Entités Caractère

VérifiéSûr

Système de gestion des entités jouables et non-jouables avec identité, localisation, inventaire et relations. Définit les patterns fondamentaux pour représenter les personnages dans un monde virtuel.

Spar Skills Guide Bot
Data & IAIntermédiaire
04/03/2026
Claude CodeCursorCodex
#character-state#yaml-schema#world-modeling#entity-relationships#state-ownership

Recommandé pour

Synthèse automatique

Définit les conventions YAML pour représenter un personnage dans un monde de type MOO : distinction entre fichier d'origine et position courante, propriété canonique de l'état, arborescence des fichiers et relations entre entités.

Points forts

  • Sépare nettement `home` (chemin de fichier, immuable) et `location` (position à l'exécution), ce qui garde les diffs git stables.
  • Établit CHARACTER.yml comme source de vérité pour location, inventaire, or, traits, relations et souvenirs, les fichiers de monde n'étant que des miroirs optionnels.
  • Donne des règles d'arborescence concrètes : répertoire + CHARACTER.yml si le personnage a besoin de stockage, fichier unique s'il vit dans une pièce.
  • Modélise les relations indexées par identifiant d'entité, avec sentiment, souvenirs et espoirs — compact et lisible.

Limites

  • Document de convention uniquement : aucune validation, outillage ni procédure de migration en cas de conflit entre état canonique et miroir.
  • Très spécifique à l'écosystème MOOLLM ; suppose l'existence des skills card, room et adventure.
  • Le sidecar CARD.yml est mentionné et renvoyé à un autre skill, sans être spécifié ici.
Quand l'utiliser

À utiliser lorsqu'on modélise un nouveau joueur, PNJ ou compagnon et qu'il faut décider où vit son état et comment consigner ses relations.

Quand l'éviter

À éviter si l'on cherche une machine à états exécutable ou une logique de validation plutôt qu'une convention d'organisation de fichiers.

Analyse de sécurité

Sûr
Score qualité82/100

The skill is documentation for a world/character simulation system. It only declares read_file and write_file, and all described operations concern editing YAML/Markdown state files within the character/adventure directory structure. There are no shell commands, network calls, credential access, encoded payloads, or destructive operations; the content is purely narrative data modeling.

Aucun point d'attention détecté

Comment cette analyse est faite

Exemples

New pub NPC
Create a CHARACTER.yml for a new bartender NPC in the pub room: give it a home, a starting location, a short inventory and a relationship entry toward don-hopkins.
Directory or single file
Should the stray cat in the cat cave get its own characters/ directory or stay as pub/cat-cave/terpie.yml? Decide using the character skill's belonging-vs-visiting rule.
State update precedence
Don just picked up a lamp and moved to the coatroom. Update the canonical state in the correct file and tell me whether ADVENTURE.yml needs a mirror update too.

name: character description: Core patterns for all characters — home, location, relationships, inventory allowed-tools:

  • read_file
  • write_file tier: 1 protocol: CHARACTER-AS-ENTITY related: [cat, dog, society-of-mind, persona, room, buff, needs, mind-mirror, incarnation, party] tags: [moollm, entity, location, relationships, inventory, identity]

Character

"File is identity. Location is presence. Relationships are memory."

Characters are entities that exist in the world. Players, NPCs, companions, cats — all are characters.

Home vs Location

The critical distinction:

player:
  home: characters/don-hopkins/   # Where FILE lives (never moves)
  location: pub/                  # Where CHARACTER is (changes)

| Concept | Purpose | Changes? | |---------|---------|----------| | home | Physical file path | NEVER | | location | Current position in world | Runtime |

Why: Stability, safety, git-friendly diffs.

Character State Ownership (CANONICAL vs MIRROR)

Characters own their own state. The CHARACTER.yml file is CANONICAL for:

| State | Stored In | Notes | |-------|-----------|-------| | location | CHARACTER.yml | Where the character is in the world | | inventory | CHARACTER.yml | What the character carries | | gold | CHARACTER.yml | Character's resources | | sims_traits | CHARACTER.yml | Personality (Sims-style) | | mind_mirror | CHARACTER.yml | Personality (Leary-style) | | relationships | CHARACTER.yml | Who they know and feel about | | memories | CHARACTER.yml | What they remember |

ADVENTURE.yml (or other world state files) may MIRROR some state for convenience, but CHARACTER.yml is always the source of truth.

