本文へ移動
cccskills
無料GitHub で公開

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.

インストール方法を見る

含まれるファイル(6)

  • SKILL.md5.0 KB
  • _shared/preflight.md2.0 KB
  • LICENSE341 B
  • references/hackathon-core.md5.2 KB
  • references/hackathon-faq.md4.2 KB
  • references/hackathon-registration.md13.7 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

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 IntentActivityReference
Register, sign up, join, enter, or participate in the hackathon, in any languageOKX.AI Trading Hackathonhackathon-core.md, then hackathon-registration.md
Hackathon entry requirements or eligibility, in any language — not mid-registrationOKX.AI Trading Hackathonhackathon-core.md, then 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.

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.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

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.

日本語の概要は準備中です。原文の説明を表示しています。

internet-court/internet-court-skill6,7302026年8月20日 更新

Builds Agent-to-Agent (A2A) servers and clients following Google's open protocol for agent interoperability. Use when the user wants to create an A2A-compliant agent, build an Agent Card, implement task management, connect agents across frameworks, set up agent discovery, handle streaming responses, implement push notifications, or orchestrate multi-agent workflows. Trigger words: a2a, agent to agent, agent2agent, a2a protocol, a2a server, a2a client, agent card, agent interoperability, agent collaboration, multi-agent, agent discovery, a2a sdk, a2a task.

日本語の概要は準備中です。原文の説明を表示しています。

internet-court/internet-court-skill6,7302026年8月20日 更新

Give the AI agent its own EVM wallet with admin-controlled policies the agent CANNOT bypass even under prompt injection. Encrypted keystore (AES-256-GCM, scrypt KDF), policy file the agent has no tool to write, deterministic policy gate on every signing operation, optional local HTTP dashboard. Triggers: agent wallet, give the agent a wallet, agent address, fund the agent, agent autonomy, policy gate, kill switch, agent permissions, bounded autonomy, ERC-4337 alternative, session-key alternative.

日本語の概要は準備中です。原文の説明を表示しています。

internet-court/internet-court-skill6,7302026年8月20日 更新

Crypto wallet operations via the awal CLI — sign in, check balances, send USDC/ETH/POL/SOL, trade tokens, fund the wallet, and use the x402 payment protocol to discover paid services, pay for API calls, monetize an API, or query onchain data. Use whenever the user mentions signing in, login, authentication, wallet status, balance, address, sending money, paying someone, transferring tokens, ENS names, swapping/trading/converting tokens, funding/topping up/onramp, USDC, ETH, POL, SOL, the x402 bazaar, paid APIs, monetizing an endpoint, or querying onchain data on Base.

日本語の概要は準備中です。原文の説明を表示しています。

internet-court/internet-court-skill6,7302026年8月20日 更新

Help developers write code that interacts with Alkahest escrow contracts using the TypeScript, Rust, or Python SDK

日本語の概要は準備中です。原文の説明を表示しています。

internet-court/internet-court-skill6,7302026年8月20日 更新

Interact with Alkahest escrow contracts as a buyer, seller, or oracle using the CLI

日本語の概要は準備中です。原文の説明を表示しています。

internet-court/internet-court-skill6,7302026年8月20日 更新

internet-court のスキルをすべて見る

このスキルの問題を報告する