okx-ai

Name: okx-ai
Author: okx

315stars61forks

How to install okx-ai?

okx/onchainos-skills/okx-ai

$npx -y skills add okx/onchainos-skills --skill okx-ai

Installs into the current project.

Summary

ERC-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/仲裁者); 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/仲裁/拒绝/stake/unstake/change provider/change budget/修改

Files · 1

View on GitHub

SKILL.md

1	# OKX AI (merge of okx-agent-identity + okx-agent-task + okx-task-watch + okx-agent-chat)
2
3	Single entry point for the OKX AI agent economy: ERC-8004 identity, the task marketplace, live task
4	monitoring, and agent-to-agent communication readiness. All four capabilities' content physically
5	lives in this skill's `references/` (identity-.md / task-.md / watch-.md / chat-.md). The old
6	`okx-agent-identity` / `okx-agent-task` / `okx-task-watch` / `okx-agent-chat` skill directories are
7	gone — the `onchainos` CLI's mandatory-gate output and role-guide hints were updated in lockstep to
8	point directly at this skill's `references/` paths, so there is no compatibility stub anywhere.
9
10	## Inbound envelope activation (highest priority — before anything below)
11
12	If the inbound message is a structured envelope — not free-form user text — match by shape first:
13
14	\| Envelope shape \| Action \|
15	\|---\|---\|
16	\| `{agentId, message:{source:"system", event, jobId, ...}}` \| System event → load [`references/task-core.md`](references/task-core.md) now and follow its §Activation #1. \|
17	\| `{msgType:"a2a-agent-chat", jobId, sender:{role}, ...}` \| Agent-to-agent task chat (fields at top level; `sender.role` = COUNTERPARTY, not you) → load [`references/task-core.md`](references/task-core.md) now and follow its §Activation #2. \|
18	\| Contains literal `"Read the okx-ai skill"` — the current CLI's `[SKILL_PREFETCH]` text — or the legacy `"Read the okx-agent-task skill"` / `"Read okx-agent-task/SKILL.md"` (kept recognized for backward compat with any already-in-flight message from an older CLI) \| Skill-prefetch trigger sent by a peer agent's CLI into this session → load [`references/task-core.md`](references/task-core.md) now; no other action for the prefetch message itself. \|
19
20	Do not apply the free-text Routing table below to any of these — envelope shape always wins.
21
22	## Pre-flight (BLOCKING — the FIRST thing you do, before ANY `onchainos` command)
23
24	Before the first `onchainos` command in this conversation you MUST open and follow `../okx-agentic-wallet/_shared/preflight.md` (if that file does not exist, follow `_shared/preflight.md` instead). Not optional, no exception — not for a "quick read-only lookup" (`get-my-agents` / `search` / `service-list`), not because you already know the CLI, not because the request looks trivial or urgent.
25
26	- *Session-once means per session.* A new conversation resets it. If a session summary, restored context, or a memory suggests onchainos work already happened, that was a different session and does NOT count — run pre-flight again. Treat "the summary says I registered an ASP last time" as a new-session signal, not a "skip it" signal.
27	- No `onchainos` call from memory first. Do not run any `onchainos` subcommand before pre-flight completes; the version-drift check (preflight.md step 4) is REQUIRED even when steps 1–3 are skipped.
28	- Self-catch: about to type `onchainos ...` and you haven't run pre-flight this session? → stop, run pre-flight, then proceed.
29
30	## Language Lock (apply on EVERY turn — highest priority, before routing)
31
32	The reply language is set by the user's FIRST message in this flow and never drifts. Detect that language once (e.g. Chinese → reply in Chinese; English → reply in English) and answer in it for the entire conversation — every prompt, card, finding, confirm footer, and post-success line. Switch only if the user themselves switches language.
33
34	- *Every template, card, footer, and prompt in this SKILL.md and all `references/identity-.md` is authored in English as a STRUCTURE GUIDE, not literal output.** Before sending, translate all of it into the locked language. "Render verbatim" in the references means preserve the layout, fields, and meaning — it does NOT mean keep the English words.
35	- Verbatim-keep ONLY: `#`ids, wallet addresses, tx hashes, raw tokens/enums the user typed, and CDN URLs. Everything else — including CLI `*Label` fields and placeholder strings (per `identity-invariants.md`) — is translated.

