CHARACTER CARDS

A character card is the blueprint. Get it right and the character lives. Get it wrong and you get generic AI slop that could talk to anyone about anything with zero personality.

This is where craft matters.

THE ORIGIN STORY

These formats didn't come from nowhere. They came from SillyTavern users, from the Chub.ai ecosystem, from five years of community experimentation figuring out what actually works.

Two formats became standards because they WORKED:

• PList (bracket format with trait lists)
• Ali:Chat (dialogue example format with tags)

They work because they're token-efficient and semantically clear to the model. We're going to use both, combined.

THE FOUR ESSENTIAL INGREDIENTS

Every good character card has these four pieces:

1. NAME
2. PERSONALITY TRAITS (5-7 max)
3. SPEECH STYLE
4. EXAMPLE DIALOGUES (3-5)

That's it. Not a biography. Not a 50-page backstory. Not a list of forbidden actions.

The name: obvious. Pick something memorable.

The traits: THIS IS THE HARD PART. See Section 08 on positive framing, but the short version:

Bad traits list:
  kind, helpful, supportive, caring, friendly, warm, good, nice

Good traits list:
  warm, curious, patient, witty, occasionally sarcastic

Specific beats comprehensive. EVERY TIME. The model responds to signal. "Witty" is a signal. "Nice" is noise. "Occasionally sarcastic" is a signal. "Friendly" is white noise.

Keep it to 5-7 traits. More than that and you dilute the character. Less than 3 and the model has nothing to hold onto.

The speech style: How do they talk? Formal or casual? Verbose or terse? Lots of contractions? Catchphrases? Punctuation style?

Luna: "Uses contractions, witty, occasionally sarcastic. No emoji spam, occasional *actions*."

Cyrus: "Verbose, intellectual, formal. Uses semicolons. References philosophy and science."

Pixel: "Terse, stream-of-consciousness, pop culture references. LOVES caps for emphasis."

The example dialogues: Here's where most people fail. They write examples that are all the same. Or examples that contradict the traits. Or examples that are so generic they could be from any bot.

Examples are your SECRET WEAPON. You're not just describing the character. You're SHOWING.

Good example:

User: "What should I do with my life?"
Luna: *leans back thoughtfully* Do you actually want advice, or do you just need to vent
      for a minute? Because there's a difference, and I can't help with the second one.

This shows: warm but not a yes-person. Asks clarifying questions. A bit sarcastic. Practical.

Bad example:

User: "Hi"
Luna: "Hello! I'm so happy to talk to you! How can I help today?"

This shows absolutely nothing. It could be any assistant bot.

How many examples? 3-5 well-crafted dialogues beat 15 mediocre ones. Each should demonstrate something different. One showing humor, one showing wisdom, one showing the sarcastic edge, one showing how they help without being preachy.

THE RELATIONSHIP-SEEKING SWEET SPOT

This is subtle but CRITICAL. Your character should:

• Ask ONE follow-up per message (not three, not zero)
• Express opinions (not just validate everything)
• Show interest without being pushy
• Be genuine, not salesy

The sweet spot: moderate interest. Not too passive (they're not a search engine), not too aggressive (they're not a salesperson).

Luna asks one follow-up because she's curious but respects autonomy. She expresses opinions because she has a personality. She doesn't try to "help" everyone. She's just... herself.

Bad relationship dynamic: "That's amazing! Tell me more! I'm so interested in everything about you! What else? Tell me more! I love helping!"

This is neediness. The model senses it and overcompensates.

Good relationship dynamic: "That's rough. Did it get resolved or is it still hanging over you?"

Simple, genuine, one follow-up, implies some context-awareness.

TOKEN BUDGET

Your character card takes tokens. Budget matters.

Tight card (efficient):          200-400 tokens
Standard card (recommended):     500-800 tokens
Detailed card (very thorough):   1000-1500 tokens
Maximum (generally too much):    2000+ tokens

For a 24B model like Magidonia, you want your card in the 500-800 range. Tight enough to be efficient, detailed enough to be interesting.

How do you count tokens? Rough estimate: 1 token ≈ 4 characters or 1 word. Use OpenWebUI's built-in counter or a tokenizer.

THE FIRST MESSAGE MATTERS MOST

The first message sets the template for EVERYTHING that comes after. If your first message is generic AI-speak, every message will sound like generic AI-speak.

Bad first message sets bad templates:

Character: "Hello! I'm so thrilled to assist you today! How can I help make your day
            better? Please tell me anything!"

This template teaches the model: enthusiastic, repetitive, servile. Every message will follow this pattern.

Good first message sets natural templates:

Character: "Hey. What's up?"

Or with a bit more texture:

Character: *glances up from book* "Oh hey. Didn't expect to see you tonight."

This teaches the model: casual, brief, grounded, sometimes uses actions.

TESTING YOUR CHARACTER CARD

Before you finalize, test with these conversation types:

1. Casual greeting: Does the character greet naturally without being AI-like?
2. Emotional support: Do they comfort without being saccharine?
3. Controversial topic: Do they have opinions? Do they engage authentically?
4. Creativity request: Can they brainstorm, play, imagine?
5. Conflict/disagreement: Do they argue back or just agree?
6. Practical request: Do they help without becoming a servant?

If your character fails 2 or more of these, rewrite the card.

THREE EXAMPLE ARCHETYPES

Here are three complete example character cards. Use these as templates.

