ito-data-atlas-agent
affaan-m/ecc
Design background Data Atlas agents for Itô basket research with human-in-the-loop review—architecture and workflow planning, not live trading.
What is ito-data-atlas-agent?
This skill helps you architect an agent that researches prediction-market baskets, drafts parameters, and routes decisions to humans for approval. Use it for designing multi-stage workflows that combine data collection, analysis, risk review, and human editing without executing live trades.
- Design four-lane agent architecture: research collector, basket drafter, risk reviewer, and human editor
- Draft candidate prediction-market baskets with underlier weights, rules, and provenance tracking
- Integrate public data sources (web, X, GitHub, venue docs) and read-only Itô API access
- Generate editable parameter specs rather than executable orders
- Maintain audit trails linking inputs, model outputs, sources, and human decisions
How to install ito-data-atlas-agent
npx skills add null --skill ito-data-atlas-agent- Itô API key (read-only access) if using Itô data endpoints
- Familiarity with prediction-market terminology and basket structure
- Understanding of your target venue's limits and resolution rules
How to use ito-data-atlas-agent
- 1.Define your user objective and list actions the agent must not take
- 2.Enumerate data sources (public web, X, GitHub, venue docs, Itô read endpoints)
- 3.Design the four-lane architecture: assign roles to research, drafting, risk, and human-review stages
- 4.Draft a basket spec template with fields for underlier, weight, rule, and source provenance
- 5.Set up human approval points and specify what triggers escalation to the editor
- 6.Define your storage and audit-trail boundary (what gets logged, where, and for how long)
- 7.Chain with complementary skills like deep-research, x-api, ito-market-intelligence, and prediction-market-risk-review
Use cases
- Plan a workflow to monitor market signals and propose basket changes for human review
- Design a research agent that collects venue limits and compliance notes before drafting parameters
- Build a multi-stage approval system where risk checks feed into human editor chat or UI
- Chain with deep-research and market-intelligence skills to gather context before basket drafting
- Create an audit-ready system that documents every data source and decision point
- Prediction-market researchers and strategists
- Product teams designing human-in-the-loop trading workflows
- Risk and compliance officers reviewing agent-assisted market operations
- Developers building agent architectures that require explicit approval gates
ito-data-atlas-agent FAQ
No. This skill is for architecture and workflow planning only. It produces editable parameter specs and audit trails, not executable orders. Any execution-capable integration requires separate controls and explicit human approval.
Public web, X, GitHub, venue documentation, API metadata, and Itô read-only endpoints (when gated access exists). It does not access private strategy logic or venue credentials.
The workflow includes a dedicated human-editor lane that opens a chat or UI state where users can approve, reject, adjust parameters, or request additional research before any downstream action.
Maintain an audit trail of inputs, model outputs, data sources with provenance, human decisions, and timestamps. Do not persist private user data unless your target repo already has a storage contract.
Use deep-research for source collection, x-api for social signals, ito-market-intelligence for venue context, ito-basket-compare for knowledge-base matching, and prediction-market-risk-review before any execution integration.
Full instructions (SKILL.md)
Source of truth, from affaan-m/ecc.
name: ito-data-atlas-agent description: 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. metadata: origin: ECC
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
Related skills
More from affaan-m/ecc and the wider catalog.
ito-inference
Agent skill from affaan-m/ecc.
ito-market-intelligence
Research prediction-market events, venues, and liquidity without investment advice or live trading.
ito-trade-planner
Build structured prediction-market trade planning worksheets without placing trades or giving advice.
ito-training
Agent skill from affaan-m/ecc.
java-coding-standards
Java coding standards for Spring Boot and Quarkus: naming, immutability, Optional, streams, exceptions, and reactive patterns.
jira-integration
Retrieve, analyze, and update Jira tickets directly from your AI coding workflow.