← ClaudeAtlas

world-model-workflowlisted

Build a rigorous world model with state, dynamics, uncertainty, and provenance. Use when creating digital twins, constructing system representations, building simulation foundations, or establishing baseline world state.
synaptiai/agent-capability-standard · ★ 4 · AI & Automation · score 74
Install: claude install-skill synaptiai/agent-capability-standard
## Intent Run the composed workflow **world-model-workflow** using atomic capability skills to construct a comprehensive, grounded representation of a system or domain. A world model captures: - **State**: Current entity states and attributes - **Dynamics**: How the system evolves over time - **Uncertainty**: Confidence bounds and unknowns - **Provenance**: Source and lineage of all facts **Success criteria:** - Complete entity inventory with identity resolution - State representation follows canonical schema - Causal relationships and dynamics modeled - Uncertainty quantified for all assertions - Full provenance chain for every fact - Simulation capability established **Compatible schemas:** - `reference/world_state_schema.yaml` - `reference/event_schema.yaml` ## Inputs | Parameter | Required | Type | Description | |-----------|----------|------|-------------| | `goal` | Yes | string | The modeling objective (e.g., "model supply chain for disruption analysis") | | `scope` | Yes | string\|array | Domain, system, or entities to model | | `constraints` | No | object | Limits (e.g., time horizon, resolution, confidence threshold) | | `sources` | No | array | Data sources for world state extraction | | `prior_model` | No | object | Existing model to extend or refine | ## Procedure 0) **Create checkpoint marker** if mutation might occur: - Create `.claude/checkpoint.ok` after confirming rollback strategy 1) **Invoke `/retrieve`** and store output as `retrieve_out` -