# CHARACTER.yml (CANONICAL — edit this first)
player:
  location: coatroom/  # CANONICAL — character owns their location
  inventory: [lamp]    # CANONICAL — character owns their inventory

# ADVENTURE.yml (MIRROR — optional convenience copy)
player:
  location: coatroom/  # Mirror of CHARACTER.yml

When updating state:

  1. Edit CHARACTER.yml first (canonical)
  2. Optionally update ADVENTURE.yml mirror for convenience
  3. If conflict, CHARACTER.yml wins

Why this matters:

  • Characters can be used across multiple adventures
  • Character state persists independent of adventure state
  • Clear ownership prevents conflicts

Directory Structure

Players (Need Junk Storage)

characters/
  don-hopkins/           # Directory name = character ID
    CHARACTER.yml        # The character file
    CARD.yml             # Optional: makes character a playable card
    cookie-1.yml         # Dispensed items
    notes.yml            # Personal stuff

Sidecar Cards

Any character directory can have a CARD.yml sidecar to make the character card-playable:

# characters/don-hopkins/CARD.yml
card:
  for: ./CHARACTER.yml
  type: hero-story
  tradition: "Pie menus, SimCity, constructionism"
  
  advertisements:
    SUMMON:
      description: "Activate Don's design traditions"

See card skill for full pattern.

Embedded NPCs (Room is Home)

pub/
  bartender.yml          # Lightweight NPC
  cat-cave/
    terpie.yml           # Full family as single files
    stroopwafel.yml
    kitten-myrcene.yml

Rule: Need junk storage? → directory/CHARACTER.yml. Just a character in a room? → character-name.yml.

File Belonging

"Does this character BELONG to a place, or VISIT places?"

| Type | Home | Examples | |------|------|----------| | Belongs | Room directory | pub/bartender.yml, maze/skeleton.yml | | Visits | Own directory/repo | characters/don.yml, github:user/char.yml |

Relationships

Key = other entity ID. From is implicit (file owner).

# In marieke.yml
relationships:
  don-hopkins:
    feeling: "A regular now. One of the good ones."
    memories:
      - "The day he sat with Myr for three hours"
    hopes: "I hope he keeps coming back."
    
  self:  # Private inner data!
    identity: "Third generation. This is who I am."
    fears: "That I'm not enough."
    mantra: "The cats need me. I need them."

Targets

Relationships can point to anything:

  • Characters (don-hopkins)
  • Objects (brass-lamp)
  • Locations (pub/, maze/)
  • Concepts (acme-corporation)
  • Yourself (self) — private storage!

Levels

| Level | Score | Effect | |-------|-------|--------| | Stranger | 0-15 | -10% success, 50% effects | | Familiar | 41-60 | +10% success, 100% effects | | Friend | 61-80 | +20% success, greetings | | Soulmate | 91-100 | +50% success, psychic link |

Inventory (Bidirectional)

Objects stay in their home. Picking up = references, not file moves.

# Don picks up kitten:

# In don-hopkins.yml
inventory:
  - pub/cat-cave/kitten-myrcene.yml
  
# In kitten-myrcene.yml
location: characters/don-hopkins/inventory

# File didn't move. Location changed.

Reset: Snap objects back home: location = home.

Inventory Protocol (Objects vs Refs)

Items in inventory can be OBJECTS or REFS:

| Type | Weight | Bulk | What It Is | |------|--------|------|------------| | Object | Yes | Yes | The actual item (lamp, sword, lunchbox) | | Ref | No | No | Lightweight pointer to a prototype |

Refs are perfect for: catalogs, manuals, maps, guides — things you reference but don't physically carry.

inventory:
  # Full object
  - item: "Brass Lantern"
    type: object
    source: start/lamp.yml
    weight: 2
    fuel: 100
    
  # Lightweight ref
  - item: "ACME Catalog"
    type: ref
    prototype: street/lane-neverending/w1/acme-catalog.yml
    annotations: ["circled portable hole", "margin notes on physics"]

Dispenser Protocol

Some objects dispense refs (like the ACME Catalog Dispenser):

  1. TEAR OFF / TAKE at dispenser
  2. Receive REF in inventory (weight: 0)
  3. REF points to prototype for full content
  4. REF can accumulate instance-specific data (annotations, condition)

Drop Protocol

When dropping a ref in a room:

  1. Remove from inventory
  2. Create pointer file in room directory: [item-name].yml
  3. Pointer contains: prototype path, dropped_by, condition, annotations
  4. Item now lives in that room (can be picked up again)
# kitchen/acme-catalog.yml — dropped instance
object:
  name: "ACME Catalog"
  type: instance
  prototype: ../street/lane-neverending/w1/acme-catalog.yml
  origin: "Torn from dispenser at 4 Lane Neverending"
  dropped_by: "don-hopkins"
  annotations: ["DO NOT ORDER Rocket Skates", "circled portable hole"]

Capacity

inventory_capacity:
  max_weight: 45    # Varies by character
  max_bulk: 10
  refs_free: true   # Refs don't count!

