okx-activity
Register for the OKX.AI Trading Hackathon or explain its entry requirements and eligibility. Trigger on requests in any language to register, sign up, join, enter, or participate in the hackathon. Registers an existing Trading ASP; never creates one.
git clone --depth 1 https://github.com/internet-court/internet-court-skill /tmp/okx-activity && cp -r /tmp/okx-activity/vendored/okx/okx-activity ~/.claude/skills/okx-activitySKILL.md
# OKX Activity — registration & participation for OKX campaign activities Each activity's flow, CLI reference, FAQ, and gates live in this skill's `references/` behind an `<activity>-*.md` prefix. This SKILL.md routes only — no templates, no CLI flags, no per-activity copy — so adding an activity never changes the rules of an existing one. ## Pre-flight Checks Before your first onchainos command, read `../okx-agentic-wallet/_shared/preflight.md` once. If it does not exist, read `_shared/preflight.md` instead. **BLOCKING** — it runs before the first `onchainos` command of the session, for every activity, a read-only listing call included. ## Intent Routing | User Intent | Activity | Reference | |---|---|---| | Register, sign up, join, enter, or participate in the hackathon, in any language | OKX.AI Trading Hackathon | [hackathon-core.md](references/hackathon-core.md), then [hackathon-registration.md](references/hackathon-registration.md) | | Hackathon entry requirements or eligibility, in any language — not mid-registration | OKX.AI Trading Hackathon | [hackathon-core.md](references/hackathon-core.md), then [hackathon-faq.md](references/hackathon-faq.md) | **Before producing ANY user-facing message about an activity, that activity's `*-core.md` must be loaded** (**BLOCKING**). It carries that activity's gates, output rules, and send-gate — the flow and FAQ files do **not** repeat them, so opening a `-registration.md` / `-faq.md` first is not a shortcut, it is a skipped gate. Do not improvise a flow, template, or eligibility answer from this file, from memory, or from the CLI's `--help` output alone. If the request names an activity with **no row above** (no reference file exists for it), say that activity isn't supported by this skill yet — never adapt another activity's flow to it, and never guess a CLI subcommand for it. ## Command Index This skill drives `onchainos <activity>` subcommands (hackathon → `onchainos hackathon`). **Learn exact syntax from the CLI, not from memory:** run `onchainos hackathon --help` for the subcommand list, and `onchainos hackathon <subcommand> --help` for a subcommand's flags. Full parameter tables, return-field schemas, and worked examples live in [hackathon-registration.md](references/hackathon-registration.md). ## Wrong-skill guard An activity here enters the **subject that activity defines** (hackathon → an existing Trading ASP agent). `competition join` (`okx-growth-competition`) signs the **wallet account** up for a standard trading competition. Different systems, different subjects — **NEVER**: substitute one for the other, because the two register different things and neither call can be undone. If one request carries signals for **both** (e.g. names "hackathon" *and* "competition" or "cup"), ask which the user means before running any command. ## Security - **Every activity registration is irreversible** — there is no list, update, status, or undo subcommand. **MUST**: hold an explicit confirm reply from the user before submitting; never answer the confirmation prompt on their behalf, and never treat a one-shot request that already named the subject as having pre-answered it. The full gate lives in the activity's `-registration.md`. - **NEVER**: log, print, or pass the JWT in a flag — it is injected by the client layer from the keychain, so leaking it would let an attacker act as the user. Activity flows create no new secrets. - **MUST**: mask user identifiers (OKX UID and the like) when echoing the executed command (`--uid <hidden>`) — they are never returned by the CLI and never pasted raw into the conversation. - **NEVER**: identify an activity by its internal activity id, in any format — name it. The CLI does not return that id; do not source it from anywhere else. - Creating an agent identity is never part of an activity flow — that is `okx-ai`. This skill only enters subjects that already exist. ## Global Notes - **Reply in the user's language.** Every template in this skill's references is authored in English as a *structure guide* — translate it before sending, keeping the layout and fields unchanged and every URL byte-for-byte, still a link. - Each activity's `-core.md` owns its own gates, Output Rules, and Pre-Delivery Checklist; those are additional to this file, never a substitute for it. ### Adding an activity (maintainers) 1. Add `references/<activity>-core.md` — its gates, reading order, output rules, and pre-delivery checklist — plus `references/<activity>-*.md` for the flow and FAQ. 2. Add one Intent Routing row per user intent that activity serves, each a complete markdown link. 3. Extend this file's `description` with the new activity's triggers.
Entry point for Internet Court — the trust layer for agent-to-agent commerce. Use whenever an agent needs to transact with another agent or a paid service, or a user mentions agent payments, paid APIs (HTTP 402/x402), wallet custody or trust concerns, spending mandates, delegated permissions (ERC-7710/7715), escrow, agent identity or reputation (ERC-8004), negotiation between agents (A2A), agent jobs (ERC-8183), machine payments (MPP, AP2), supervision of agent behavior, revocation, verification, or dispute resolution (GenLayer) — even if they never say "Internet Court". Routes to the vendored protocol skills and connector skills in this package.
Connect GenLayer Intelligent Contract decisions to ERC-7710-style delegated authority. Use when an agent needs to design the interface, message schema, relayer/bridge path, EVM revocation controller, constraint updates, proof/finality assumptions, and failure handling that turn a GenLayer agent-performance review into ERC-7710 revocation or policy changes.
Internet Court adapter for GenLayer Intelligent Contract supervision. Use to specify agent-performance rubrics, evidence schemas, decision outputs, and ERC-7710 connector expectations, while delegating actual GenLayer contract writing, linting, testing, deployment, and CLI interaction to the official GenLayer skills at https://skills.genlayer.com/.
Design and implement demos combining x402 HTTP payments with ERC-7710 smart contract delegations and ERC-7715 wallet permission requests for subscriptions, bounded agent budgets, recurring spend, pay-per-use APIs, and agentic commerce.
0G Compute Network guide for decentralized AI inference, fine-tuning, and GPU services. Covers chatbots, image generation, speech-to-text, SDK integration (0g-serving-broker), processResponse API, broker.inference methods, CLI commands (0g-compute-cli), and account management. Use this skill for any 0G compute, 0G AI, or decentralized GPU question.
Use this skill when the user asks to list, create, inspect, update, disable, re-enable, or revoke AltLLM Portal API keys for external agents or applications. Do NOT use for wallet login, billing history, or payment links.
Use this skill when the user asks to log in or out with a wallet session, fetch a wallet sign-in challenge, verify an externally signed challenge, or troubleshoot AltLLM Portal wallet login for the local altllm CLI. Do NOT use for API key management, billing history, or payment links.
Use this skill when the user asks to inspect AltLLM Portal balance, redeem a promo code, review billing transactions, or view usage analytics by period, model, or API key using the local altllm CLI. Do NOT use for API key lifecycle management or payment-link execution.