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.
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.
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
SûrThe 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 faiteExemples
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.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.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:
- Edit CHARACTER.yml first (canonical)
- Optionally update ADVENTURE.yml mirror for convenience
- 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):
- TEAR OFF / TAKE at dispenser
- Receive REF in inventory (weight: 0)
- REF points to prototype for full content
- REF can accumulate instance-specific data (annotations, condition)
Drop Protocol
When dropping a ref in a room:
- Remove from inventory
- Create pointer file in room directory:
[item-name].yml - Pointer contains: prototype path, dropped_by, condition, annotations
- 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:
- Original stays
- Instance created:
characters/don-hopkins/cookie-1.yml - 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 annexesCe 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.mdDepuis 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’OpenSkillsopenskills 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 syncMode 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.
Créer des cartes interactives avec kepler.gl
Data & IA
Création de cartes interactives et export HTML autonome avec le package Python keplergl, à partir de données géospatiales (DataFrame, GeoJSON, CSV).
Optimisation de paramètres par agent
Data & IA
Guide d'optimisation de systèmes configurables avec objectif mesurable, via des essais bornés et une recommandation fondée sur des preuves.
Relance des visiteurs ICP
Data & IA
Identifiez les utilisateurs inscrits correspondant au profil client idéal mais qui n'ont pas activé, et rédigez des messages de relance personnalisés pour les réengager.