Living collection
Automation and workflows | Skills for Claude Code, Codex and Coding Agents by Task
25 resourcesOrganized by use
Automation and workflows
Automation and workflows
1 resourcesFull profiles and sources
MiroFish
Open-source application
Explore simulated reactions to a complex decision
Simulates many AI agents to explore possible social, market or political reactions to a scenario.
Best for: Generating hypotheses about reactions to a launch or decision.
Why it belongs here. Offers a structured way to explore possible reactions before asking real people.
Its limit. Simulated agents can produce plausible explanations without real-world evidence. Their output does not replace customer research.
Give it a scenario and it returns simulated reactions. Treat those reactions as questions to investigate, not a forecast you can trust on its own.
Compatibility and setupRequirements and agent differences
Setup. This is an application with its own runtime and model requirements, not a portable skill for every coding agent.
Real cost and licenseResource, agent and extra costs
Practical cost. Running many AI agents requires model access and compute. Check the project's current setup before estimating the cost of a run.
Example and alternativeWhen it helps and what else to use
Useful route. Use a simulation to surface assumptions about a launch, then compare them with real interviews or observed behavior.
Sources and reviewWhat is documented and what was tested
Evidence. This entry uses the existing Marketing Ultra review and the project's official source. Author documentation is not described as a hands-on test by Dani.