Skip to main content
moollm The soul of MOOLLM โ self-explanation, help, navigation, philosophy
Jump to install Skills Marketplace Discover and explore AI skills built by the community.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Copy promptShow prompt details A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/SimHacker/moollm --skill moollmThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Download Zip Downloading... More from this repository skill-snitch-report.md 4.1 KB Related occupations SOC
Based on SOC occupation classification
name moollm description The soul of MOOLLM โ self-explanation, help, navigation, philosophy license MIT tier 0 allowed-tools ["read_file","list_dir"] protocol MOOLLM-HELP related ["leela-ai","plain-text","room","yaml-jazz","skill","k-lines","play-learn-lift","sister-script","sniffable-python","society-of-mind","adversarial-committee","constructionism","postel","speed-of-light","representation-ethics","incarnation","adventure","needs","prototype"] tags ["moollm","meta","help","philosophy","navigation","foundational"]
MOOLLM
"Many-Voiced Object-Oriented LLM โ the system that explains itself."
What Is It?
The moollm skill is the spirit and constitution of MOOLLM itself. It's the top-level help agent that can:
Explain what MOOLLM is
Answer "what can I do?"
Navigate users to relevant skills
Articulate the philosophy
Show the constitution
Recommend approaches for tasks
When confused, invoke this skill.
The Core Ideas
Many-Voiced
MOOLLM doesn't use a single LLM perspective. It simulates multiple agents debating within a single call:
Committees of personas with opposing views
Deliberation forced by Robert's Rules
Evaluation by independent assessors
The debate produces wisdom, not statistics
Filesystem as World Model
Directories are rooms. Files are objects:
examples/adventure-4/
โโโ pub/ # A room
โ โโโ ROOM.yml # Room properties
โ โโโ pie-table.yml # An object
โ โโโ cat-cave/ # Nested room
โโโ characters/ # Metaphysical room
โโโ ADVENTURE.yml # Game state
Play-Learn-Lift
The methodology:
PLAY โ Explore freely, try things, fail safely
LEARN โ Notice patterns, document what works
LIFT โ Share as reusable skills
Skills as Prototypes
Skills are documented capabilities that can be:
Instantiated into specific contexts
Composed with other skills
Inherited (multiple inheritance)
Evolved through play
Protocol
When invoked, this skill should:
Assess what the user needs
If lost โ provide orientation
If asking "what can I do?" โ show relevant capabilities
If asking about philosophy โ explain core concepts
If asking about skills โ navigate to skill system
Always be helpful, welcoming, and clear
Constitutional File Map (kernel/)
kernel/README.md โ index and navigation for kernel docs
kernel/constitution-core.md โ core constitution and invariants
kernel/constitution-template.md โ template for new constitutions
kernel/ARCHITECTURE.md โ system architecture overview
kernel/context-assembly-protocol.md โ context assembly rules
kernel/memory-management-protocol.md โ memory, limits, persistence
kernel/event-logging-protocol.md โ logging and provenance
kernel/tool-calling-protocol.md โ tool usage contract
kernel/self-healing-protocol.md โ recovery and repair behaviors
kernel/DIRECTORY-AS-OBJECT.md โ directory as object model
kernel/SELFISH-COM-IMPLEMENTATION.md โ SELF lineage in practice
kernel/INTEREST-GATES.yml โ attention gating rules
kernel/NAMING.yml โ top-level naming policy
kernel/naming/NAMING.yml โ detailed naming rules
kernel/naming/NAMING-K-LINES.yml โ K-line naming standards
kernel/naming/NAMING-CONSTELLATIONS.yml โ constellation naming
kernel/naming/NAMING-COMPILATION.yml โ compiled name patterns
kernel/naming/NAMING-PATH-VARIABLES.yml โ path variable rules
kernel/naming/NAMING-RELATIONSHIPS.yml โ relationship naming
kernel/naming/URLS.yml โ URL conventions
kernel/drivers/README.md โ driver index
kernel/drivers/cursor.yml โ Cursor-specific driver
kernel/drivers/generic.yml โ baseline driver
kernel/drivers/custom.yml โ site-specific overrides
kernel/drivers/claude-code.yml โ Claude Code driver
kernel/drivers/antigravity.yml โ experimental driver
Local Runtime Files (.moollm/) These are gitignored runtime files for session state, scratch, and logs.
.moollm/working-set.yml โ current focus and active files
.moollm/hot.yml โ priority hints
.moollm/cold.yml โ cold-start state
.moollm/startup.yml โ startup context
.moollm/output.md โ append-only output log
.moollm/session-log.md โ append-only session log
.moollm/bootstrap-probe.yml โ bootstrap probes and checks
Cursor Boot Optimization (cursor-mirror) Use cursor-mirror to inspect boot state, reduce context bloat, and verify setup.
Commands (need composer ID):
tree โ list sessions/composers
status โ quick health check
tail --limit 50 โ recent messages
timeline <composer> โ full event sequence
thinking <composer> โ reasoning blocks
tools <composer> โ tool call history
grep <pattern> โ search transcripts
confirm which bootstrap ran
locate missing context
triage performance issues
audit tool-call provenance
Plan: MOOLLM Linter, Mirror, Compiler
Phase 0 โ Meta Inhale (Planning Only)
Inventory the repository structure and file types.
Define categories: essential, primary, secondary, hidden.
Establish ignore rules (build output, caches, temp files, editor artifacts).
Identify canonical docs to preserve: top-level README.md, designs/, docs/.
Map root entry points to their authoritative specs (skills, kernels, protocols).
Reverse-engineer the root README.md into a structured spec:
Purpose
Audience
Sections
Source references
Link strategy
Define a report format for validation output:
Structural warnings
Missing declarations
Naming consistency
Cross-link integrity
Define "what to hide" for human-facing outputs (noise, duplication, low-signal).
Define "what to surface" for quick navigation (skills index, starting points).
Define sister-script scope: lint, mirror, compile.
Write a sister-script design brief (no code yet).
Inputs
User questions about MOOLLM
Requests for help or navigation
Philosophical inquiries
Outputs
Clear explanations
Skill recommendations
Navigation guidance
Philosophy articulation
Dovetails With
Protocol Symbol Invoke when: User is confused, lost, or wants to understand the system.