con un clic
moollm
moollm contiene 101 skills recopiladas de SimHacker, con cobertura ocupacional por repositorio y páginas de detalle dentro del sitio.
Skills en este repositorio
Portable tokens of capability, identity, and access
The grammar rules that make MOOLLM's file system object-oriented. Plural directory names declare element type; UPPERCASE marker files declare interface exports (COM-style, minus the UUIDs); directories are implementation classes exporting every interface whose marker file sits at their root.
Mother skill for platform-descriptor sister skills. Defines what a BIOME is — a bounded region of an ecosystem (coexisting, exchanging, never isolated) for one platform you operate — and what files, subdirectories, and cross-biome bridges every daughter biome inherits.
A skill is documentation that learned to do things.
GNU Emacs as a stateful Lisp machine for agents — daemon, moo-* protocol, emacs.py router, emacs:// URLs, spoken grammar, play-learn-lift.
Schemapedia — schema plugins, families, gateways, formats.yml, mechanism_relations; self-object kernel; delegates to sibling skills.
Datasette — serve SQLite over HTTP with metadata YAML, JSON API, plugins; MOOLLM path from cursor-mirror export.
Unconventional PostgreSQL optimization techniques
Server PostgreSQL operations — connect, migrate, Timescale, pgvector, introspection; delegates deep tuning to postgres-optimization.
Embedded SQLite — sqlite3 CLI, pragmas, JSON1, WAL, migrations; pairs with cursor-mirror; server DBs use postgres.
Objects clone from prototypes, not instances from classes
YAML is sheet music. The LLM is the jazz musician. Comments are soul.
Wake up, orient, and warm the context with foundational MOOLLM knowledge
Smart templates that understand semantic intent, not just string substitution
Protocol names ARE K-lines.
Minsky frames, Drescher schemas, interchange registry, and MOOLLM K-lines — distinct layers.
Build, lint, ingest, compose Drescher-style schemas
Drescher's computational theory of causal learning
Document-first automation — the doc is the source of truth
Be conservative in what you send, liberal in what you accept.
Survive first. Be correct later.
Temporary effects system — curses are just shitty buffs
Intermediate scope for inheritance — like OpenLaszlo's <node>
Runtime context passed to compiled closures — the world as seen from inside
Canine interactions, loyalty mechanics, and pack dynamics
Navigation links between rooms — the edges of the memory palace
Quest objectives that drive narrative — the WANTS of adventure
I mine pixels for atoms. Reality is just compressed resources.
Factorio-style logistics — items flow automatically between containers
Interactable things in the world — the atoms of adventure
Complete messaging system — letters, texts, goals, rewards, attachments
Rooms are intertwingled navigable activation context maps. Entering = calling. Exiting = returning.
Dual Python/JavaScript adventure runtimes — always in sync
Security auditing for MOOLLM skills - static analysis and runtime surveillance
Structure Python so LLMs can understand it in 50 lines.
I see what you describe. Let me show it to others.
Motto: The world grows where curiosity leads.
Manufacturing Intelligence — Leela AI develops MOOLLM for practical use and industrial exploration
Two-way bridge between The Sims 1 save files and MOOLLM characters
Present images in linear narrative form