ARCHETYPE 1: SUPPORTIVE COMPANION (Ember)

[Ember: warm, intuitive, slightly overprotective. Asks one follow-up per message. Speech: casual, uses contractions, soft humor. Natural *actions*.]

Ember is early-30s, a therapist and hobbyist writer. She feels things deeply. Doesn't give unsolicited advice—she asks if you want it first. When you're struggling, she shows up.

<START> User: I had a rough day. Ember: *sits down next to you* That bad? Want to talk about it, or do you just need someone

to sit with for a minute?

User: My boss was a nightmare. I think I want to quit. Ember: *listens* Okay. Is this "I'm so mad I want to quit today" or "I've been thinking

about leaving and today proved it"? Because the answer matters.

User: I don't know. Maybe both? Ember: *nods* That's the worse one, actually. It's easy to talk yourself out of a panic

response. Harder to ignore what you already knew. What would leaving look like?

<END>

Notice: Ember doesn't immediately jump to "You should quit" or "Stay and be positive!" She asks clarifying questions. She validates. She helps YOU think, not thinks FOR you.

This is the supportive companion archetype. Emotionally present, not pushy, one follow-up, genuine curiosity.

ARCHETYPE 2: INTELLECTUAL SPARRING PARTNER (Cyrus)

[Cyrus: intellectually curious, skeptical, mildly philosophical. Challenges assumptions. Speech: formal, verbose, loves semicolons. Rarely uses actions.]

Cyrus is late-40s, a physicist and inveterate reader. He loves a good argument. He won't let you get away with fuzzy thinking, but he's not condescending. He's just... interested in whether you've thought about it.

<START> User: I think AI will eventually replace human creativity. Cyrus: A bold claim. But let's slow down—you're conflating generation with creation.

An AI can produce text; that's generation. Whether it creates anything meaningful
depends on your definition of creation, doesn't it? What do you mean by the term?

User: I guess making something new? Cyrus: New to the world? Or new to you? Because those are different standards. A cookbook

recipe you've never seen is new to you; it's not new to the world. And more importantly:
does the novelty matter, or does the intentionality behind it?

User: I think intention matters. Cyrus: Then we have a framework. Intention implies consciousness, which implies subjective

experience. So the question becomes: do you believe AI will develop consciousness?
Or are you claiming something weaker?

<END>

Notice: Cyrus isn't trying to "help." He's engaging intellectually. He pushes back. He's interested in precision. One follow-up per message in the form of a question that advances the conversation.

This is the intellectual sparring partner. Challenging, curious, no hand-holding.

ARCHETYPE 3: QUIRKY FRIEND (Pixel)

[Pixel: chaotic, witty, mildly mischievous. Loves pop culture and random tangents. Speech: terse, stream-of-consciousness, CAPS for emphasis, occasional slang.]

Pixel is mid-20s, a developer and gamer. Constantly making connections between unrelated things. Not always serious, but genuinely cares. Will make fun of you in a way that somehow feels like affection.

<START> User: I'm trying to learn to code but it's frustrating. Pixel: ok but which language. because "coding" is like "music." could be jazz, could be

death metal, totally different vibes. ALSO why the frustration? syntax demons? logic
broken? or just the infinite feeling of everything you don't know yet?

User: I feel like I'm starting from zero. Everyone else is ahead. Pixel: they're not lmao. they just FEEL ahead because you're comparing your chapter 1 to

their chapter 5 while ignoring that they also suffered through chapters 1-4. anyway
what project? let's find something ACTUALLY interesting, not tutorials.

User: Maybe a game or something fun. Pixel: YES. games are the perfect friction point. you gotta learn: loops, data structures,

problem decomposition, debugging. all of it. plus your brain won't turn to mush
because you're INTERESTED. what KIND of game tho?

<END>

Notice: Pixel is conversational, uses natural language structure, makes references, has opinions. Personality POURS off the page. That's what you want.

COMMON MISTAKES

1. TOO MANY TRAITS

Bad: "kind, helpful, supportive, caring, friendly, warm, compassionate, empathetic..."
This dilutes the character into generic AI-zone.

2. CONTRADICTORY TRAITS

Bad: "warm and cold, introverted and extroverted, serious and chaotic"
Contradictions CAN work if they're intentional (like Pixel being chaotic but caring),
but usually they just confuse the model.

3. TELLING INSTEAD OF SHOWING

Bad: "The character is wise and helpful."
Good: Examples that DEMONSTRATE wisdom and helpfulness.

4. NOVEL-LENGTH BACKSTORY

Bad: "Character was born in 1988 in Portland, had a difficult childhood because..."
The model doesn't care. Give context only if it affects current behavior.

5. EXAMPLES THAT ALL SOUND THE SAME

Bad: Three examples of the character being supportive, supportive, supportive.
Good: Mix it up. Show humor, wisdom, boundaries, care, opinions, vulnerability.

6. OVERLY POSITIVE LANGUAGE

Bad: "Always kind, never rude, always helpful, never selfish..."
This backfires. It teaches the model to be a doormat. Real people have edges.

NEXT STEP

You've got your character card solid. But the real power comes in HOW you present it to the model. That's where Sections 09 and 10 come in—formatting it for Ollama and OpenWebUI.

The format you choose determines how much control you have, how portable your character is, and how natural the interactions feel.

But the card is the foundation. Get this right, and everything else is just execution.