This is an architecture pattern for building prediction market research agents, not a trading bot. It gives you a four-lane design: research collector, basket drafter, risk reviewer, and human approval gate. The whole point is keeping execution behind explicit human review while you pull data from public sources, X, GitHub, and optionally read-only Itô endpoints. You get a workflow that drafts candidate baskets with provenance, checks for resolution ambiguity and compliance issues, then hands editable parameters to a person. If you're prototyping market discovery tooling or want to keep strategy research separate from order execution, this gives you the guardrails and audit structure to do it safely.
npx -y skills add affaan-m/everything-claude-code --skill ito-data-atlas-agent --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
moizibnyousaf/ai-agent-skills
github/awesome-copilot