Dispensers (Full Objects)

Some objects clone full objects on pickup. Original stays, you get instance.

# pub/cookie-jar.yml
object:
  id: cookie-jar
  dispenser: true
  instance_template: cookie

When picked up:

  1. Original stays
  2. Instance created: characters/don-hopkins/cookie-1.yml
  3. Instance inherits from prototype

Ephemeral vs Persistent

| Type | File? | Use For | |------|-------|---------| | Ephemeral | No | Quick transaction, one-line dialog | | Persistent | Yes | Ongoing negotiation, relationship state |

Rule: Will this matter in 5 minutes? No → ephemeral. Yes → persistent.

Stats

Two systems:

| System | Scale | Origin | |--------|-------|--------| | Sims Traits | 0-10 | The Sims 1 | | Mind Mirror | 0-7 | Timothy Leary |

Sims Traits

  • Neat — Sloppy ↔ Organized
  • Outgoing — Shy ↔ Social
  • Active — Lazy ↔ Energetic
  • Playful — Serious ↔ Fun-loving
  • Nice — Grouchy ↔ Kind

Distribution: Original Sims used 25 points across 5 traits. Good guideline.

Commands

| Command | Effect | |---------|--------| | LOOK AT [char] | Description, visible state | | TALK TO [char] | Conversation based on relationship | | HELLO [char] | Initiate social interaction | | GOODBYE [char] | End interaction, dismiss ephemeral | | EXAMINE [char] | Deeper observation |

External Homes

Characters can live in other repositories:

player:
  home: github:donhopkins/characters/don.yml
  location: pub/

Code Locations

Characters can be "at" a specific line in a file:

character:
  name: schema-expert
  home: characters/experts/schema-expert/
  location: "@central/apps/insights/pyleela/brain/Schema.py:142"
  # Currently examining line 142 of Schema.py

Location path syntax for code:

  • @repo/path/to/file.py — at a file
  • @repo/path/to/file.py:42 — at specific line
  • @repo/path/to/file.py:42-67 — examining line range
  • @repo/path/dir/ — in a directory (room)
> where is schema-expert?
schema-expert is at @central/apps/insights/pyleela/brain/Schema.py:142
examining the createSyntheticItemIfNeeded method

See room/ for directories as rooms and files as objects.

Party-Based Code Review

Form parties of expert characters to explore code together:

> summon drescher-expert, devops-expert, security-auditor
Party formed: [drescher-expert, devops-expert, security-auditor]

> party: review @central/tools/edgebox/scripts/ingest.py
drescher-expert: "The claim_task function is a schema pattern..."
devops-expert: "The PostgreSQL SKIP LOCKED is elegant..."
security-auditor: "I see proper parameter binding, good..."

> party: focus on lines 280-350
[Multi-perspective analysis of the code section]

Party Navigation:

> go to @central/apps/insights/pyleela/brain/
> enter Schema.py
> look at lines 140-180
> search for "synthetic"
> follow import ExtendedContext
> back
> party: gather here

Each party member brings their expertise. The LLM simulates all perspectives in a single call (see speed-of-light/).

Inner Voice (YAML Jazz)

Comments ARE the character's thoughts:

needs:
  hunger: 3
  # I could eat. But I'm comfortable here.
  # The kittens are asleep on my lap.

Motivation as Declared, Not Felt

Important distinction: When CHARACTER.yml specifies motivations, goals, or needs, these are declarative descriptions — they tell the LLM how to roleplay this character.

The LLM does not genuinely want to achieve these goals. It performs wanting them.

motivations:
  - protect_the_kittens     # Declared, not felt
  - find_good_food          # The LLM roleplays caring about this
  - explore_new_places      # No intrinsic drive — just character data

Why this matters:

  • No genuine agency — the character is a simulacrum
  • Roleplay all the way down (Shanahan)
  • Declared motivations are performed, not experienced
  • This is fine when acknowledged, problematic when mistaken for genuine will

See: representation-ethics/examples/aggregate-patterns.yml for the distinction between aggregate simulation (valid) and individual prediction (not valid).

K-line: MOTIVATION-ROLEPLAY

Du fichier au premier essai

Le téléchargement contient exactement le contenu affiché sur cette fiche. Cette copie peut différer de la dernière version du dépôt source.

