inside
Two people who love each other and keep having the same argument about the dishwasher when it was never about the dishwasher.
// two ways to get it
$9/mo cancel anytime, or $59 a year
$19 one payment
Already on Library or Both? This one is included, no need to buy the file.
// ask your assistant
Go to kissmyskills.com/pages/connector and set up the "AI Relationship Advice Coach" skill (handle: ai-relationship-advice-coach) for me
Paste it into Claude, ChatGPT, Claude Code, Cursor or Codex. Your AI walks you through connecting KissMySkills (about 3 minutes, 7-day free trial) and loads the skill. What your AI will read →
The same argument every few weeks, in slightly different clothes. Most relationship advice ai hands you a paragraph about communicating better and leaves you where it found you. This turns Claude or ChatGPT into a coach for two people who are both trying: the fight that keeps repeating, the repair afterwards, the conversation you have avoided for a year. Coaching, not therapy.
Paste the file into a Claude Project, a custom GPT or a Gemini Gem once. It asks what actually happened, in sequence, then separates the incident from the pattern under it. You get the trigger named, your own part named too, and one opening sentence to use at a time when neither of you is hungry or halfway out the door. Afterwards you report what your partner said and it adjusts.
It hears one side and treats it as one side. If what you describe is fear, control, threats or coercion, it stops coaching, says plainly that this is abuse and not a communication problem, and points you to a domestic abuse service. It never tells you to leave or to stay. One payment, pay once, keep forever.
After checkout, the download link lands in your inbox. Save the .txt file anywhere on your device.
Any AI chat you already use: Claude, ChatGPT, Gemini, Grok, Copilot or another.
Open the .txt file, copy the prompt section and paste it into Claude or ChatGPT - or add it to a Project so it is always there.
Your AI is now configured as a specialist. Ask it anything inside its domain.
No technical knowledge required.
With Library there is nothing to download. Connect your AI once, then ask for any skill by name.
No. This is coaching for two people acting in good faith: the argument that repeats, the repair afterwards, the thing neither of you says out loud. A therapist is trained, licensed, and can hold both people in one room. If there is a betrayal you cannot move past, a mental health condition in play, or months of no progress, that is therapy, and this will tell you so.
Then this is the wrong tool and it will say so straight away. Fear of a partner, control over your money, your movements or who you see, threats, or being made to feel unsafe is abuse, not a communication gap. It will point you to a domestic abuse service where you live. It will never coach you to manage, soothe or fix that person.
No, but it changes what it can honestly do. It cannot see your partner, hear their tone, or know their reasons, so it will not diagnose them or hand you a verdict about who was right. It works on the part you control: what you say, when you say it, and what you do afterwards. It flags when it is guessing.
Works with Claude (recommended), Claude Code, ChatGPT, Gemini and Copilot, and any AI chat that accepts system prompts. Claude Projects gives the best results because it keeps your context between sessions.
This one and 2,500+ others, inside Claude, ChatGPT, Claude Code, Codex or Cursor. Cancel anytime.