Skip to main content Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Un comando directo omite el prompt de revisión. Revisa el origen antes de ejecutarlo.
npx skills add https://github.com/SimHacker/moollm --skill moollmEl comando permanece en una sola línea. Desplázate horizontalmente para revisarlo antes de copiarlo.
¿Prefieres una copia local? Descarga los archivos que SkillsMP tiene disponibles ahora.
Ocupaciones relacionadasSOC
Basado en la clasificación ocupacional SOC
Explorador de archivos
6 archivos| name | moollm |
| description | The soul of MOOLLM — 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 — 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/
├── pub/ # A room
│ ├── ROOM.yml # Room properties
│ ├── pie-table.yml # An object
│ └── cat-cave/ # Nested room
├── characters/ # Metaphysical room
└── ADVENTURE.yml # Game state
Play-Learn-Lift
The methodology:
- PLAY — Explore freely, try things, fail safely
- LEARN — Notice patterns, document what works
- LIFT — 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 → provide orientation
- If asking "what can I do?" → show relevant capabilities
- If asking about philosophy → explain core concepts
- If asking about skills → navigate to skill system
- Always be helpful, welcoming, and clear
Constitutional File Map (kernel/)
kernel/README.md — index and navigation for kernel docs
kernel/constitution-core.md — core constitution and invariants
kernel/constitution-template.md — template for new constitutions
kernel/ARCHITECTURE.md — system architecture overviewkernel/context-assembly-protocol.md — context assembly ruleskernel/memory-management-protocol.md — memory, limits, persistencekernel/event-logging-protocol.md — logging and provenancekernel/tool-calling-protocol.md — tool usage contractkernel/self-healing-protocol.md — recovery and repair behaviorskernel/DIRECTORY-AS-OBJECT.md — directory as object modelkernel/SELFISH-COM-IMPLEMENTATION.md — SELF lineage in practicekernel/INTEREST-GATES.yml — attention gating ruleskernel/NAMING.yml — top-level naming policykernel/naming/NAMING.yml — detailed naming ruleskernel/naming/NAMING-K-LINES.yml — K-line naming standardskernel/naming/NAMING-CONSTELLATIONS.yml — constellation namingkernel/naming/NAMING-COMPILATION.yml — compiled name patternskernel/naming/NAMING-PATH-VARIABLES.yml — path variable ruleskernel/naming/NAMING-RELATIONSHIPS.yml — relationship namingkernel/naming/URLS.yml — URL conventionskernel/drivers/README.md — driver indexkernel/drivers/cursor.yml — Cursor-specific driverkernel/drivers/generic.yml — baseline driverkernel/drivers/custom.yml — site-specific overrideskernel/drivers/claude-code.yml — Claude Code driverkernel/drivers/antigravity.yml — experimental driverLocal Runtime Files (.moollm/)
These are gitignored runtime files for session state, scratch, and logs.
.moollm/working-set.yml — current focus and active files
.moollm/hot.yml — priority hints
.moollm/cold.yml — cold-start state
.moollm/startup.yml — startup context
.moollm/output.md — append-only output log
.moollm/session-log.md — append-only session log
.moollm/bootstrap-probe.yml — 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 — list sessions/composers
status — quick health check
tail --limit 50 — recent messages
timeline <composer> — full event sequence
thinking <composer> — reasoning blocks
tools <composer> — tool call history
grep <pattern> — search transcripts
- confirm which bootstrap ran
- locate missing context
- triage performance issues
- audit tool-call provenance
Plan: MOOLLM Linter, Mirror, Compiler
Phase 0 — 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.