Crowdcast
Skill Verified ActiveRun multi-agent social simulations for prediction and creative exploration. Use when the user wants to simulate group behavior, predict public reactions, explore fictional scenarios, or analyze how agents would interact. Trigger words - "simulate", "prediction", "multi-agent", "what would happen if", "social simulation", "crowdcast".
To enable users to run complex multi-agent social simulations for predictive analysis or creative storytelling without requiring any external setup or APIs.
Features
- Run multi-agent social simulations
- Analyze documents to extract knowledge graphs
- Generate AI agent personas
- Simulate agent interactions in forecast or creative modes
- Resume interrupted simulations
- Interview simulated agents in character
Use Cases
- Predicting public reactions to policy changes or news events
- Exploring fictional scenarios and character interactions
- Analyzing group behavior dynamics
- Generating narrative content based on complex prompts
Non-Goals
- Requiring external APIs or infrastructure
- Running simulations at massive scale (millions of agents)
- Providing real-time web-based interfaces
Workflow
- User invokes `/crowdcast simulate <files> "prompt"`
- Skill generates simulation ID and directory structure
- Skill copies seed files and writes initial metadata
- Phase 1: Subagent analyzes documents to create knowledge graph and config
- Phase 2: Subagents generate key agent personas and crowd group profiles in parallel
- Phase 3: Subagents simulate rounds sequentially, updating platform/world state and agent memories
- Phase 4: Subagent generates a final report and structured data
- User receives report and can optionally interview agents
Practices
- Simulation design
- Agent orchestration
- Narrative generation
Prerequisites
- Claude Code environment
- Claude subscription (Pro, Team, or Enterprise)
Installation
First, add the marketplace
/plugin marketplace add TheQmaks/crowdcast/plugin install crowdcast@theqmaksQuality Score
VerifiedSimilar Extensions
Hive Mind Advanced
98Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory
External Context
100Invoke parallel document-specialist agents for external web searches and documentation lookup
Swarm Orchestration
100Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.
OraClaw Forecast
100Time series forecasting for AI agents. ARIMA and Holt-Winters predictions with confidence intervals. Predict revenue, traffic, prices, or any sequential data. Sub-5ms inference.
Simulate Cpu Architecture
100Design and simulate a minimal CPU from scratch: define an instruction set architecture (ISA), build the datapath (ALU, register file, program counter, memory interface), design the control unit (hardwired or microprogrammed), implement the fetch-decode-execute cycle, and verify by tracing a small program clock cycle by clock cycle. The capstone "computer inside a computer" exercise that composes combinational and sequential building blocks into a complete processor.
Lyric Writer
99Writes or reviews lyrics with professional prosody, rhyme craft, and quality checks. Use when writing new lyrics, revising existing lyrics, or when the user says 'let's work on a track.'