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.4---5
6# Itô Data Atlas Agent
7
8Use this skill to design an agent that watches data sources, builds candidate
9prediction-market baskets, drafts parameter changes, and hands the result to a
10human for review.
11
12This skill describes architecture and workflow. It does not run live trading.
13
14## Guardrails
15
16- Keep all execution behind explicit human approval.
17- Require `ITO_API_KEY` only for read-only Itô data access unless a separate
18 private implementation explicitly adds execution controls.
19- Do not persist private user data unless the target repo already has a storage
20 contract and the user asks for it.
21- Do not expose private strategy logic, venue credentials, or local paths in
22 public docs.
23
24## Architecture Pattern
25
26Use four lanes:
27
281. Research collector: public web, X, GitHub, venue docs, API metadata, and
29 Itô read endpoints when gated access exists.
302. Basket drafter: turns sources into candidate underliers, weights, rules, and
31 questions.
323. Risk reviewer: checks data freshness, venue limits, resolution ambiguity,
33 compliance notes, and prompt-injection exposure.
344. Human editor: opens a chat or UI state where the user can approve, reject,
35 adjust, or ask for more research.
36
37## Workflow
38
391. Define the user objective and excluded actions.
402. List data sources and access requirements.
413. Draft a basket spec with provenance for every underlier.
424. Produce editable parameters rather than executable orders.
435. Store an audit trail: inputs, model output, sources, and human decision.
44
45## Useful Skill Chains
46
47- `deep-research` for source collection.
48- `x-api` for current social/event signal.
49- `ito-market-intelligence` for venue and underlier context.
50- `ito-basket-compare` for user knowledge-base matching.
51- `prediction-market-risk-review` before any execution-capable integration.
52
53## Output Contract
54
55Return an implementation-ready workflow spec with:
56
57- data sources
58- access gates
59- agent roles
60- human approval points
61- storage/audit boundary
62- non-goals
RajanthaR