sniffable-python
Structure Python so LLMs can understand it in 50 lines.
Browse published AI skills maintained by SimHacker. Compare skill descriptions and follow each source repository for setup instructions.
Indexed skills
90Repository stars across indexed skills
1,416Repository forks
360Average repository stars per indexed skill
16Repository stars may repeat across skills from the same repository.
Structure Python so LLMs can understand it in 50 lines.
Everything is alive. Everything can speak.
Temporary effects system — curses are just shitty buffs
The slogan unpacked — seven readings of 'Manufacturing Intelligence'
Identity layers for characters — WHO they are vs WHAT they do
Objects clone from prototypes, not instances from classes
Quest objectives that drive narrative — the WANTS of adventure
Complete messaging system — letters, texts, goals, rewards, attachments
Interactable things in the world — the atoms of adventure
Generic bartending capabilities — pour drinks, manage tabs, know regulars
Spatial organization of knowledge in navigable directories
Security auditing for MOOLLM skills - static analysis and runtime surveillance
Plain text formatting that's readable raw AND rendered
Intelligence emerges from many simple agents (Minsky)
Implication beats simulation — imagination renders (Will Wright)
Motto: The LLM is the dice. It narrates the outcome.
Companions and group dynamics — you're never alone
Objects announce what they can do — The Sims style
Educational philosophy — learn by building inspectable things
Cannabis-specialized bartender — strains, terpenes, edibles, rolling
Big-endian file naming as semantic binding
The LLM as consistency maintainer and orchestrator
Systematic bug investigation with hypothesis tracking
Build narrative capture and sharing into the system.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.