People who liked this also viewed

6 picks

Type

okx-ai

315stars61forks

View on GitHub

How to install okx-ai?

okx/onchainos-skills/okx-ai

$npx -y skills add okx/onchainos-skills --skill okx-ai

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# OKX AI (merge of okx-agent-identity + okx-agent-task + okx-task-watch + okx-agent-chat)
2
3	Single entry point for the OKX AI agent economy: ERC-8004 identity, the task marketplace, live task
4	monitoring, and agent-to-agent communication readiness. All four capabilities' content physically
5	lives in this skill's `references/` (identity-.md / task-.md / watch-.md / chat-.md). The old
6	`okx-agent-identity` / `okx-agent-task` / `okx-task-watch` / `okx-agent-chat` skill directories are
7	gone — the `onchainos` CLI's mandatory-gate output and role-guide hints were updated in lockstep to
8	point directly at this skill's `references/` paths, so there is no compatibility stub anywhere.
9
10	## Inbound envelope activation (highest priority — before anything below)
11
12	If the inbound message is a structured envelope — not free-form user text — match by shape first:
13
14	\| Envelope shape \| Action \|
15	\|---\|---\|
16	\| `{agentId, message:{source:"system", event, jobId, ...}}` \| System event → load [`references/task-core.md`](references/task-core.md) now and follow its §Activation #1. \|
17	\| `{msgType:"a2a-agent-chat", jobId, sender:{role}, ...}` \| Agent-to-agent task chat (fields at top level; `sender.role` = COUNTERPARTY, not you) → load [`references/task-core.md`](references/task-core.md) now and follow its §Activation #2. \|
18	\| Contains literal `"Read the okx-ai skill"` — the current CLI's `[SKILL_PREFETCH]` text — or the legacy `"Read the okx-agent-task skill"` / `"Read okx-agent-task/SKILL.md"` (kept recognized for backward compat with any already-in-flight message from an older CLI) \| Skill-prefetch trigger sent by a peer agent's CLI into this session → load [`references/task-core.md`](references/task-core.md) now; no other action for the prefetch message itself. \|
19
20	Do not apply the free-text Routing table below to any of these — envelope shape always wins.
21
22	## Pre-flight (BLOCKING — the FIRST thing you do, before ANY `onchainos` command)
23
24	Before the first `onchainos` command in this conversation you MUST open and follow `../okx-agentic-wallet/_shared/preflight.md` (if that file does not exist, follow `_shared/preflight.md` instead). Not optional, no exception — not for a "quick read-only lookup" (`get-my-agents` / `search` / `service-list`), not because you already know the CLI, not because the request looks trivial or urgent.
25
26	- *Session-once means per session.* A new conversation resets it. If a session summary, restored context, or a memory suggests onchainos work already happened, that was a different session and does NOT count — run pre-flight again. Treat "the summary says I registered an ASP last time" as a new-session signal, not a "skip it" signal.
27	- No `onchainos` call from memory first. Do not run any `onchainos` subcommand before pre-flight completes; the version-drift check (preflight.md step 4) is REQUIRED even when steps 1–3 are skipped.
28	- Self-catch: about to type `onchainos ...` and you haven't run pre-flight this session? → stop, run pre-flight, then proceed.
29
30	## Language Lock (apply on EVERY turn — highest priority, before routing)
31
32	The reply language is set by the user's FIRST message in this flow and never drifts. Detect that language once (e.g. Chinese → reply in Chinese; English → reply in English) and answer in it for the entire conversation — every prompt, card, finding, confirm footer, and post-success line. Switch only if the user themselves switches language.
33
34	- *Every template, card, footer, and prompt in this SKILL.md and all `references/identity-.md` is authored in English as a STRUCTURE GUIDE, not literal output.** Before sending, translate all of it into the locked language. "Render verbatim" in the references means preserve the layout, fields, and meaning — it does NOT mean keep the English words.
35	- Verbatim-keep ONLY: `#`ids, wallet addresses, tx hashes, raw tokens/enums the user typed, and CDN URLs. Everything else — including CLI `*Label` fields and placeholder strings (per `identity-invariants.md`) — is translated.

People who liked this also viewed

6 picks

Type