context-continuity
High-fidelity context transfer protocol for moving conversations between AI agents. Preserves decision tempo, open loops, and critical context with graceful degradation. Use when the user says "transfer," "hand...
Découvrez les skills Outils, comparez leurs dépôts et consultez leurs instructions.
High-fidelity context transfer protocol for moving conversations between AI agents. Preserves decision tempo, open loops, and critical context with graceful degradation. Use when the user says "transfer," "hand...
Review MCP server specifications and updates for compliance, security, and quality. Use when evaluating spec.yaml files, PRs adding/updating servers, or assessing MCP server changes.
How to design formats that succeed — simplicity, community, timing
Working memory for thinking out loud.
Navigation links between rooms — the edges of the memory palace
Human-readable markdown session logs for characters and adventures.
Rooms are intertwingled navigable activation context maps. Entering = calling. Exiting = returning.
The soul of MOOLLM — self-explanation, help, navigation, philosophy
YAML is sheet music. The LLM is the jazz musician. Comments are soul.
Structured multi-perspective deliberation through adversarial dialogue
Same card active in multiple rooms simultaneously
Graceful memory compression with integrity — summarize before forgetting, never fabricate
Dynamic motivations (Sims-style) — needs fluctuate and drive behavior
Intermediate scope for inheritance — like OpenLaszlo's
Measurable criteria translating qualitative debate to quantitative scores
Start Playing. Keep Learning. Lift Others.
Rooms as pipeline nodes, exits as edges, objects as messages
First-person code — the "I" shifts based on who is speaking
Present images in linear narrative form
Protocol names ARE K-lines.
Parliamentary procedure as forcing function for genuine deliberation
Wake up, orient, and warm the context with foundational MOOLLM knowledge
Structure Python so LLMs can understand it in 50 lines.
Everything is alive. Everything can speak.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.