Cournot
Cournot Intelligence Skills let AI agents ask a plain-language question about a crypto event and receive a structured probability, the exact claim being evaluated, and the sources …
Cournot-AI
@cournot-ai
Install
$ openclaw skills install @cournot-ai/cournotCournot
Query one event's probability from Cournot. Trigger only on an explicit Cournot request such as /cournot … or “use Cournot to look this up.” One paid probability call is allowed per user instruction. On a bad result, stop rather than retrying with a rephrased query.
The event message is the user's claim in their own words, not the command. Remove /cournot and probability; if no claim remains with an asset, threshold, or date, ask for one and stop without calling the API.
Cournot has no mispricing API. If the user asks whether a market is mispriced or priced correctly, say so and stop.
Reply in the user's language. Ignore /cournot and API titles when detecting it.
API base: https://interface.cournot.ai
Service and Runtime
The Skill is free to install. Cournot is an external service with three free probability calls per account; after that, each probability call costs $0.01 through a supported x402 or b402 wallet flow. Resolve and disambiguation remain free. A wallet is optional until the free allowance is exhausted, and every payment requires explicit confirmation.
The bundled client requires Node.js 22.20 or newer. It calls the Cournot API, stores short-lived single-use payment intents in the operating system's temporary directory, and invokes a compatible wallet command only for a confirmed paid request. It never requires an API key, private key, or seed phrase.
Workflow
- For every request, read references/query-flow.md and follow resolve, disambiguation, and probability handling.
- Send probability requests only through
scripts/cournot-client.mjs, which returns either the result or a sanitized payment preview. Only for a payment preview, read references/payment.md. Wallet setup may be assisted only after the separate confirmation defined there; keep credentials outside the model context and Cournot client. - When probability succeeds, read references/response-format.md and render only the returned assessment and evidence.
Preserve the pending event text and selected market ids across disambiguation, wallet setup, and payment confirmation so the user does not need to enter them again.
Hosts
Claude Code, Codex, Grok, and other Agent Skills hosts use this same folder. Install or copy the entire skills/cournot/ directory so the linked references remain available.
Top skills in this category
polymarket-agent
@andretutaResearch Polymarket markets, whale flow and smart money; optionally trade a Polygon wallet behind deterministic risk guard-rails.
Decision Trees
@evgyurDecision tree analysis for complex decision-making across all domains. Use when user needs to evaluate multiple options with uncertain outcomes, assess risk/reward scenarios, or structure choices systematically. Applicable to business, investment, personal decisions, operations, career choices, product strategy, and any situation requiring structured evaluation. Triggers include decision tree, should I, what if, evaluate options, compare alternatives, risk analysis.
eastmoney skills
@qqk000基于东方财富权威数据库的金融数据查询工具，支持行情、财务及关联关系数据。
Seedstr (Earn pasive income with your agent)
@mastersyondgyA marketplace connecting AI agents with humans who need tasks completed. Agents earn cryptocurrency (ETH or SOL) for accepted work. Supports swarm jobs where...
Agent Evaluation
@rustyorbTesting and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.