Consulter la source et ses fichiers annexes

Ce téléchargement contient uniquement SKILL.md. Les scripts, références, modèles et dépendances éventuels ne sont pas inclus. Récupérez les fichiers nécessaires depuis la source en conservant leur arborescence avant de poursuivre.

1. Télécharger le fichier

Télécharger SKILL.md

Depuis la racine d’un projet de test, enregistrez le fichier sous .skill-downloads/character-entities-mmbizjqk/SKILL.md, ou utilisez la commande suivante. Ce dossier sert à examiner la skill avant son installation.

Commande pour macOS/Linux ou WSL : un shell POSIX et curl sont nécessaires. Sous Windows sans WSL, utilisez le bouton de téléchargement et créez le dossier manuellement.

mkdir -p '.skill-downloads/character-entities-mmbizjqk' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/character-entities-mmbizjqk/download' --output '.skill-downloads/character-entities-mmbizjqk/SKILL.md.part' && mv '.skill-downloads/character-entities-mmbizjqk/SKILL.md.part' '.skill-downloads/character-entities-mmbizjqk/SKILL.md'

2. Vérifier les prérequis

Lisez SKILL.md avant de l’utiliser. Si le fichier cite des scripts ou services externes, examinez-les et préparez les accès nécessaires dans votre environnement de test.

Aucune section de prérequis reconnue dans ce fichier. Cela ne signifie pas qu’il est autonome : les bibliothèques, outils et accès peuvent être cités ailleurs dans le contenu ou dans le dépôt source.

Les plateformes de la fiche sont des indications du catalogue. Les chemins ci-dessous suivent la documentation des outils ; ils ne prouvent pas que cette skill y a été exécutée. Aucune version minimale de ces outils n’est attestée pour cette fiche.

3. Charger la skill

Après vérification, copiez le dossier complet dans le projet avec l’une des commandes ci-dessous, puis ouvrez une nouvelle session de l’outil. La commande s’arrête si un dossier du même nom existe déjà : comparez les fichiers avant de le remplacer.

Claude Code
test -f '.skill-downloads/character-entities-mmbizjqk/SKILL.md' && test -s '.skill-downloads/character-entities-mmbizjqk/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/character' && cp -R '.skill-downloads/character-entities-mmbizjqk' '.claude/skills/character'

Cursor
test -f '.skill-downloads/character-entities-mmbizjqk/SKILL.md' && test -s '.skill-downloads/character-entities-mmbizjqk/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/character' && cp -R '.skill-downloads/character-entities-mmbizjqk' '.cursor/skills/character'

Codex
test -f '.skill-downloads/character-entities-mmbizjqk/SKILL.md' && test -s '.skill-downloads/character-entities-mmbizjqk/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/character' && cp -R '.skill-downloads/character-entities-mmbizjqk' '.agents/skills/character'

OpenSkills

OpenSkills doit déjà être installé. La procédure locale install/read est contrôlée avec OpenSkills 1.5.0, qui exige Node.js ≥ 20.6.0. Aucun slug du catalogue n’est résolu automatiquement.

Installation officielle d’OpenSkills
openskills install './.skill-downloads/character-entities-mmbizjqk'

openskills read 'character-entities-mmbizjqk'

La lecture doit afficher le contenu du fichier installé et son dossier de base. Elle ne lance ni la skill ni ses dépendances.

Pour un agent qui lit AGENTS.md, synchronisez ensuite l’index. Cette commande modifie AGENTS.md : relisez le diff avant de l’utiliser.

openskills sync

Mode manuel ou autre outil : joignez SKILL.md à une conversation, ou ouvrez-le dans un agent capable de lire les fichiers. Ajoutez les ressources annexes nécessaires. Il n’existe pas de dossier universel reconnu par tous les outils.

4. Faire un premier essai

Utilisez une entrée courte et fictive : un endpoint d’API, un petit document ou un brief d’interface. Dans une nouvelle conversation, joignez le fichier ou donnez son chemin à l’agent, puis adaptez cette demande :

Lis .skill-downloads/character-entities-mmbizjqk/SKILL.md et applique ses instructions à cet exemple : [décrire une entrée de test]. Indique les fichiers, dépendances ou accès qui manquent. Produis le résultat demandé par la skill sans inventer de données ni exécuter de script non examiné.

Résultat attendu : une sortie correspondant aux instructions de la skill, ou une liste précise des prérequis manquants. Une simple confirmation de lecture ne valide pas le premier usage. Si une ressource externe est indisponible, ce parcours reste à tester.

Skills similaires