Itô Data Atlas Agent
Use this skill to design an agent that watches data sources, builds candidate prediction-market baskets, drafts parameter changes, and hands the result to a human for review.
This skill describes architecture and workflow. It does not run live trading.
Guardrails
- Keep all execution behind explicit human approval.
- Require
ITO_API_KEYonly for read-only Itô data access unless a separate
private implementation explicitly adds execution controls.
- Do not persist private user data unless the target repo already has a storage
contract and the user asks for it.
- Do not expose private strategy logic, venue credentials, or local paths in
public docs.
Architecture Pattern
Use four lanes:
- Research collector: public web, X, GitHub, venue docs, API metadata, and
Itô read endpoints when gated access exists.
- Basket drafter: turns sources into candidate underliers, weights, rules, and
questions.
- Risk reviewer: checks data freshness, venue limits, resolution ambiguity,
compliance notes, and prompt-injection exposure.
- Human editor: opens a chat or UI state where the user can approve, reject,
adjust, or ask for more research.
Workflow
- Define the user objective and excluded actions.
- List data sources and access requirements.
- Draft a basket spec with provenance for every underlier.
- Produce editable parameters rather than executable orders.
- Store an audit trail: inputs, model output, sources, and human decision.
Useful Skill Chains
deep-researchfor source collection.x-apifor current social/event signal.ito-market-intelligencefor venue and underlier context.ito-basket-comparefor user knowledge-base matching.prediction-market-risk-reviewbefore any execution-capable integration.
Output Contract
Return an implementation-ready workflow spec with:
- data sources
- access gates
- agent roles
- human approval points
- storage/audit boundary
- non-goals
