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_KEY only 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-research for source collection.
x-api for current social/event signal.
ito-market-intelligence for venue and underlier context.
ito-basket-compare for user knowledge-base matching.
prediction-market-risk-review before 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
1---2name: ito-data-atlas-agent3description: Design background Data Atlas style agents for Itô basket research, market discovery, parameter drafting, and human-in-the-loop editing. Use for architecture and workflow planning, not live order execution.4metadata:5 source: https://skillmd.com/skills/mhassan0000/ito-data-atlas-agent6 origin: ECC7---89# Itô Data Atlas Agent1011Use this skill to design an agent that watches data sources, builds candidate12prediction-market baskets, drafts parameter changes, and hands the result to a13human for review.1415This skill describes architecture and workflow. It does not run live trading.1617## Guardrails1819- Keep all execution behind explicit human approval.20- Require `ITO_API_KEY` only for read-only Itô data access unless a separate21 private implementation explicitly adds execution controls.22- Do not persist private user data unless the target repo already has a storage23 contract and the user asks for it.24- Do not expose private strategy logic, venue credentials, or local paths in25 public docs.2627## Architecture Pattern2829Use four lanes:30311. Research collector: public web, X, GitHub, venue docs, API metadata, and32 Itô read endpoints when gated access exists.332. Basket drafter: turns sources into candidate underliers, weights, rules, and34 questions.353. Risk reviewer: checks data freshness, venue limits, resolution ambiguity,36 compliance notes, and prompt-injection exposure.374. Human editor: opens a chat or UI state where the user can approve, reject,38 adjust, or ask for more research.3940## Workflow41421. Define the user objective and excluded actions.432. List data sources and access requirements.443. Draft a basket spec with provenance for every underlier.454. Produce editable parameters rather than executable orders.465. Store an audit trail: inputs, model output, sources, and human decision.4748## Useful Skill Chains4950- `deep-research` for source collection.51- `x-api` for current social/event signal.52- `ito-market-intelligence` for venue and underlier context.53- `ito-basket-compare` for user knowledge-base matching.54- `prediction-market-risk-review` before any execution-capable integration.5556## Output Contract5758Return an implementation-ready workflow spec with:5960- data sources61- access gates62- agent roles63- human approval points64- storage/audit boundary65- non-goals