Unconventional PostgreSQL optimization techniques
Skills in this repository
SimHacker/moollm - Page 2
SkillsMP has collected 111 skills from SimHacker/moollm. Open a skill to review its source and details.
SimHacker/moollmShowing 40 of 111 collected skills.
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
Wake up, orient, and warm the context with foundational MOOLLM knowledge
Smart templates that understand semantic intent, not just string substitution
Minsky frames, Drescher schemas, interchange registry, and MOOLLM K-lines — distinct layers.
Drescher's computational theory of causal learning
Source text: Mixed languages
Document-first automation — the doc is the source of truth
Be conservative in what you send, liberal in what you accept.
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
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
Dual Python/JavaScript adventure runtimes — always in sync
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
Present images in linear narrative form
Sims-inspired task scheduling — queue actions, execute in order
Committee of personas with opposing propensities forcing genuine debate
Objects announce what they can do — The Sims style
Feline interactions, buffs, and relationship building
Systematic code analysis with evidence collection
The LLM as consistency maintainer and orchestrator
Educational philosophy — learn by building inspectable things
Rooms as pipeline nodes, exits as edges, objects as messages
Structured multi-perspective deliberation through adversarial dialogue
Systematic bug investigation with hypothesis tracking
Currency and trade — gold flows where stories lead
Intent-based code interpretation across all languages — SQL, Python, JS, YAML, Bash, and beyond
Independent assessment without debate context — adversarial loop prevents gaming
How to design formats that succeed — simplicity, community, timing
You carry pointers. When you set them down, they become real.