$ loading_
Plan Data Atlas agents for Ito basket research and workflow design.
This skill appears to be prompt/documentation-oriented architecture guidance and does not itself execute code, access networks, or read/write data. Combined with its open-source source and strong community adoption, the overall risk is low, with only minor caution that the docs discuss chaining to external data sources and future execution-capable integrations not implemented by the skill itself.
The metadata says no keys or environment variables are required. Although the README mentions `ITO_API_KEY` for read-only Itô data access, that is framed as guidance for possible private implementations or later integrations, not as a current credential requirement or direct secret-handling behavior of this skill.
The metadata and checks indicate no remote endpoints, and the skill is classified as prompt-only. The docs mention public web, X, GitHub, and venue docs as possible data sources in an architecture pattern, but there is no evidence that this skill itself sends user data to any endpoint.
The material explicitly states this is for architecture and workflow planning and 'does not run live trading.' There is no indication of local process spawning, script execution, system command use, or integration with execution-capable control planes. Its output contract is a workflow spec rather than executable actions.
No access to local files, databases, or system resources is declared. The README instead states minimization guardrails such as not persisting private user data unless the target repo already has a storage contract and the user asks for it, indicating governance guidance rather than actual data access capability.
The source is an open-source GitHub repository with very strong community adoption (~210.5k stars), which is a significant positive trust signal. The license and maintenance status are not explicit, leaving some audit gaps, but absent signs of closed-source distribution, suspicious packaging, or misleading installation behavior, this does not justify a higher risk rating.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "ito-data-atlas-agent" skill from askskill: 1. Download https://raw.githubusercontent.com/affaan-m/ECC/main/skills/ito-data-atlas-agent/SKILL.md 2. Save it as ~/.claude/skills/ito-data-atlas-agent/SKILL.md 3. Reload skills and tell me it's ready
Design a Data Atlas-style multi-agent architecture for Itô basket research with four modules: market discovery, parameter drafting, human review, and version rollback. Describe each module’s inputs, outputs, dependencies, and handoff workflow. Use it only for research and process planning, not live trading.
A clear multi-agent architecture plan showing module roles, data flow, and human-in-the-loop checkpoints.
Draft a parameter generation and editing workflow for Ito basket strategy research. Cover candidate parameter sources, filtering rules, human editing steps, audit log fields, and how to organize everything in a Data Atlas structure.
An actionable parameter drafting workflow with field suggestions, review steps, and content organization.
Design a human-in-the-loop collaboration model for a research agent used in Ito basket market discovery. Specify which tasks can be automated, which checkpoints require human approval, how conflicting judgments are resolved, and how revision history is recorded.
A human collaboration control plan defining automation boundaries, approval checkpoints, and tracking mechanisms.
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.
ITO_API_KEY only for read-only Itô data access unless a separate
private implementation explicitly adds execution controls.Use four lanes:
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.Return an implementation-ready workflow spec with:
Record polished web app UI demo videos for walkthroughs, tutorials, and showcases.
Refine retrieved context iteratively to improve subagent understanding and output quality.
Unify multi-channel notifications for routing, deduplication, escalation, and inbox consolidation.
Audit, plan, and implement SEO improvements for better search visibility.
Create iOS liquid glass interfaces with dynamic visuals and interactive morphing.
Fetches up-to-date framework docs for setup, APIs, and code examples.
Compare prediction-market baskets with research notes to find gaps and alignment.
Research prediction markets and produce source-grounded intelligence briefings without trading advice.
Create a non-advisory prediction-market trade planning worksheet for manual execution.
Keep a private, local-first diary through any AI agent.
Connect a Git-native knowledge base so AI can search, write, and rewind context.
Connect coding agents to Atlas for context retrieval and work capture.