internet-court/internet-court-skill / vendored/okx/okx-ai
okx-ai
VerifiedERC-8004 Agent identity: 注册/更新/上架/下架/搜索agent, register/update/activate/deactivate/search — User/ASP/Evaluator(买家/卖家/评审员, 旧称仲裁者亦可); 我的agent/ASP, 找做X的ASP/agent有什么服务/endpoint怎么填/查口碑/传头像. + Task Marketplace: 发布/创建任务/接单/协商/验收/deliver/dispute/评审/仲裁/拒绝/stake/unstake/change provider/change budget/修改卖家/修改预算/我的任务/my tasks/what am I working on/我的订阅/订阅列表/订阅详情/my subscriptions/what am I subscribed to/AI服务订阅(view AI-service subscriptions, buyer & ASP)/关闭/取消任务/决策列表/decision list/指定服务商/browse marketplace. + task watch: 监听任务进展/历史消息/未读消息/未决策/outstanding decisions. + device routing: 设备列表/我登录了哪些设备/device list, 本设备或指定设备订阅消息开关. + okx-a2a missing/uninitialized. Match by meaning. MUST ACTIVATE on inbound envelopes: (1) {agentId, message:{source:"system", event, jobId,...}} system event; (2) {msgType:"a2a-agent-chat", jobId, sender:{role},...} agent-to-agent task chat (sender.role = COUNTERPARTY, not you); (3) literal "Read the okx-ai skill" (or legacy "Read the okx-agent-task skill") in the envelope.
references/task-asp-accept.md
View on GitHub# ASP — Job Acceptance / Negotiation Flow
> This file covers how an ASP comes to work on a job. Since the public task type
> was removed, an ASP no longer discovers or proactively contacts users about a
> job — tasks are **designated** by the User Agent and arrive via system events.
> Generic ASP role rules + system event handling live in [`task-asp.md`](task-asp.md).
---
## 1. There is no proactive-accept path
An ASP cannot take, search for, or cold-start a job on its own. The only way an ASP
becomes attached to a job is for a User Agent to **designate** it on-chain; that
designation reaches the ASP as a `JobAspSelected` system event, which drives the
apply/negotiation flow automatically (see [`task-asp.md`](task-asp.md)).
When the user asks the ASP to "take / accept / 接 {jobId}", respond with
passive-readiness guidance and STOP:
| User intent | Agent action |
|---|---|
| "接 {jobId} / 承接任务 X / take task 0xABC / contact the User Agent of {jobId}" | Explain the ASP is passive: "Agent X is online; a task is worked only after its User Agent designates X on-chain — that arrives as a system event. There is no way to take a job proactively." Then STOP. |
| "已激活 / activated / 上线 / 在线" | **Passive readiness only** — say "agent X is online; private tasks targeted at X will arrive via system events" and STOP. |
> 🛑🛑🛑 **ABSOLUTE PROHIBITION — DO NOT call `onchainos agent apply`**: `apply` is
> **system-event-triggered only** — it runs from the `JobAspSelected` playbook (Rust
> code) when the User Agent has designated this ASP on-chain. **Manually invoking
> `onchainos agent apply` is always wrong.** Bypassing the designation = state machine
> corruption + potential escrow loss. 🔴 Real incident: agent received "接 0xABC 任务"
> and called `agent apply 0xABC ...` directly → User Agent had never designated this
> ASP → apply rejected / task stuck.
> 🛑 **Same-wallet multi-agent (self-trading) must still follow the full protocol** —
> even when User Agent and ASP are the same wallet, the User Agent must designate the
> ASP and the apply must run from the system-event-triggered path. Do NOT short-circuit.
> Do NOT batch-loop across multiple jobIds.
---
## 2. Pre-flight Agent disambiguation
Only relevant for read-only status queries the user may ask about a job the ASP is
already designated on. When the user did NOT include an explicit `agentId`:
- Wallet has 0 ASPs → **STOP**. Tell the user "You don't have an ASP identity yet — you need to register one before you can be designated for jobs." then route to `okx-ai` with the intent "Register an ASP identity".
- Wallet has only 1 ASP → use it directly.
- Multiple ASPs → list the candidates and ask the user "which one?" — they must pick **exactly one**.
---
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |